Risk assessment based collision avoidance decision-making for autonomous vehicles in multi-scenarios

Abstract In this paper, we proposed a new risk assessment based decision-making algorithm to guarantee collision avoidance in multi-scenarios for autonomous vehicles. A probabilistic-model based situation assessment module using conditional random field was proposed to assess the risk level of surrounding traffic participants. Based on the assessed risk from the situation assessment module, a collision avoidance strategy with driving style preferences (e.g., aggressive or conservative) was proposed to meet the demands of different drivers or passengers. Finally, we conducted experiments in Carla (car learning to act) to evaluate our developed collision avoidance decision-making algorithm in different scenarios. The results show that our developed method was sufficiently reliable for autonomous vehicles to avoid collisions in multi-scenarios with different driving style preferences. Our developed method with adjustable driving style preferences to meet the demand of different consumers would improve drivers’ acceptance of autonomous vehicles.

[1]  Ching-Yao Chan,et al.  A Reinforcement Learning Based Approach for Automated Lane Change Maneuvers , 2018, 2018 IEEE Intelligent Vehicles Symposium (IV).

[2]  Alireza Talebpour,et al.  Weather and road geometry impact on longitudinal driving behavior: Exploratory analysis using an empirically supported acceleration modeling framework , 2016 .

[3]  Yang Gao,et al.  End-to-End Learning of Driving Models from Large-Scale Video Datasets , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Kibeom Lee,et al.  Collision Avoidance/Mitigation System: Motion Planning of Autonomous Vehicle via Predictive Occupancy Map , 2019, IEEE Access.

[5]  Guofa Li,et al.  Effectiveness of Flashing Brake and Hazard Systems in Avoiding Rear-End Crashes , 2014 .

[6]  Luigi dell’Olio,et al.  The quality of service desired by public transport users , 2011 .

[7]  Xingda Qu,et al.  Drivers' visual scanning behavior at signalized and unsignalized intersections: A naturalistic driving study in China. , 2019, Journal of safety research.

[8]  Chang Liu,et al.  Kalman filter-based tracking of moving objects using linear ultrasonic sensor array for road vehicles , 2018 .

[9]  Matthew Johnson-Roberson,et al.  Occlusion-Aware Risk Assessment for Autonomous Driving in Urban Environments , 2018, IEEE Robotics and Automation Letters.

[10]  Carl-Johan Hoel,et al.  Combining Planning and Deep Reinforcement Learning in Tactical Decision Making for Autonomous Driving , 2019, IEEE Transactions on Intelligent Vehicles.

[11]  Stewart Worrall,et al.  Vehicle collision probability calculation for general traffic scenarios under uncertainty , 2014, 2014 IEEE Intelligent Vehicles Symposium Proceedings.

[12]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[13]  Sorin Grigorescu,et al.  A Survey of Deep Learning Techniques for Autonomous Driving , 2020, J. Field Robotics.

[14]  Ching-Yao Chan,et al.  Driving Decision and Control for Automated Lane Change Behavior based on Deep Reinforcement Learning , 2019, 2019 IEEE Intelligent Transportation Systems Conference (ITSC).

[15]  Keqiang Li,et al.  Driving safety field theory modeling and its application in pre-collision warning system , 2016 .

[16]  Dongsuk Kum,et al.  Collision Risk Assessment Algorithm via Lane-Based Probabilistic Motion Prediction of Surrounding Vehicles , 2018, IEEE Transactions on Intelligent Transportation Systems.

[17]  Samyeul Noh,et al.  Decision-Making Framework for Automated Driving in Highway Environments , 2018, IEEE Transactions on Intelligent Transportation Systems.

[18]  Bo Cheng,et al.  Detection of road traffic participants using cost-effective arrayed ultrasonic sensors in low-speed traffic situations , 2019, Mechanical Systems and Signal Processing.

[19]  Hyungjun Park,et al.  Cooperative lane control application for fully connected and automated vehicles at multilane freeways , 2020 .

[20]  Kyongsu Yi,et al.  Human-Centered Risk Assessment of an Automated Vehicle Using Vehicular Wireless Communication , 2019, IEEE Transactions on Intelligent Transportation Systems.

[21]  Hong Wang,et al.  Crash Mitigation in Motion Planning for Autonomous Vehicles , 2019, IEEE Transactions on Intelligent Transportation Systems.

[22]  Pravin Varaiya,et al.  Making intersections safer with I2V communication , 2018, Transportation Research Part C: Emerging Technologies.

[23]  Brendan Tran Morris,et al.  Looking at Intersections: A Survey of Intersection Monitoring, Behavior and Safety Analysis of Recent Studies , 2017, IEEE Transactions on Intelligent Transportation Systems.

[24]  Guofa Li,et al.  Deep Learning Approaches on Pedestrian Detection in Hazy Weather , 2020, IEEE Transactions on Industrial Electronics.

[25]  Guofa Li,et al.  Decision Tree-Based Maneuver Prediction for Driver Rear-End Risk-Avoidance Behaviors in Cut-In Scenarios , 2017 .

[26]  Krister Wolff,et al.  A Review of Near-Collision Driver Behavior Models , 2012, Hum. Factors.

[27]  Gang Xu,et al.  The Determinants behind the Acceptance of Autonomous Vehicles: A Systematic Review , 2020, Sustainability.

[28]  Samyeul Noh,et al.  Decision-Making Framework for Autonomous Driving at Road Intersections: Safeguarding Against Collision, Overly Conservative Behavior, and Violation Vehicles , 2019, IEEE Transactions on Industrial Electronics.

[29]  Jae-Hwan Kim,et al.  Threat prediction algorithm based on local path candidates and surrounding vehicle trajectory predictions for automated driving vehicles , 2015, 2015 IEEE Intelligent Vehicles Symposium (IV).

[30]  Benoit Vanholme,et al.  Maneuver-Based Trajectory Planning for Highly Autonomous Vehicles on Real Road With Traffic and Driver Interaction , 2010, IEEE Transactions on Intelligent Transportation Systems.

[31]  Xingda Qu,et al.  Influence of traffic congestion on driver behavior in post-congestion driving. , 2020, Accident; analysis and prevention.

[32]  Mujahid N. Syed,et al.  Heuristic Approach for Real-Time Multi-Agent Trajectory Planning Under Uncertainty , 2020, IEEE Access.

[33]  Peter Stone,et al.  Transfer Learning for Reinforcement Learning Domains: A Survey , 2009, J. Mach. Learn. Res..

[34]  Igor Skrjanc,et al.  Efficient Time-To-Collision Estimation for a Braking Supervision System with LIDAR , 2017, 2017 3rd IEEE International Conference on Cybernetics (CYBCON).

[35]  Bo Cheng,et al.  Estimation of driving style in naturalistic highway traffic using maneuver transition probabilities , 2017 .

[36]  Jonas Sjöberg,et al.  Threat assessment design under driver parameter uncertainty , 2012, 2012 IEEE 51st IEEE Conference on Decision and Control (CDC).

[37]  Wei Zhang,et al.  The roles of initial trust and perceived risk in public’s acceptance of automated vehicles , 2019, Transportation Research Part C: Emerging Technologies.

[38]  Wanzhong Zhao,et al.  An Integrated Threat Assessment Algorithm for Decision-Making of Autonomous Driving Vehicles , 2020, IEEE Transactions on Intelligent Transportation Systems.

[39]  Guofa Li,et al.  Driver braking behavior analysis to improve autonomous emergency braking systems in typical Chinese vehicle-bicycle conflicts. , 2017, Accident; analysis and prevention.

[40]  Jun Tang,et al.  A causal encounter model of traffic collision avoidance system operations for safety assessment and advisory optimization in high-density airspace , 2018 .