Program for 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC)

Time Etoile (2F) Cherie (2F) Kohaku (2F) Ruby (2F) Ruby-1 (2F) Ruby-2 (2F) Hisui (2F) Sakura (3F) Yuri (3F) Bara (3F) Rainbow (7F) Bohyoh (7F)

Monday, October 16

09:00-12:12   WS05-0: Deep Learning for Autonomous Driving WS02: Human Factors in Intelligent Vehicles WS06: Artificial Transportation Systems and Simulation     WS03-1: Eco-drive at Intersections with Connected,Cooperative and Automated Vehicle Technology         WS09: Transportation 5.0
09:10-09:40   WS05-1: Deep Learning for Autonomous Driving            
09:40-10:10   WS05-2: Deep Learning for Autonomous Driving            
10:10-10:40   WS05-3: Deep Learning for Autonomous Driving            
10:45-11:10         WS03-2: Eco-drive at Intersections with Connected,Cooperative and Automated Vehicle Technology        
11:00-11:10               WS07-0: The Third International Workshop on Intelligent Public Transports -- Toward the Next Generation of Urban Mobility
11:10-12:10   WS05-4: Deep Learning for Autonomous Driving     WS03-3: Eco-drive at Intersections with Connected,Cooperative and Automated Vehicle Technology       WS07-1: The Third International Workshop on Intelligent Public Transports -- Toward the Next Generation of Urban Mobility
11:40-12:00               WS07-2: The Third International Workshop on Intelligent Public Transports -- Toward the Next Generation of Urban Mobility
12:00-12:20                   WS07-3: The Third International Workshop on Intelligent Public Transports -- Toward the Next Generation of Urban Mobility
12:20-12:40                     WS07-4: The Third International Workshop on Intelligent Public Transports -- Toward the Next Generation of Urban Mobility  
12:55-13:00                       WS10-0: International workshop on Large-Scale Traffic Modeling and Management
13:00-13:25       WS04-0: Modelling, Analysis and Control of Intelligent Mobility-on-Demand Systems     WS01-0: Industry Panel: Connected, cooperative and automated transport         WS10-1: International workshop on Large-Scale Traffic Modeling and Management
13:10-16:30   WS05-5: Deep Learning for Autonomous Driving WS08: Behavioural Change Support Intelligent Transportation Applications     WS01-1: Industry Panel: Connected, cooperative and automated transport        
13:15-14:15   WS04-1: Modelling, Analysis and Control of Intelligent Mobility-on-Demand Systems            
13:25-13:50               WS10-2: International workshop on Large-Scale Traffic Modeling and Management
13:50-14:15               WS10-3: International workshop on Large-Scale Traffic Modeling and Management
14:00-15:20             WS07-5: The Third International Workshop on Intelligent Public Transports -- Toward the Next Generation of Urban Mobility
14:10-14:55   WS05-6: Deep Learning for Autonomous Driving     WS01-2: Industry Panel: Connected, cooperative and automated transport      
14:15-15:00   WS04-2: Modelling, Analysis and Control of Intelligent Mobility-on-Demand Systems           WS10-4: International workshop on Large-Scale Traffic Modeling and Management
14:40-15:10   WS05-7: Deep Learning for Autonomous Driving           WS10-5: International workshop on Large-Scale Traffic Modeling and Management
15:10-15:30                   WS10-6: International workshop on Large-Scale Traffic Modeling and Management
15:30-16:30     WS04-3: Modelling, Analysis and Control of Intelligent Mobility-on-Demand Systems     WS01-3: Industry Panel: Connected, cooperative and automated transport          
15:40-16:10   WS05-8: Deep Learning for Autonomous Driving              
15:45-16:10               WS10-7: International workshop on Large-Scale Traffic Modeling and Management
15:50-16:50             WS07-6: The Third International Workshop on Intelligent Public Transports -- Toward the Next Generation of Urban Mobility
16:00-17:30       WS01-4: Industry Panel: Connected, cooperative and automated transport      
16:10-17:10   WS05-9: Deep Learning for Autonomous Driving           WS10-8: International workshop on Large-Scale Traffic Modeling and Management
16:30-17:30     WS04-4: Modelling, Analysis and Control of Intelligent Mobility-on-Demand Systems          
16:35-17:00               WS10-9: International workshop on Large-Scale Traffic Modeling and Management
16:50-17:00               WS07-7: The Third International Workshop on Intelligent Public Transports -- Toward the Next Generation of Urban Mobility
17:10-17:30   WS05-10: Deep Learning for Autonomous Driving                
17:30-17:35       WS04-5: Modelling, Analysis and Control of Intelligent Mobility-on-Demand Systems                

Tuesday, October 17

09:30-10:30 KS-1: Keynote Speech I                    
11:00-12:00 KS-2: Keynote Speech II                    
13:30-15:20 SS-1: Special Session I Tu02-1: Transportation Networks (1) Tu03-1: Autonomous Driving (1)   Tu04-1: Vehicle Localization (1) Tu05-1: Modeling, Control and Simulation (1) Tu06-1: Vision and Environment Perception (1) Tu07-1: ITS (1) Tu08-1: Human Factors (1) Tu09-1: Cooperative Technology (1) Tu10-1: Big Data (1) Tu11-1: Intelligent Vehicle (1)
16:00-17:50 SS-2: Special Session II Tu02-2: Transportation Networks (2) Tu03-2: Autonomous Driving (2)   Tu04-2: Vehicle Localization (2) Tu05-2: Modeling, Control and Simulation (2) Tu06-2: Vision and Environment Perception (2) Tu01-2: Sensing, Detectors and Actuators (1) Tu08-2: Human Factors (2) Tu09-2: Cooperative Technology (2) Tu10-2: Big Data (2) Tu11-2: Intelligent Vehicle (2)

Wednesday, October 18

09:00-10:00 KS-3: Keynote Speech III                    
10:30-12:00 SS-3: Special Session III We03-1: Autonomous Driving (3)   We04-1: Vehicle Localization (3) We05-1: Modeling, Control and Simulation (3) We06-1: Vision and Environment Perception (3)   We08-1: Travel Behavior We09-1: Traffic Flow for Automated Vehicle We10-1: Big Data (3) We11-1: Intelligent Vehicle (3)
13:20-15:10 We01-2: Sensing, Detectors and Actuators (2) We02-2: Transportation Networks (3) We03-2: Autonomous Driving (4)   We04-2: Vehicle Localization (4) We05-2: Modeling, Control and Simulation (4) We06-2: Vision and Environment Perception (4)   We08-2: Commercial Vehicle We09-2: Traffic Management We10-2: Big Data (4) We11-2: Intelligent Vehicle (4)
15:40-17:10 We01-3: Sensing, Detectors and Actuators (3) We02-3: Transportation Networks (4) We03-3: Autonomous Driving (5)   We04-3: Vehicle Localization (5) We05-3: Modeling, Control and Simulation (5) We06-3: Vision and Environment Perception (5)   We08-3: ITS (2) We09-3: Public Transportation We10-3: Big Data (5) We11-3: Intelligent Vehicle (5)

Thursday, October 19

09:00-10:30 AS-1: Award Speech                    
11:00-12:50     Th03-1: Autonomous Driving (6)   Th04-1: Motion Planning (1) Th05-1: Modeling, Control and Simulation (6) Th06-1: Vision and Environment Perception (6) Th07-1: Advanced Driving Assistant System Th08-1: Connected Car (1) Th09-1: Rail Traffic Management Th10-1: Big Data (6) Th11-1: Intelligent Vehicle (6)
14:10-16:00 Th01-2: Electronic Vehicle Th02-2: Communication in ITS Th03-2: Autonomous Driving (7)   Th04-2: Motion Planning (2) Th05-2: Traffic Theory Th06-2: Vision and Environment Perception (7)   Th08-2: Connected Car (2) Th09-2: Air Traffic Management Th10-2: Big Data (7) Th11-2: Intelligent Vehicle (7)

KS-1: Keynote Speech I

SIP Automated Driving

The Cross-ministerial Strategic Innovation Promotion Program (SIP) is a newly established program for achieving science, technology and innovation as a result of the Council for Science, Technology and Innovation exercising its headquarters function to accomplish its role in leading science, technology and innovation beyond the framework of government ministries and traditional disciplines from 2014.

The Council for Science, Technology and Innovation (CSTI) selects projects that answer critical social needs and offer competitive advantage to Japanese industry and the economy as the cross-ministerial initiatives. SIP promotes focused, end-to-end research and development, from basic research to practical application and commercialization, and utilize results in regulations, systems, special wards, government procurement, etc.

3 prioritized societal issues (Energy, Next-Generation Infrastructures, Local Resources) and 11 projects have been selected as follows,

< Energy > Innovative combustion technology, Next-generation power electronics, Innovative structural materials, Energy carrier, Next-generation ocean resources development technologies < Next-Generation Infrastructures > Automated driving system, Technologies for maintenance/upgrading/ management of infrastructures, Reinforcement of resilient function for preventing and mitigating disasters, Cyber-Security for Critical Infrastructure < Local Resources> Technologies for creating next-generation agriculture, forestry and fisheries, Innovative design/manufacturing technologies Intellectual property management system facilitating strategic corporate use of research results is used. PDs (Program Directors) have been selected by invitation from among top-class leaders in industry and academy. Program Directors break through ministerial silos, managing programs from a cross-ministerial perspective. "Automated Driving System" is one of the SIP activities. PD is Seigo KUZUMAKI, Toyota Motor Company. 3 Sub-PDs are supporting him, Tateo ARIMOTO / Japan Science and Technology Agency, Masao FUKUSHIMA / Nissan Motor Co., Ltd, Yoichi SUGIMOTO / Honda Motor Co., Ltd. SIP-Automated Driving System (SIP-AD) is acting under the slogan of "In Pursuit of a Transport Society That Brings Everyone a Smile" undertaking activities with the goal of reducing traffic congestion, reducing traffic accident fatalities, and realizing, popularizing and deploying the automated driving system, as a result of utilizing automated driving technologies Research & Development plans of SIP-AD are as follows, Dynamic map, Human factors, Cyber security, Next generation transportation, Pedestrian traffic safety using Vehicle to Pedestrian communication, V2X for AD cars such as Machine to Machine / Infrastructure communication, Low speed automated mini-buses, so on. These activities are reported to and checked by "Promoting Committee and Working Group" by the industry experts, government and academia members. In this key note speech, the over-view of SIP-AD project is introduced.

KS-2: Keynote Speech II

From the World's 1st Car Navigation, towards Connected and Automated Driving in the future

Aiming at the collision-free society with the joy and freedom of mobility, Honda has been proactively working on research and developments of intelligent vehicle technologies. As one of its achievements, the World's 1st car navigation system was introduced in 1981, which localizes a subject vehicle's position using dead reckoning with a high precision gas-rate gyro and shows it to a driver with a map on a CRT. It was evolved to one combined also with GNSS and a digital map later, which is the basis of modern car navigation systems. Further, it was connected to servers, uploading floating car data, and made it possible to provide precise real-time traffic information. This map and localization technology has become one of the essential technologies for ITS and Automated Driving. In parallel, Honda has been also developing ADAS (Advanced Driver Assistance System) technologies with environmental sensors such as radars and cameras, and introduced the World's 1st AEB (Automatic Emergency Braking) in 1983, which is also one of the essential technologies for Automated Driving. This presentation reviews the history of the technologies for navigation and ADAS, which Honda has been working on, and introduces prospects on Connected and Automated Driving in the future.

SS-1: Special Session I

International Collaborative Research on Automated Vehicles

Automated and Connected Vehicle technologies CV technologies are viewed as the next generation of Intelligent Transportation Systems that hold promise to provide substantial improvements in safety, mobility, and the environment. The development of Connected and Automated vehicles have gaining momentum. Substantial public and private sector resources are now being invested in Europe, Asia, Europe and the United States, and elsewhere in the world. In this increasingly globalized world, scientists, engineers and innovators must be able to connect, collaborate and create with counterparts around the world. This session discuss about a few new initiatives involving international collaborative research on autonomous driving, covering the areas of trajectory planning, sensing and localization and functional safety. Panelist and topics:

  1. Research on Trajectory Planning under the Chair Drive for All
    Arnaud de La Fortelle, Mines ParisTech (France)

  2. Functional Safety of Automated Driving Systems and AI/Machine Learning - A Dialogue
    Ching-yao Chan, California PATH Program, University of California at Berkeley

  3. V2V Cooperation and Interaction with VRUs in the BRAVE and AutoDrive Projects
    Miguel A. Sotelo Vázquez, University of Alcalá

  4. Integrated environmental sensing and localization
    Shunsuke Kamijo, the University of Tokyo

Tu02-1: Transportation Networks (1)

Lane-Level Route Planning Based on a Multi-Layer Map Model
External Cost Continuous Type Wardrop Equilibria in Routing Games
Infinite-Horizon Average-Cost Markov Decision Process Routing Games
Multi-period Planning of Road Trips in a Cooperative Environment
Bi-Objective Eco-Routing in Large Urban Road Networks

Tu03-1: Autonomous Driving (1)

Cognitive Map-based Model: Toward a Developmental Framework for Self-driving Cars
Trajectory Planning of Automated Vehicles in Tube-like Road Segments
High-Speed Trajectory Planning for Autonomous Vehicles Using a Simple Dynamic Model
Trajectory Planning Under Vehicle Dimension Constraints Using Sequential Linear Programming
How Good is My Prediction? Finding a Similarity Measure for Trajectory Prediction Evaluation

Tu04-1: Vehicle Localization (1)

Failure Detection for Laser-based SLAM in Urban and Peri-Urban Environments
Linear-complexity Stochastic Variational Bayes Inference for SLAM
Autonomous Vehicle Self-Localization Based on Probabilistic Planar Surface Map and Multi-channel LiDAR in Urban Area
GPS-independent Localization for Off-road Vehicles Using Ultra-wideband (UWB)
Joint Graph Optimization Towards Crowd Based Mapping

Tu05-1: Modeling, Control and Simulation (1)

Structural Observability of Multi-Lane Traffic with Connected Vehicles
Multi-lane Reduction: A Stochastic Single-lane Model for Lane Changing
Safety and Mobility Trade-off Assessment of a Microscopic Variable Speed Limit Model
Comparison of Feedback Linearization & Model Predictive Techniques for Variable Speed Limit Control
Partial Speed Trajectory Optimization for Urban Rail Vehicle with Considerations on Motor Efficiency

Tu06-1: Vision and Environment Perception (1)

Cyclist Detection in LIDAR Scans Using Faster R-CNN and Synthetic Depth Images
Pedestrian Intention Recognition by Means of a Hidden Markov Model and Body Language
Natural Vision Based Method for Predicting Pedestrian Behaviour in Urban Environments
VRID-1: A Basic Vehicle Re-identification Dataset for Same Type Vehicles
Fast On-road Object Detector with the Fusion of Object and Scene CNN Features

Tu07-1: ITS (1)

Simulation of Cut-In by Manually Driven Vehicles in Platooning Scenarios
New Estimation of Pedestrian's Rushing Out in Front of Cars by Pressure and Direction Sensors in ITS
Reducing the Intrusive Driving Behaviour in LDAS Using Machine Learning Approach
Implementation of a Real-Time Data Driven System to Provide Queue Alerts to Stakeholders
How Safe is Automated Driving? Human Driver Models for Safety Performance Assessment

Tu08-1: Human Factors (1)

Modelling the Effect of Human Anticipation on Driving Maneuvers in Lane Changing Process
Driving Data Distribution of Human Drivers in Urban Driving Condition
Using Eye-tracking Technology and Google Street View to Understand Cyclists' Perceptions
Drivers' Avoidance Patterns in Near-Collision Intersection Conflicts
Actions Speak Louder: Effects of a Transforming Steering Wheel on Post-Transition Driver Performance

Tu09-1: Cooperative Technology (1)

Autonomous Cooperative Driving Using V2X Communications in Off-Road Environment
Eco-Platooning of Autonomous Electrical Vehicles Using Distributed Model Predictive Control
Forward-looking Automated Cooperative Longitudinal Control
Intra-Platoon Vehicle Sequence Optimization for Eco-Cooperative Adaptive Cruise Control
Optimization of Vehicle Connections in V2V-based Cooperative Localization

Tu10-1: Big Data (1)

Vessel Traffic Flow Separation-Prediction Using Low-Rank and Sparse Decomposition
Data-driven Multi-Agent System for Maritime Traffic Safety Management
Summarizing Large Scale 3D Point Cloud for Navigation Tasks
Integration of GPS and Satellite Images for Detection and Classification of Fleet Hotspots
Big-video Mining of Road Appearances in Full Spectrums of Weather and Illuminations

Tu11-1: Intelligent Vehicle (1)

LIDAR-based Driving Path Generation Using Fully Convolutional Neural Networks
Accurate Vertical Road Profile Estimation Using v-Disparity Map and Dynamic Programming
Dynamic Vehicle Velocity Prediction Based on Sensor Data Fusion for Enabling Predictive Functions
Real-Time Lane Detection Using Spatio-Temporal Incremental Clustering
Framework for Control and Deep Reinforcement Learning in Traffic

SS-2: Special Session II

Naturalistic Driving Data Acquisition for Smart Mobility Application

Session abstract: Recently,naturalistic driving data becomes more important roles, not only for investigation of the misbehavior of drivers to develop advanced driver assistant systems (ADAS), but also for development of artificial intelligence for smart mobility related fields. So far, deep learning of big data have been used for interpreting sensor and image data of other vehicles, pedestrians, bicycles, ans so on. Similar learning approach can be applicable to judgement, actions, and evaluations by collecting and learning many traffic situations and drivers' actions for each situation. This special session introduce latest research activities of naturalistic driving study and the platform development for the self driving cars and other applications.

  1. Naturalistic Driving Studies for Driver Assistance and Autonomous Driving: Team LISA perspective
    Mohan M. Trivedi(1), Kevan Yuen(1), Akshay Rangesh(1)
    (1) Laboratory for Intelligent and Safe Automobiles, University of California, San Diego

  2. Developing Driving Behavior Database for Naturalistic Driving Study
    Chiyomi Miyajima(1) and Kazuya Takeda(1)
    (1) Institutes of Innovation for Future Society, Nagoya University

  3. Automan: An Open Service Platform for Autonomous Driving AI
    Shinpei Kato(1), Kazumasa Sakiyama(1), Yuki Tsuji(1), Shunya Seiya(1), Daisuke Fukutomi(1), and Yuki Iida(1)
    (1) University of Tokyo

  4. An Open Platform for Driving and Lifelog Data Collection and Utilization
    Hirofumi Aoki(1), Takahiro Tanaka(1), Masayuki Shimizu(1), Taisuke Sato(2), and Yuki Umemoto(3)
    (1) Institutes of Innovation for Future Society, Nagoya University (2) Kurusugawa Computer Inc. (3) Arc Co., Ltd.

Tu01-2: Sensing, Detectors and Actuators (1)

Stereo Based 3D Reconstruction of Potholes by a Fast, Hybrid Matching Scheme
All Weather Road Edge Identification Based on Driving Video Mining
Introduction to Rain and Fog Attenuation on Automotive Surround Sensors
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor Setups

Tu02-2: Transportation Networks (2)

Joint Perimeter and Signal Control of Urban Traffic via Network Utility Maximization
Multimodal Transit Scheduler: An Actor-based Concurrent Approach
Train Scheduling with Short Turning Strategy for an Urban Rail TransitLine with Multiple Depots
Real-time Estimation of Aggregated Traffic States of Multi-region Urban Networks

Tu03-2: Autonomous Driving (2)

Towards a Skill- And Ability-Based Development Process for Self-Aware Automated Road Vehicles
Robust Long-Range Teach-and-Repeat in Non-Urban Environments
Generation and Validation of Virtual Point Cloud Data for Automated Driving Systems
How MuCAR Won the Convoy Scenario at ELROB 2016
When to Use What Data Set for Your Self-Driving Car Algorithm: An Overview of Publicly Available Driving Datasets

Tu04-2: Vehicle Localization (2)

Utilizing Semantic Visual Landmarks for Precise Vehicle Navigation
Behavior-Based Relative Self-Localization in Intersection Scenarios
Ego-Lane Estimation by Modeling Lanes and Sensor Failures
Cross-season Vehicle Localization Using Bag of Local 3D Features
Applying Low Cost WiFi-based Localization to In-Campus Autonomous Vehicles

Tu05-2: Modeling, Control and Simulation (2)

Visualizing Vehicle Arrivals in Coordinated Arterials Using a Colored PCD Concept
Estimating Travel Time Distributions Using Copula Graphical Lasso
Relocation in Car Sharing Systems with Shared Stackable Vehicles: Modelling Challenges and Outlook
Ridepooling with Trip-Chaining in a Shared-Vehicle Mobility-on-Demand System
Reducing Range Estimation Uncertainty with a Hybrid Powertrain Model and Online Parameter Estimation

Tu06-2: Vision and Environment Perception (2)

ORB-SLAM Based Semi-Dense Mapping with Monocular Camera
Improving the Performance of ADAS Application in Heterogeneous Context: a Case of Lane Detection
Pollution Discrimination on Rail Surface for Adhesion Evaluation Using Hyperspectral Signatures
Free-hand Gesture Recognition with 3D-CNNs for In-car Infotainment Control in Real-time
Landmarks Based Human-like Guidance for Driving Navigation in an Urban Environment

Tu08-2: Human Factors (2)

Optimizing Interaction Between Humans and Autonomy via Information Constraints on Interface Design
Driving Behavior Classification Based on Sensor Data Fusion Using LSTM Recurrent Neural Networks
Deployment of Public Bus HMI Displays for Intelligent Junction Safety: A Field Trial
Distracted Pedestrians Crossing Behaviour: Application of an Immersive Head Mounted Virtual Reality
Pedestrian Positioning in Urban Environment by Integration of PDR and Traffic Mode Detection

Tu09-2: Cooperative Technology (2)

Cooperative Parking Search: Reducing Travel Time by Information Exchange Among Searching Vehicles
Smart Mobility for All - A Global Federated Market for Mobility-as-a-Service Operators
Multiagent-based Cooperative Vehicle Routing Using Node Pressure and Auctions
Cooperative Starting Intention Detection of Cyclists Based on Smart Devices and Infrastructure
Enhanced Vehicle Positioning in Cooperative ITS by Joint Sensing of Passive Features

Tu10-2: Big Data (2)

A Privacy Design Problem for Sharing Transport Service Tour Data
Validation of a Per-Lane Traffic State Estimation Scheme for Highways with Connected Vehicles
Time of Arrival Cumulative Probability in Public Transportation Travel Assistance
Big Data Management and Processing in the Context of the System Wide Information Management
Acquisition of Precise Probe Vehicle Data in Urban City Based on Three-Dimensional Map Aided GNSS

Tu11-2: Intelligent Vehicle (2)

Identifying Major Accident Scenarios in Intersection and Evaluation of Collision Warning System
Driver's Gaze Prediction in Dynamic Automotive Scenes
Inertial Sensor Driven Smartphone and Automobile Coordinate System Alignment
Driver Classification in Vehicle-Following Behavior by Using Dynamic Potential Field Method
Systematic Literature Review on Driving Behavior

KS-3: Keynote Speech III

Smart Cities: An Intelligent Vehicles Perspective

Smart City related initiatives have been gaining popularity around the world. These all provide a showcase for technologists to test their ideas and developments related to ITS (Intelligent Transportation Systems) and IV (Intelligent Vehicles) and understand both the practical deployment issues and the acceptance by the public.

One such testbed/deployment program (possibly one of the largest) is in Columbus, Ohio, USA, where the city has won a large ($50M) grant from the US DoT, almost tripled by cost sharing. An aspect of this project has been understanding the maturity and deployability of numerous technologies and use cases that we all hear about. What is ready to run (not for a couple of demo days, but continuously)? And what is still in a development/proof of concept stage?

After a brief look at the subprojects considered for Columbus deployment, I will try to address the question of "what is a direct application of general ITS/IV R&D?" and "what is special about the Smart City that can orient our IV research?"

Smart Cities can collect and distribute extensive data helping mobility and safety. We can specifically think of use cases in automated parking, in complex intersections and specialized transportation. One aspect that is important in cities is the dense population of pedestrians, and their interaction with automated vehicles. I shall outline our work at the Ohio State University, both in developing small platforms for providing mobility to the impaired, and also the safe motion of such platforms in dense pedestrian environments.

SS-3: Special Session III

QZSS: Quasi-Zenith Satellite System

This special session focuses the recent developments in QZSS, Quasi-Zenith Satellite System. The QZSS is a regional navigation satellite system which cooperates with GPS and improve position accuracy. Presentations from the government and contractors will cover the latest program status, launch of navigation satellites, navigation performance, payload design/characteristics, technical validation results, and application development activities. Attending the special session, you will be fully informed about the QZSS to be operational in 2018.

  1. The Latest Status of QZSS: Service, System, Applications
    Satoshi Kogure, National Space Policy Secretariat of Japan

  2. High Accurate Centimeter-level Positioning Solutions using Quasi-Zenith Satellite System
    Ryoichiro Yasumitsu, Mitsubishi Electric Corp.

  3. Japanese SBAS Service: Status and Future Plan
    Masashi Giho, Civil Aviation Bureau, Ministry of Land, Infrastructure, Transport and Tourism

  4. Some QZSS Demonstrations in Japan
    Yoshiyuki Murai, NEC Corp.

We03-1: Autonomous Driving (3)

A Multi-period Analysis of Taxi Drivers' Behaviors Based on GPS Trajectories
Predicting Driver Left-Turn Behavior from Few Training Samples Using a Maximum-a-posteriori Method
Interaction-Aware Driver Maneuver Inference in Highways Using Realistic Driver Models
Simultaneous Policy Learning and Latent State Inference for Imitating Driver Behavior

We04-1: Vehicle Localization (3)

Lane-Level Vehicle Self-Localization in Under-Bridge Environments Based on Multi-Level Sensor Fusion
Vehicle Trajectory and Lane Change Prediction Using ANN and SVM Classifiers
Autonomous Driving Based on Accurate Localization Using Multilayer LiDAR and Dead Reckoning
LIDAR Scan Matching in Off-Road Environment

We05-1: Modeling, Control and Simulation (3)

Online State and Multidimensional Parameter Estimation for a Macroscopic Model of a Traffic Junction
A Multi-method Simulation of a High-frequency Bus Line
Dynamic Signal Optimization for Traffic Networks
Distributed State Observer Based Traffic Density Estimation of Urban Freeway Network

We06-1: Vision and Environment Perception (3)

Region Segmentation Using LiDAR and Camera
Super-sensor for 360-degree Environment Perception: Point Cloud Segmentation Using Image Features
Joint Spatial-Temporal Saliency with Discriminative Correlation Filters
Vertical Digital Beamforming Versus Vertical Doppler Beam Sharpening

We08-1: Travel Behavior

Reconstructing Fixed Time Traffic Light Cycles by Camera Data Analytics
A Hidden Markov Model for Route and Destination Prediction
Model Based Cyclist Energy Prediction
Traffic Optimization via Road Pricing for Queuing and Flow Congestion

We09-1: Traffic Flow for Automated Vehicle

A Cooperative Intersection Control for Automated Vehicles
Rating Cooperative Driving: A Scheme for Behavior Assessment
A Time Gap-Based Spacing Policy for Full-Range Car-Following
Impact of Connected and Automated Vehicles on Traffic Flow

We10-1: Big Data (3)

Analysis of Speed Characteristics of Urban Expressways Under Rainy Conditions
Predicting Hazardous Events in Work Zones Using Naturalistic Driving Data
Identifying Passenger Distribution Corridor for the Transportation Hub Based on Mobile Phone Data
Basic Study of the Estimation of the Cognitive Level Using Senior Driver's Driving Behaviors

We11-1: Intelligent Vehicle (3)

Neural Network for Lane Change Prediction Assessing Driving Situation, Driver Behavior and Vehicle Movement
Convolution Neural Network-based Lane Change Intention Prediction of Surrounding Vehicles for ACC
Time-to-Lane-Change Prediction with Deep Learning
Intent Detection and Semantic Parsing for Navigation Dialogue Language Processing

We01-2: Sensing, Detectors and Actuators (2)

Efficient Ground Object Segmentation in 3D LIDAR Based on Cascaded Mode Seeking
Precise Mobile Laser Scanning for Urban Mapping Utilizing 3D Aerial Surveillance Data
Prediction of Driving Behavior Based on Sequence to Sequence Model with Parametric Bias
Multiple Moving Target Tracking with Hypothesis Trajectory Model for Autonomous Vehicles
Automated Rotational Calibration of Multiple 3D LIDAR Units for Intelligent Vehicles

We02-2: Transportation Networks (3)

Multiple Imputation for Incomplete Traffic Accident Data Using Chained Equations
Auto-Adaptive Multi-Hop Clustering for Hybrid Cellular-Vehicular Networks
Unmanned Air Traffic Network Design Concepts
How Far is Traffic from User Equilibrium?
Structure of Traffic Information Related to Suddenly Occurring Events on Expressway

We03-2: Autonomous Driving (4)

Implementation of Dynamic Boundary on Multiple Kalman Tracking Using Radar
Automated Vehicle System Architecture with Performance Assessment
Minimizing Long Vehicles Overhang Exceeding the Drivable Surface via Convex Path Optimization
Multi Object-based Predictive Virtual Lane
Negotiation of Drivable Areas of Cooperative Vehicles for Conflict Resolution

We04-2: Vehicle Localization (4)

A Particle Filter for Vehicle Tracking with Lane Level Accuracy Under GNSS-Denied Environments
Object Tracking based on an Extended Kalman Filter in High Dynamic Driving Situations
Estimating Localization Uncertainty Using Multi-hypothesis Map-Matching on High Definition Road Maps
GNSS Mulitpath Detection Using a Machine Learning Approach
Hybrid Urban Navigation for Smart Cities

We05-2: Modeling, Control and Simulation (4)

Randomness in Transportation Utility Models
Adaptive Traffic Light Control on Highway Entrances
String Stability of Heterogeneous Platoons with Non-connected Automated Vehicles
Constructing Multi-Labelled Decision Trees for Junction Design Using the Predicted Probabilities
Calibration and Evaluation of Car Following Models Using Real-World Driving Data

We06-2: Vision and Environment Perception (4)

A Context Aware and Video-Based Risk Descriptor for Cyclists
Exciting Trajectories for Extrinsic Calibration of Mobile Robots with Cameras
Wide-baseline Omni-Stereo at Junctions: Extrinsic Auto-Calibration, Trajectory and Speed Estimation
Classification and Tracking of Traffic Scene Objects with Hybrid Camera Systems
Transferring Visual Knowledge for a Robust Road Environment Perception in Intelligent Vehicles

We08-2: Commercial Vehicle

A Multi-objective Model for Dial-a-Ride Problems with Service Quality and Eco-efficiency
Multi-Criterion Optimization of Heavy-Duty Powertrain Design
Vehicle Weight Estimation Based on Piezoelectric Sensors Used at Traffic Enforcement Cameras
Longitudinal Evaluation of the System Performance of a Junction Safety System with Public Buses
Fuel Consumption Prediction for Heavy-duty Vehicles Using Digital Maps

We09-2: Traffic Management

Hierarchical Coordination of Trains and Traction Substation Storages for Energy Cost Optimization
A Speed Trajectory Optimization Model for Rail Vehicles Using Mixed Integer Linear Programming
Supervisory Multi-Class Event-Triggered Control for Congestion and Emissions Reduction in Freeways
Optimization for Train Speed Trajectory Based on Pontryagin's Maximum Principle
ART-UTC: An Adaptive Real-Time Urban Traffic Control Strategy

We10-2: Big Data (4)

Realization of Highly Anticipative Driving in a Partially Connected Vehicle Environment
Comparison of Non-linearities in Urban & Highway Traffic Data
Integration of Loop and Probe Data for Traffic State Estimation on Freeway and Arterial Links
Detection Method of Wide-Area Incident with Massive Probe Vehicle Data
Network-Wide Link Flow Estimation Through Probe Vehicle Data Supported Count Propagation

We11-2: Intelligent Vehicle (4)

Personalized Maneuver Prediction at Intersections
Step Up/Down Motion for a Four-Wheel-Type Vehicle
Robust Multi-Model Longitudinal Tire-force Estimation Scheme: Experimental Data Validation
Driver Adaptive Predictive Velocity Control
Energy and Mobility Benefits from Connected Ecodriving for Electric Vehicles

We01-3: Sensing, Detectors and Actuators (3)

Low Complexity Techniques for Robust Real-time Traffic Incident Detection
Anomaly Detection for Automotive Visual Signal Transition Estimation
Challenges in Head Pose Estimation of Drivers in Naturalistic Recordings Using Existing Tools
Probabilistic Estimation of the Driver's Gaze from Head Orientation and Position

We02-3: Transportation Networks (4)

Transport Infrastructure Optimization Method Based on a Memetic Algorithm
Fast Identification of Critical Roads by Neural Networks Using System Optimum Assignment Information
Impact of Mobility-on-Demand on Traffic Congestion: Simulation-basedStudy
An Adaptive Control Scheme for Local and Coordinated Ramp Metering

We03-3: Autonomous Driving (5)

Ensuring Drivability of Planned Motions Using Formal Methods
Optimal Path Selection in a Continuous-Time Route Reservation Architecture
Comparison of Trajectory Tracking Controllers for Autonomous Vehicles
Exploiting Dream-Like Simulation Mechanisms to Develop Safer Agents for Automated Driving

We04-3: Vehicle Localization (5)

Efficient Global Localization Using Vision and Digital Offline Map
Momo: Monocular Motion Estimation on Manifolds
Compensating Drift of Mono-Visual Odometry Using Road Direction Sign Database
Map-based Curvilinear Coordinates for Autonomous Vehicles

We05-3: Modeling, Control and Simulation (5)

Rollover Prevention Using Active Suspension System
Sensitivity of Traffic Accidents Mitigation Policies Based on Fuzzy Modeling: A Case Study
Path Planning for Wheel Loaders: a Discrete Optimization Approach
Towards a Qualitative Spatial Model for Road Traffic in Urban Environment

We06-3: Vision and Environment Perception (5)

Detecting the Road Surface Condition by Using Mobile Crowdsensing with Drive Recorder
Real Time Driver Body Pose Estimation for Novel Assistance Systems
A Hybrid Approach of Candidate Region Extraction for Robust Traffic Light Recognition
Fast Reducing Perspective Distortion for Road Marking Recognition

We08-3: ITS (2)

Congestion Barcodes: Exploring the Topology of Urban Congestion Using Persistent Homology
Learning to Tell Brake and Turn Signals in Videos Using CNN-LSTM Structure
A Hierarchical Co-Simulation Optimization Control System for Multimodal Freight Routing

We09-3: Public Transportation

User Context Estimation for Public Travel Assistance and Intelligent Service Scheduling
Optimal Design of Transit Demand Management Strategies
Intelligent Traffic Light Control Using Distributed Multi-agent Q Learning
Automatic Train Supervision for a CBTC Suburban Railway Line Using Multiobjective Optimization

We10-3: Big Data (5)

A New Modelling Framework over Temporal Graphs for Collaborative Mobility Recommendation Systems
Impact of Surrounding Cyclists on Car Driver Behavior Recognition at Roundabouts
Characterizing Activity Patterns Using Co-Clustering and User-Activity Network
Mobility Knowledge Discovery to Generate Activity Pattern Trajectories

We11-3: Intelligent Vehicle (5)

Simultaneous Tracking and Shape Estimation Using a Multi-Layer Laserscanner
Fog Detection for De-fogging of Road Driving Images
Parking Slots Detection on the Equivalence Sphere with a Progressive Probabilistic Hough Transform
Learning and Predicting On-road Pedestrian Behavior Around Vehicles

AS-1: Award Speech

Th03-1: Autonomous Driving (6)

Towards Affordable On-track Testing for Autonomous Vehicle - A Kriging-based Statistical Approach
Validation of Collision Frequency Estimation Using Extreme Value Theory
TrafficNet: An Open Naturalistic Driving Scenario Library
Benchmark for Road Marking Detection: Dataset Specification and Performance Baseline
V2V and On-Board Sensor Fusion for Road Geometry Estimation

Th04-1: Motion Planning (1)

Interaction-Aware Occupancy Prediction of Road Vehicles
Determining the Maximum Time Horizon for Vehicles to Safely Follow a Trajectory
A Leader-Following Approach Based on Probabilistic Trajectory Estimation and Virtual Train Model
Trajectory Optimization for Autonomous Overtaking with Visibility Maximization
Static Free Space Detection with Laser Scanner Using Occupancy Grid Maps

Th05-1: Modeling, Control and Simulation (6)

Optimal Powertrain Control of a Heavy-Duty Vehicle Under Varying Speed Requirements
Quantifying the Impact of Limited Information and Control Robustness on Connected Automated Platoons
Robust Tube-Based MPC for Automotive Adaptive Cruise Control Design
Method for Comprehensive and Adaptive Risk Analysis for the Development of Automated Driving
Object Detection in Adaptive Cruise Control Using Multi-Class Support Vector Machine

Th06-1: Vision and Environment Perception (6)

Characterization and Simulation of the Effect of Road Dirt on the Performance of a Laser Scanner
Saliency Guided Region Proposal Network for CNN Based Object Detection
DepthCN: Vehicle Detection Using 3D-LIDAR and ConvNet
The Volcanormal Density for Radar-Based Extended Target Tracking

Th07-1: Advanced Driving Assistant System

Multi-Level Vehicle Dynamics Modeling and Export for ADAS Prototyping in a 3D Driving Environment
Torque Based Lane Change Assistance with Active Front Steering
Testing of Autonomous Vehicles Using Surrogate Models and Stochastic Optimization
A Hybrid Fusion Based Frontal-Lateral Collaborative Pedestrian Detection and Tracking
Comparative Analysis on Information Fusion Conflict Redistribution and Driving Risk Classification

Th08-1: Connected Car (1)

Towards a Real-Time Driver Identification Mechanism Based on Driving Sensing Data
Robust Model Predictive Cooperative Adaptive Cruise Control Subject to V2V Impairments
Automatic Background Filtering and Lane Identification with Roadside LiDAR Data
Cellular Communication of Traffic Signal State to Connected Vehicles for Arterial Eco-Driving
Spatial Stochastic Vehicle Traffic Modeling for VANETs

Th09-1: Rail Traffic Management

Improved Control Strategy of Energy Storage System Considering Train Operation States
Comparison of Multi-Objective Optimization Approaches for the Train Load Planning Problem
Performance Analysis and Evaluation of EDGE System for High-speed Railway
Prediction Algorithms for Train Arrival Time in Urban Rail Transit
Scene-segmentation Based Control Strategy of Energy Storage System for Urban Railway

Th10-1: Big Data (6)

Estimating Urban Road Traffic States Using Mobile Network Signaling Data
Traffic State Estimation Method with Efficient Data Fusion Based on the Aw-Rascle-Zhang Model
Short-term Travel Time Prediction by Deep Learning: A Comparison of Different LSTM-DNN Models
Road Network State Estimation Using Random Forest Ensemble Learning

Th11-1: Intelligent Vehicle (6)

Autonomous Braking System via Deep Reinforcement Learning
Predicting Steering Actions for Self-Driving Cars Through Deep Learning
Integrating End-to-End Learned Steering into Probabilistic Autonomous Driving
Multi-Point Turn Decision Making Framework for Human-Like Automated Driving
Looking Ahead: Anticipatory Interfaces for Driver-Automation Collaboration

Th01-2: Electronic Vehicle

Can Small Smart Swappable Battery EVs Outperform Gas Powertrain Economics?
A Simulation-based Heuristic for City-scale Electric Vehicle Charging Station Placement
On Charge Point Anxiety and the Sharing Economy
Energy Consumption Model of Electric Scooter for Routing Applications: Experimental Validation

Th02-2: Communication in ITS

Vehicular Dynamics Based Plausibility Checking
Roadside Units Deployment in Hybrid VANETs with Synchronous Communication
Modified K-best Receiver for Multi-antenna Vehicular Networks
Research on Multi - Agent Traffic Signal Control System Based on VANET Information
A Memetic Algorithm Approach to Deploy RSUs Based on the Gamma Deployment Metric

Th03-2: Autonomous Driving (7)

Interactive Ramp Merging Planning in Autonomous Driving: Multi-Merging Leading PGM (MML-PGM)
Safe Autonomous Lane Change in Dense Traffic
Towards Tactical Behaviour Planning Under Uncertainties for Automated Vehicles in Urban Scenarios
Personalization in Advanced Driver Assistance Systems and Autonomous Vehicles: A Review
Aggressive Vehicle Control Using Polynomial Spiral Curves

Th04-2: Motion Planning (2)

Maneuver Planning for AutonomousVehicles, with Clothoid Tentacles for LocalTrajectory Planning
Using Evidential Occupancy Grid for Vehicle Trajectory Planning Under Uncertainty with Tentacles
Constrained Iterative LQR for On-Road Autonomous Driving Motion Planning
HC Steer: A Novel Extend Fct. for Sampling-Based Nonholonomic Motion Planning in Tight Environments
Automated Driving: Safe Motion Planning Using Positively Invariant Sets

Th05-2: Traffic Theory

Urban Network Travel Time Prediction via Online Multi-Output Gaussian Process Regression
Fundamental Diagram Estimation Using GPS Trajectories of Probe Vehicles
Short-term Traffic Flow Prediction with LSTM Recurrent Neural Network
Intersection Analysis Using the Ideal Flow Model

Th06-2: Vision and Environment Perception (7)

Deep Semantic Segmentation for Automated Driving: Taxonomy, Roadmap and Challenges
Convolutional Gated Recurrent Networks for Video Semantic Segmentation in Automated Driving
A Combined Recognition and Segmentation Model for Urban Traffic Scene Understanding
Continuous Stereo Camera Calibration in Urban Scenarios

Th08-2: Connected Car (2)

A Car-following Model for Connected Vehicles Under the Bidirectional-leader Following Topology
A Simple Distributed Algorithm for Lightless Intersection Control Based on Non-linear Interactions
Evaluation of an MPC Strategy for Motorway Traffic Comprising Connected and Automated Vehicles
Traffic Responsive Intersection Control Algorithm Using GPS Data
Trajectory Prediction of Traffic Agents at Urban Intersections Through Learned Interactions

Th09-2: Air Traffic Management

Multi-objective Fuzzy Rule-Based Prediction and Uncertainty Quantification of Aircraft Taxi Time
Key Distribution Scheme for Aircraft Equipped with Secure ADS-B IN
A Type-2 Fuzzy Modelling Framework for Aircraft Taxi-Time Prediction
Fast and Near-optimal Trajectory Planning for Fixed-wing UAVs in Urban Area

Th10-2: Big Data (7)

A Holistic Framework for Acquisition, Processing and Evaluation of Vehicle Fleet Test Data
A Continuum Approach to Assessing the Impact of Spatio-Temporal EV Charging to Distribution Grids
Application of Data Analytics to Transport Corridor Diagnostics and Performance Benchmarking
Counting Public Transport Passenger Using WiFi Signatures of Mobile Devices
A Convolutional Neural Network for Traffic Information Sensing from Social Media Text

Th11-2: Intelligent Vehicle (7)

Introducing ASIL Inspired Dynamic Tactical Safety Decision Framework for Automated Vehicles
Analysis of Potential Co-Benefits for Bicyclist Crash Imminent Braking Systems
Collision Risk Assessment for Possible Collision Vehicle in Occluded Area Based on Precise Map
Formulation of Deep Reinforcement Learning Architecture Toward Autonomous Driving for On-Ramp Merge
Adaptability of Automated Driving Systems to the Hazardous Nature of Road Networks

WS01-0: Industry Panel: Connected, cooperative and automated transport

Opening

WS01-1: Industry Panel: Connected, cooperative and automated transport

Paper presentations
Vision Based Lane Change Detection Using True Flow Features
Leveraging Cloud Intelligence for Hybrid Vehicular Communications

WS01-2: Industry Panel: Connected, cooperative and automated transport

Invited speeches 1

Invited speeched: Haesik Kim, VTT (14:10-14:25); Satoshi Nagata, NTT DOCOMO (14:25-14:40); Feiyue Wang , Huawei (14:40-14:55)

WS01-3: Industry Panel: Connected, cooperative and automated transport

Invited speeches 2

Invited speeches: Yasin Ferdous Ahmed Khan Ericsson (15:30-15:45); Onur Altintas, Toyota (15:45-16:00)

WS01-4: Industry Panel: Connected, cooperative and automated transport

Industry Panel

Panelists: Tim Leinmüller, Denso / Onur Altintas, Toyota / Satoshi Nagata, NTT DOCOMO / Feiyue Wang, Huawei / TBD China Mobile / Yasin Ferdous Ahmed Khan, Ericsson / Koichi Sakai, University of Tokyo / Meng Lu, Dynniq

WS02: Human Factors in Intelligent Vehicles

Hypovigilance in Limited Self-Driving Automation: Peripheral Visual Stimulus for a Balanced Level of Automation and Cognitive Workload
Adaptive Behaviour Selection for Autonomous Vehicle Through Naturalistic Speed Planning
Cost-Efficient Brainwave Controller for Automated Vehicles Route Decisions
Driver's Decision Analysis in Terms of Pedestrian Attributes -A Case Study in Passing by a Pedestrian-
Coffee break
Effect on Driving Performance of Two Visualization Paradigms for Rear-End Collision Avoidance
Individualized Driver Action Anticipation Using Deep (Bidirectional) Recurrent Neural Network
Evaluating Passenger Characteristics for Ride Comfort in Autonomous Wheelchairs
A Collision Mitigation Strategy for Intelligent Vehicles to Compensate for Human Factors Affecting Manually Driven Vehicles

WS03-1: Eco-drive at Intersections with Connected,Cooperative and Automated Vehicle Technology

Signal Plan Stabilization to Enable Eco-Driving
Cluster-Wise Cooperative Eco-Approach and Departure Application Along Urban Signalized Arterials
Connected and Autonomous Vehicles Coordinating Method at Intersection Utilizing Preassigned Slots
Coffee break

WS03-2: Eco-drive at Intersections with Connected,Cooperative and Automated Vehicle Technology

Invited Session : An Extensive Investigation on Cooperative Eco-approach Controller Under Partially Connected and Automated Vehicle Environment

This study evaluated the performance of a cooperative eco-approach control system at signalized intersections under partially connected and automated vehicles environment. The controller was recently published and is the first eco-approach controller that is able to function with existence of surrounding human-driven traffic. The purpose of this work is to further conduct an extensive test on the controller in order to identify the room for improvement. Two different networks were tested, including an isolated signalized intersection and a corridor with two signalized intersections. The measurements of effectiveness (MOE) adopted are throughput, fuel consumption and CO2 emissions. All the before-and-after MOEs have been tested for statistical significance using t-tests, and the Pearson correlation of the MOEs with respect to various traffic-related and infrastructure-related factors was assessed to identify factors that significantly impact controller's performance. The results indicate the eco-approach control generally reduces fuel consumption and emission without harming mobility, and can be equipped at isolated signalized intersections or on signalized arterials. The performance of eco-approach control is affected by several traffic-related and infrastructure-related factors, including market penetration rate of connected and automated vehicles, congestion level, green ratio of traffic signal and minimum speed of connected and automated vehicle. Excessive small distance between adjacent intersections causes significant gating effect and has negative impact on the performance of eco-approach control.

WS03-3: Eco-drive at Intersections with Connected,Cooperative and Automated Vehicle Technology

Oral Session 2
Multi-Camera System for Traffic Light Detection: About Camera Setup and Mapping of Detections

WS04-0: Modelling, Analysis and Control of Intelligent Mobility-on-Demand Systems

Welcome and opening remarks

WS04-1: Modelling, Analysis and Control of Intelligent Mobility-on-Demand Systems

Keynote: Smart move

Abstract: In our research we look at demand-responsive urban transportation: next-gen smart mobility. The focus is on concepts of economic feasibility, and on raising its attraction and trust. I'll give an overview of the ongoing work.

Bio: Stephan Winter is Professor and Discipline Leader, Geomatics, at the Department of Infrastructure Engineering, The University of Melbourne. He is a world-wide recognized researcher in spatial information science, specializing in human spatial cognition and interaction, and intelligent mobility / transport. He leads the smart city agenda of the Melbourne School of Engineering. He is member of IEEE.

WS04-2: Modelling, Analysis and Control of Intelligent Mobility-on-Demand Systems

Session 1: Demand estimation for MoD
Analysis on Supply and Demand of Shared Autonomous Vehicles Considering Household Vehicle Ownership and Shared Use
A Critical Analysis of Travel Demand Estimation for New One-Way Carsharing Systems

WS04-3: Modelling, Analysis and Control of Intelligent Mobility-on-Demand Systems

Session 2: Operations of MoD
DeepSpeedometer: Vehicle Speed Estimation from Accelerometer and Gyroscope Using LSTM Model
Rebalancing Shared Mobility-on-Demand Systems: a Reinforcement Learning Approach
Stackable VS Autonomous Cars for Shared Mobility Systems: a Preliminary Performance Evaluation

WS04-4: Modelling, Analysis and Control of Intelligent Mobility-on-Demand Systems

Session 3: Simulation of MoD
Agent-Based Simulation of a Shared, Autonomous and Electric On-Demand Mobility Solution
Development of a Simulation Platform to Implement Vehicle Routing Algorithms for Large Scale Fleet Management Systems
City-wide Shared Taxis:A Simulation Study in Berlin

WS04-5: Modelling, Analysis and Control of Intelligent Mobility-on-Demand Systems

Closing remarks

WS05-0: Deep Learning for Autonomous Driving

Opening Remarks

WS05-1: Deep Learning for Autonomous Driving

Invited Talk #1 : Virtual Worlds for the Perception and Control of Self-Driving Vehicles

Deep learning has emerged as a key enabling technology for developing autonomous driving under two main paradigms. On the one hand, we can find modular approaches with explicit tasks for detecting the free road, the dynamic objects, etc. and then plan for a safe vehicle maneuver according to particular control laws.  These tasks rely on deep models. On the other hand, there are end-to-end driving approaches able to output vehicle motion commands by processing the raw data with a deep model, without explicit tasks for detecting the free road, the dynamic objects or running a specific control law. In the former case, perception and control are separated, in the latter they are not; but in both cases some sort of ground truth (GT) is required for training and testing the self-driving AI agents. In fact, deep models are very data hungry (raw and GT). Our research group at the CVC/UAB has been investigating during the last eight years how virtual worlds and simulation can help training and testing advanced driver assistance systems (ADAS) first, and self-driving AI agents nowadays. In this talk we review all this research presenting last news about our well-known SYNTHIA environment, as well as new simulation environments such as CARLA. Focusing on how these environments can contribute to both self-driving paradigms, as well as to other tasks related to vision zero traffic accidents.

WS05-2: Deep Learning for Autonomous Driving

Invited Talk #2 : From Deep Learning to Autonomous Driving

Deep Learning and Autonomous Driving are emerging research topics that become more and more interweaved. Besides continuously upcoming new achievements in learning, we see successful approaches in the domain of autonomous vehicles reaching from learning individual components of the overall system, over several components at once, up to directly learning vehicle control commands from visual sensor input. However, when bringing these approaches to real world autonomous driving, the question on how to safely incorporate those techniques into production-grade vehicles arises. This issue can be considered manageable when learning techniques are used for highly dedicated perception tasks with a single learning step, but becomes more complex with increasing responsibilities of the learning system. If vehicles are controlled by learning-based approaches directly, rare failures will have immediate impact and thus more severe consequences. This emphasizes the importance for research towards the additional integration of expert knowledge in order to constrain vehicle behaviors in terms of safety and reliability.  his presentation will outline the power and computational expressiveness of deep learning approaches in autonomous driving. Furthermore, the potential of current end-to-end learning concepts for vehicle control using supervised and unsupervised methods will be discussed. This will be followed by potential methods to combine such learning algorithms with model driven and probabilistic approaches in order to gain comprehensiveness and accountability. Experiments and results from real world scenarios with our autonomous research car CoCar will be shown.

WS05-3: Deep Learning for Autonomous Driving

Invited Talk #3 : Faster Convolutional Architecture Search for Semantic Segmentation

Designing deep learning architectures is a complex task and requires expert knowledge. Convolutional Neural Networks involve different network topologies, layers, layer parameters. In order to automate the design process our approach is based on MetaQNN, the Q-learning agent design architectures by selecting CNN layers. We extend the approach for semantic segmentation task, where architecture involves encoder-decoder layers. To speed up the search process, we use a Hyperband-like technique. Our experiments are evaluated on CamVid urban street scene semantic segmentation dataset. The architectures designed by the Q-learning agent for semantic segmentation task are better than some commonly used hand-designed architectures with similar number of parameters.

WS05-4: Deep Learning for Autonomous Driving

Oral Paper Session #1
Learning Temporal Features with CNNs for Monocular Visual Ego Motion Estimation
Speed and Steering Angle Prediction for Intelligent Vehicles Based on Deep Belief Network
Adding Navigation to the Equation: Turning Decisions for End-to-End Vehicle Control

WS05-5: Deep Learning for Autonomous Driving

Poster Session
Intent Prediction of Vulnerable Road Users from Motion Trajectories Using Stacked LSTM Network
Feature Detectors for Traffic Light Recognition
An LSTM Network for Highway Trajectory Prediction
Deep Fully Convolutional Networks with Random Data Augmentation for Enhanced Generalization in Road Detection
Deep Convolution Long-Short Term Memory Network for LIDAR Semantic Segmentation
Fast Semi-Dense 3D Semantic Mapping with Monocular Visual SLAM

WS05-6: Deep Learning for Autonomous Driving

Invited Talk #4 : Deep Learning Implementation and Optimization on DRIVE PX Autonomous Driving Platform

DL (Deep Learning) offers a superhuman image recognition performance today, and this is the strong motivation to apply this technology for autonomous driving perception. Additionally the capability of driving smoothly in various conditions is expected to be implemented by the End-to-End DL. NVIDIA has developed an autonomous driving platform Drive PX that include both of those DL features. This platform also implement massive parallel computing that is necessary to execute human written algorithms for image processing, localization, path planning etc. In this talk, we will introduce our DRIVE PX platforms based on Parker and Xavier SoCs (System On a Chip), DL and GPU computing implemented on those platforms and key technologies including TensorRT, DLA(DL Accelerators) that enables the DN execution in a practical performance/watt level.

WS05-7: Deep Learning for Autonomous Driving

Invited Talk #5 : Towards Deep Understanding of the Vulnerable Road User

Daimler introduced an advanced set of driver assistance functions starting from 2013 in its Mercedes-Benz S-, E-, and C-Class models using stereo vision. Already included was a pedestrian safety component which facilitates fully automatic emergency braking. During the last years our research focused on developing the next-generation of active pedestrian and cyclist safety systems. These systems extract higher-level visual cues and use more sophisticated motion models for path prediction - enabling a deeper traffic situation understanding. The potential to react earlier in dangerous traffic situations, without increasing the false alarms, make such systems essential for autonomous driving in our cities. In this talk we provide an overview over current research projects and show how these works can greatly improve the perception of difficult traffic situations by making use of modern machine learning methods.

WS05-8: Deep Learning for Autonomous Driving

Invited Talk #6 : Deep learning journey: from driver assistance to driver replacement

According to recent expectations, fully autonomous commercial vehicles should start rolling in the streets in less than three years. This is the fruit of at least a decade of research and development work. In this talk, we will trace this interesting journey focusing on its machine vision aspect. It all started with detecting individual objects from images and videos - especially pedestrians. Soon after, with the successful introduction of convolutional neural networks, pixel segmentation of multiple objects simultaneously was deemed possible to assist drivers in unfavorable weather conditions. Furthermore, another line of research focused on monitoring the driver to detect alertness and concentration. Recently, deep learning has been active in estimating the correct steering angle from camera feeds. Hopefully, integrating all these components together can help enjoying the ride safely in autonomous cars be very soon.

WS05-9: Deep Learning for Autonomous Driving

Oral Paper Session #2
Probabilistic Vehicle Trajectory Prediction over Occupancy Grid Map via Recurrent Neural Network
A Survey on Leveraging Deep Neural Networks for Object Tracking
Imitation Learning for Vision-based Lane Keeping Assistance

WS05-10: Deep Learning for Autonomous Driving

Closing Remarks & discussion

WS06: Artificial Transportation Systems and Simulation

Short-term Traffic Flow Forecasting Based on Wavelet Transform and Neural Network
Hybrid Calibration of Agent-Based Travel Model Using Traffic Counts and AVI Data
Teaching Self-Driving Cars to Dream: A Deeply Integrated, Innovative Approach for Solving the Autonomous Vehicle Validation Problem
Automated Scenario Generation for Regression Testing of Autonomous Vehicles
Efficient Expression and Deep Analysis Platform of Massive Traffic Video Data
Coffee break
Relaying Algorithm Based on Soft Estimated Information for Cooperative V2X Networks
Behavioral Trajectory Planning for Motion Planning in Urban Environments
Market-based Approach for Cooperation and Coordination Among Multiple Autonomous Vehicles

WS07-0: The Third International Workshop on Intelligent Public Transports -- Toward the Next Generation of Urban Mobility

Opening Session

WS07-1: The Third International Workshop on Intelligent Public Transports -- Toward the Next Generation of Urban Mobility

SESSION I - Demand Patterns

"Future Public Transport Fare Structures: Behavioural and Social Impacts of IST"

Automatic Fare Collection (AFC) systems such as smart cards, or mobile phone based charging are allowing us to collect long-term data records of user behaviour. This information can be used to optimize a transport network including network structure and fares, though understanding and predicting demand elasticities remains a challenging topic. At the same time, new AFC technologies are not only a data source but also allow operators to introduce complex fare structures including spatial, temporal and user group distinguished charging. The talk will discuss some of these trends and possibilities, such as changes from flat or zonal to distance-based fares and price capping. Potential impacts for single travelers as well as specific parts of a hypothetical city will be discussed to illustrate that some cities understandably hesitate to use the full potential of now possible charging structures.

WS07-2: The Third International Workshop on Intelligent Public Transports -- Toward the Next Generation of Urban Mobility

SESSION I - Demand Patterns
Daily Metro Origin-Destination Pattern Recognition Using Dimensionality Reduction and Clustering Methods

WS07-3: The Third International Workshop on Intelligent Public Transports -- Toward the Next Generation of Urban Mobility

SESSION I - Demand Patterns

Predicting the Next Trip of Individual Public Transportation Passengers * by Zhan Zhao, Haris N. Koutsopoulos and Jinhua Zhao

WS07-4: The Third International Workshop on Intelligent Public Transports -- Toward the Next Generation of Urban Mobility

SESSION I - Demand Patterns
Short & Long Term Forecasting of Multimodal Transport Passenger Flows with Machine Learning Methods

WS07-5: The Third International Workshop on Intelligent Public Transports -- Toward the Next Generation of Urban Mobility

SESSION II - Operations and Traffic Dynamics
Novel C-ITS Support for Electric Buses with Opportunity Charging
Adjusting Bus Timetables Considering Observed Delays and Passenger Numbers
Fault Diagnosis Method of the On-board Equipment of Train Control System Based on Rough Set Theory
Non-stationary Traffic Flow Prediction Using Deep Learning

WS07-6: The Third International Workshop on Intelligent Public Transports -- Toward the Next Generation of Urban Mobility

SESSION III - Network Dynamics
Resiliency Assessment of Urban Rail Transit Networks: A Case Study of Shanghai Metro
Using Mobile Phone Data Analysis for the Estimation of Daily Urban Dynamics
Simulation of Demand and Supply of Urban Rail in a Multimodal Environment

WS07-7: The Third International Workshop on Intelligent Public Transports -- Toward the Next Generation of Urban Mobility

Closing Session

WS08: Behavioural Change Support Intelligent Transportation Applications

Implementation of a Mobility Behavior Change Support System in Manila Philippines
Exploring Influential Factors on Transition Process of Vehicle Ownership in Developing Asian City- A Case Study in Bogor City Indonesia
Pricing as a Tool to Influence Behaviour
Personalized Persuasion Services for Route Planning Applications
Classifying Aggressive Drivers for Better Traffic Signal Control
Coffee break
Impact of Autonomous Vehicles on Pedestrians' Safety
Assessing Passenger Feedback Reliability in Crowd-Sourced Measurement of Transit Ride Quality
Reliable Feeder Bus Schedule Optimization in A Multi-mode Transit System
Incident Detection Using Data from Social Media

WS09: Transportation 5.0

Transportation 5.0 in CPSS: Towards ACP-based Society-Centered Intelligent Transportation
CPSS Models and Spatiotemporal Collaborative Optimization of Urban Public Transport Dynamic Network
A Hybrid Deep Learning Approach for Urban Expressway Travel Time Prediction Considering Spatial-Temporal Features
DeepTrend: A Deep Hierarchical Neural Network for Traffic Flow Prediction
Risk Diagnosis Model for the Disaster Spread of Highway Traffic Network
Memetic Algorithm with Adaptive Local Search for Capacitated Arc Routing Problem
Lane-changing Rules Based on Cellular Automaton Traffic Flow Model Under V2V Environment
Improved Single Image Haze Removal for Intelligent Driving
Scene-Specific Pedestrian Detection Based on Parallel Vision
Visual Lane Detection Based on the Hierarchical Grouping Structure
The ParallelEye Dataset: Constructing Large-Scale Artificial Scenes for Traffic Vision Research
An Improved Method of Real-time Camera Pose Estimation Based on Descriptor Tracking
Accelerate the Autonomous Vehicles Reliability Testing in Parallel Paradigm
An Accelerated Testing Approach for Automated Vehicles with Background Traffic Described by Joint Distributions

WS10-0: International workshop on Large-Scale Traffic Modeling and Management

Openning

WS10-1: International workshop on Large-Scale Traffic Modeling and Management

Macroscopic fundamental diagram for coordinated ramp metering

Recent studies on aggregated traffic modeling of urban networks have shown the existence of a well-defined and low-scatter Macroscopic Fundamental Diagram (MFD) that links network aggregated flow and density. However, the MFD of freeway networks typically exhibits high scatter and hysteresis loops that challenge the monitoring capability and control performance of MFD-based congestion management schemes in freeways. This paper investigates the effect of density heterogeneity and capacity drop on characteristics of freeway MFD based on field traffic data. In addition, we introduce a model to capture the evolution of density heterogeneity which is essential to reproduce the dynamics of freeway MFD accurately. The proposed model is incorporated in a hierarchical control structure for coordinated ramp metering on a freeway stretch with multiple congestion bottlenecks and on- and on-ramps. At the upper level, a model predictive control (MPC) approach is developed to optimize total inflow from on-ramps to the freeway stretch, where the prediction model is formulated based on the proposed MFD model. The lower level controller distributes the optimal total inflows to each on-ramp of the freeway based on local traffic state feedback. The proposed ramp metering framework shows desirable performance to reduce the total time spent and eliminate congestion. The control approach is compared with other coordinated ramp metering controllers based on the MPC framework with different prediction models (e.g. CTM and METANET). Simulation outcomes highlight that the MFD-based hierarchical controller (i) is better able to overcome the modeling mismatch between the prediction model and the plant (process model) in the MPC framework and (ii) requires less computation effort than other nonlinear controllers.

WS10-2: International workshop on Large-Scale Traffic Modeling and Management

Hierarchical management of large-scale networks via path assignment and regional route guidance

Alleviating congestion via manipulation of traffic flows or assignment of vehicles to specific paths has a great potential in achieving efficient network usage. Motivated by this fact, this paper proposes a hierarchical traffic management scheme that combines a network-level regional route guidance model predictive control (MPC) scheme with a region-level subregional path assignment mechanism. The route guidance MPC optimizes network performance based on actuation via regional split ratios, whereas the path assignment mechanism recommends paths for vehicles to follow, realizing the regional split ratios sent by the MPC in order to achieve said performance. Simulation results in a detailed 49 subregion model indicates potential of the proposed scheme in achieving coordination and efficient use of network capacity, leading to increased mobility.

WS10-3: International workshop on Large-Scale Traffic Modeling and Management

A macroscopic approach for optimizing road space allocation of bus lanes in multimodal urban networks through simulation analysis: An Application to the Tokyo CBD Network
A Macroscopic Approach for Optimizing Road Space Allocation of Bus Lanes in Multimodal Urban Networks Through Simulation Analysis: An Application to the Tokyo CBD Network

WS10-4: International workshop on Large-Scale Traffic Modeling and Management

3D clustering methods to estimate travel times at large urban scale

This presentation is about partitioning link speed data every 10 min into 3D clusters that proposes a parsimonious sketch of the congestion patterns at the whole city scale. Days with similar patterns are then gathered using consensus clustering methods to produce a unique global pattern that fits multiple days. We show that Amsterdam's network over 35 days can be synthesized into only 4 consensual 3D speed maps with 9 clusters. A new travel time estimation method can be derived from such patterns. By matching the current observation to historical consensual 3D speed maps, an efficient real-time method is designed. It successfully predicts 84% trips travel times with an error margin below 25%.

WS10-5: International workshop on Large-Scale Traffic Modeling and Management

A Case Study of a Continuous Flow Intersection and Its Impact on Public Transport
A Case Study of a Continuous Flow Intersection and Its Impact on Public Transport

WS10-6: International workshop on Large-Scale Traffic Modeling and Management

Off the Shortest Path: Betweenness on Street Network Level to Study Pedestrian Movement
Off the Shortest Path: Betweenness on Street Network Level to Study Pedestrian Movement

WS10-7: International workshop on Large-Scale Traffic Modeling and Management

Multi-Agent Based Road Traffic Control Optimization
Multi-Agent Based Road Traffic Control Optimization

WS10-8: International workshop on Large-Scale Traffic Modeling and Management

Bus Arrival Time Prediction at Any Distance of Bus Route Using Deep Neural Network Model
Bus Arrival Time Prediction at Any Distance of Bus Route Using Deep Neural Network Model

WS10-9: International workshop on Large-Scale Traffic Modeling and Management

ANALYSING THE IMPACTS OF TRAFFIC STATES AND OD-PATTERNS ON THE PARTITION OF LARGE-SCALE URBAN ROAD NETWORKS

With the expansion of cities and the increasing of traffic demand, the scale of the physics of congestion increases. The macroscopic fundamental diagram (MFD) is widely applied for understanding these physics, and serves as a tool monitoring and control of large-scale networks. The MFD is also becoming a topic of increasing concern. The existence of a well-defined MFD requires spatial homogeneity in traffic distribution in a region, which necessitates transportation network partitioning an essential step in MFD-type applications. This paper moves forward with this direction and investigates the partitioning criteria and methods. Firstly, two partition factors, namely link average density and average speed are defined; Secondly, an extended NCut algorithm is built up and partitions are performed based on the two factors respectively. Then, both partitions are applied and tested in the Sioux Falls network. We employ a variance coefficient to evaluate the performance and a diversity coefficient to qualify the sensitivity of the proposed partitions to the variation of traffic demand. The results reveal that (1) the two methods shall not be regarded as equivalent for obvious differences quantified up to 30%, (2) the density-based method shows advantages in effective and steady identification of traffic patterns under slow-varying demand scenarios and (3) a threshold on the variation of demand can be found, exceeding which the demand profile experiences significant change and the speed-based partition method outperforms the density-based method with respective to partitioned homogeneity. This paper is among the few pioneer works targeting the issues of network partition based on the MFD state variables.