C0-Director, Berkeley DeepDrive
Researcher, CALIFORNIA PATH
Dr. Ching-Yao Chan is Co-Director, along with Prof. Trevor Darrell and Prof. Kurt Keutzer, of Berkeley DeepDrive (BDD). Dr. Chan leads research projects on intelligent autonomy of dynamic systems. His recent projects involve deep reinforcement learning, meta-learning, pedestrian trajectory projection, multi-person action forecasting based on machine learning, and radar-camera sensor fusion.
Dr. Chan has three decades of research experience in a broad range of automotive and transportation systems. His research ranges from automated systems, sensing and wireless communication technologies, data analytics and safety assessment, to applications of artificial intelligence on autonomy.
Dr. Chan is a Researcher at California PATH (Partners for Advanced Transportation Technology). At PATH, Dr. Chan leads research projects in automation, advanced technologies, human factors, and transportation systems.
In the summer of 2021, Dr. Chan formally retired from the University of California, but he returned with a recall appointment to continue his work on a variety of collaborative research with industrial partners.
Dr. Chan serves as a member of the board of directors for the School of Computing, National Cheng-Kung University, Taiwan. He was a Visiting Professor at University of Tokyo in 2006-2007. He is also the recipient of the Team Leadership Award from Berkeley Institute of Transportation Studies in 2020.
CURRENT RESEARCH AREAS
His current research is focused in the following topic areas.
- Vehicle Automation and Advanced Driver Assistance Systems (ADAS)
- Berkeley DeepDrive: Machine Learning for Intelligent Autonomy
- Human Factors Studies and Human-Machine Interaction
SELECTIVE CURRENT AND PAST RESEARCH ACTIVITIES
- Berkeley DeepDrive: Chan is PI for the infrastructure projects of BDD, and research on reinforcement learning for automated driving, pedestrian-vehicle interaction, and safety verification of networked-based algorithms.
- California SB-1 Project, Drivers’ Responses to Eco-driving Applications: Effects on Fuel Consumption and Driving Safety: Chan led this project to evaluate the effects of driver behaviors on the effectiveness of eco-driving and related policy complications.
- Survey of Autonomous Vehicle Industry: Chan is PI for a project sponsored by California DOT, which involves discussions with the AV industry to investigate the AV operational requirements and needs of infrastructure collaboration.
- Meta Learning for Autonomous Driving: Chan leads this collaborative research with Guangdong Automotive Research Silicon Valley, to explore the implementation of model agnostic meta learning for driving.
- Drive for All Foundation: Chan led Berkeley participation in this international consortium, headed by MINES ParisTech of France, with international partners working on autonomous driving in urban environment.
- Safety Effects of Yellow Alert: Chan leads this human-factor study sponsored by California Department of Transportation, to evaluate the impact of highway changeable messages on driver’s behaviors.
- Design of Interactive Display Boards and Their Impacts on Driving: Chan leads this human-factor study sponsored by California Department of Transportation, to evaluate interactive display boards on I-80.
- NSF Cyberphysics System Project on Advanced Traffic Systems: Chan works jointly with Professors Varaiya, Horowitz, Moura of UCB on an NSF project that develops vehicle technologies for traffic operation efficiency.
- California SB-1 Project, User Acceptance of Vehicle Automation and Public Policy: Chan led this project to develop an acceptance model of automation that help assess user acceptance and to help define public policy.
- Powertrain Technology and Fuel Efficiency Evaluation in a Traffic Network: 2016-2017: Chan led this Hyundai-sponsored eco-driving project, focused on traffic simulation platform and advanced power-train technology.
- Assisting California DMV in Developing Regulations for Automated Vehicles; 2013-2016: Chan was a major contributor to support California DMV in drafting regulations for Autonomous Technology.
- Connected Vehicles Test Bed for Nissan Motor; 2015-2016: Chan was PI for a project with Nissan Motor to establish a DSRC communication-enabled test bed in Sunnyvale, for research on connected vehicles.
- Cooperative Adaptive Cruise Control (CACC) with DENSO; 2015-2016: Chan led this DENSO project to evaluate safety and mobility benefits as well as human-machine interface for CACC in freeway driving scenarios.
- Eco-Driving Applications for Freeway and Arterial Driving: 2013-2014: Chan led this Hyundai Motor-sponsored eco-driving project, incorporating all relevant data to achieve a realistic and implementable solution.
- DSRC and High-Precision Positioning – Industrial Technology Research Institute; 2013: Chan managed the collaboration with ITRI on vehicle on-board implementation of DSRC related applications.
- Advisory Board member, School of Computing, National Cheng-Kung University, Taiwan, September 2020 –.
- Visiting Professor, University of Tokyo, JAPAN, May 2006 – Jan. 2007.
- Visiting Scholar, INRETS (now IFSTTAR, French National Transportation Research Institute), 2004
- Professional Engineer, California, since 1994
SELECTIVE RECENT PUBLICATIONS
- Fei Ye, et al., “Motion Planning and Control of Autonomous Vehicles,” IEEE Intelligent Vehicles, July 2021.
- Fei Ye, et al., “Meta Reinforcement Learning-Based Lane Change Strategy for Autonomous Vehicles, “IEEE Intelligent Vehicles, July 2021.
- Y. Lee, P. Wang, C-Y Chan, “RESTEP into the Future: Relational Spatio-Temporal Learning for Multi-Person Action Forecasting,” IEEE Transactions on Multimedia, Print ISSN: 1520-9210, Online ISSN: 1941-0077, June 2021.
- B. Yang et al, "A Novel Graph-based Trajectory Predictor with Pseudo Oracle," IEEE Transactions on Neural Networks and Learning Systems,” Print ISSN: 2162-237X, Online ISSN: 2162-2388, June 2021.
- I-Hsi Kao, et al, “A Posture Features Based Pedestrian Trajectory Prediction with LSTM,” IEEE-International Conference on Consumers Electronics, June 2021.
- P. Wang et al, "Decision Making for Autonomous Driving via Augmented Adversarial Inverse Reinforcement Learning", IEEE International Conference on Robotics and Automation, to be presented, May 2021.
- P. Wang, H. Li, C-Y Chan, "Learning Adaptable Policy via Meta-Adversarial Inverse Reinforcement Learning for Decision-making Tasks", IEEE International Conference on Robotics and Automation, to be presented, May 2021.
- B. Yang et al, " Crossing or not? Context-based recognition of pedestrian crossing intention in the urban environment", T-ITS-19-03-0334, IEEE Transactions on ITS, Print ISSN: 1524-9050, Online ISSN: 1558-0016, February 2021.
- Sanaz Motamedi, Pei Wang, Ching-Yao Chan, "Exploring Public Perception of Level-2 Automation and Full Automation: Interview Based Study", Paper 21-01824, Transportation Research Board Meeting, January 2021.
- X. Zhou, T. Zhang, P. Wang, C-Y Chan, "Visualization of Driving Scenes for Realistic Simulator Experimentation - An Efficient Framework", Paper 21-03634, Transportation Research Board Meeting, January 2021.
- P. Wang, et al, “Pedestrian Interaction with Automated Vehicles at Uncontrolled Intersections, “ Transportation Research Part F: Psychology and Behaviour, Dec. 2020.
- L. Bai, et al, “Capacity Estimation of Midblock Bike Lanes with Mixed Two-Wheeled Traffic, “ Transportation A: Transport Science, Dec. 2020.
- Yanli Ma, et al., “Impact of Lane Changing on Adjacent Vehicles considering Multi-Vehicle Interaction in Mixed Traffic Flow: A Velocity Estimating Model, “Physics A: Statistical Mechanics and Its Applications, November 2020.
- Fei Ye, et al., “Automated Lane Change Strategy using Proximal Policy Optimization-based Deep Reinforcement Learning, “IEEE Intelligent Vehicles, October 2020.
- J. M. Salt Ducaju, et al., “Application Specific System Identification for Model-Based Control in Self-Driving Cars, “IEEE Intelligent Vehicles, October 2020.
- Wenshuo Wang, et al., “Learning Representations for Multi-Vehicle Spatio-temporal Interactions with Semi-Stochastic Potential Fields,“ IEEE IV, October 2020.
- Arian Ranjbar, et al., “Scene Novelty Prediction from Unsupervised Discriminative Feature Learning, , “ IEEE ITSC, September 2020.
- I-Ming Chen, C-Y Chan, "Deep Reinforcement Learning Based Path Tracking Controller for Autonomous Vehicle" accepted for publication in Proc. IMechE, Part D: Journal of Automobile Engineering, August 2020.
- Yanli Ma, et al., “Drivers’ Visual Attention Characteristics under Different Cognitive Workload: An On-road Driving Behavior study,” International Journal of Environmental Research and Public Health, July 2020.
- Yanli Ma, et al., “Support vector machines for the identification of real-time driving distraction using in-vehicle information systems,” Journal of Transportation Safety and Security, DOI: 10.1080/19439962.2020.1774019, June 2020.
- Yi He, et al., “Visualization Analysis of Intelligent Vehicles Research Field Based on Mapping Knowledge Domain,” IEEE Transactions on Intelligent Transportation Systems, Print ISSN: 1524-9050, Online ISSN: 1558-0016, May 2020.
- Tianyi Li, et al.,“ Lane-level localization system using surround view cameras adaptive to different driving conditions,” International Journal of Advanced Robotic Systems, March 2020.
- Tingting Li, et al., “A Cooperative Lane Change Model for Connected and Automated Vehicles,” IEEE Access, page(s): 1-12, ISSN: 2169-3536, March 2020.
- S. Motamedi, P. Wang, C-Y Chan, “Acceptance of Full Driving Automation: Personally-Owned and Shared-Use Concepts,” Human Factors: The Journal of the Human Factors and Ergonomics Society, March 2020.
- Zhaoting Li, Wei Zhan*, Liting Sun, Ching-Yao Chan, Masayoshi Tomizuka, “Adaptive sampling-based motion planning with a non-conservatively defensive strategy for autonomous driving,” IFAC 2020.
- Huanjie Wang, et al., “Tactical driving decisions of unmanned ground vehicles in complex highway environments: A deep reinforcement learning approach,” Proceedings of the Institution of Mechanical Engineers, Part D, February 2020.
- Yanli Ma, et al., “Psychological and Environmental Factors Affecting Driver’s Frequent Lane-changing Driving Behaviors: A National Sample of Drivers in China,” IET Intelligent Transport Systems, January 2020.
- Pin Wang, Hanhan Li, Ching-Yao Chan, "Structured Quadratic Q-network for Learning Continuous Vehicle Control", Paper 20-02002, Transportation Research Board Meeting, presentation only, January 2020.
- Sanaz Motamedi, et al., "External Interface of Automated Driving Systems: Communication and Interaction with Pedestrians", Paper 20-03984, TRB 2020.
- Pei Wang, et al., "Freeway Traffic Sign Design for Interstate 80 Smart Corridor in California: A Driving Simulator Study", Paper 20-03907, TRB 2020.
- Yanli Ma, et al., “An On-Road Driving Test of Cognitive Distraction: Characteristics of Drivers’ Visual Behavior,” Paper 20-02501, TRB 2020.
- Hongyu Hu, et al., “Driver Identification Using 1-D Convolutional Neural Networks with Vehicular CAN Signals,” Paper 20-01857, TRB 2020.
- B.S., Mechanical Engineering, National Taiwan University, 1981
- M.S., Mechanical Engineering, University of California at Berkeley, 1985
- Ph.D., Mechanical Engineering, University of California at Berkeley, 1988
TECHNICAL BACKGROUND AND PROFESSIONAL CAREER
After receiving his Ph.D. degree in Mechanical Engineering from UC Berkeley in 1988, he worked in the private sector before returning to Berkeley in 1994. Prior to joining PATH, Dr. Chan worked in the field of vehicular passive safety systems. While being involved in the research, and development of crash sensing technologies, he also gained first-hand knowledge on general passive restraint systems, as he worked with automotive tier-one supplies and automotive OEMs. During 1990-1994, he worked in litigation support on accident reconstruction and participated in numerous cases of vehicle crashes, through which he gained insights on the interaction of drivers, vehicle characteristics, roadway environment, and their impacts on driving risks.
Due to his nationally recognized expertise in crash sensing and vehicular safety, Dr. Chan was invited by Society of Automotive Engineers (SAE) to provide tutorials to more than 500 automotive professionals in an SAE seminar series. He has given lectures to various organizations. He collaborated with SAE to publish a book and a video tutorial, and he was the recipient of the 1998 SAE Forest R. MacFarland Award for his outstanding contributions to engineering education.
Dr. Chan was also significantly involved in the research and development of vehicle automation technologies. During the years of the National Automated Highway Systems Consortium in 1990s, he represented PATH in the national working group of technology development and evaluation. Subsequently, he also worked in projects that involved the use of various technologies for vehicular automation systems. In 2003, he led a team of researchers and engineers in the Demonstration of Bus Automation Technology in San Diego. The project subsequently won the prestigious award of the Best of ITS Research Award from the ITS America in 2004.
Dr. Chan also collaborated with industrial and academic partners in developing and implementing communication-enabled cooperative systems in multiple projects. Applications include vehicle-to-vehicle and vehicle-to-infrastructure, vehicle-to-pedestrian, and road equipment-to-network operation scenarios. These projects were supported by and jointly conducted with federal and state governments, automaker consortium, and private-sector partners.
Dr. Chan served as a visiting Professor at the University of Tokyo, Institute of Industrial Science from May 2006 to January 2007 and a visiting scholar at Institute of French National Transport Research (INRETS, which is now IFSTTAR) in the summer of 2004.