Interpretable Modelling of Driving Behaviors in Interactive Driving Scenarios based on Cumulative Prospect Theory

Understanding human driving behavior is important for autonomous vehicles. In this paper, we propose an interpretable human behavior model in interactive driving scenarios based on the cumulative prospect theory (CPT). As a non-expected utility theory, CPT can well explain some systematically biased or "irrational" behavior/decisions of human that cannot be explained by the expected utility theory. Hence, the goal of this work is to formulate the human drivers’ behavior generation model with CPT so that some "irrational" behavior or decisions of human can be better captured and predicted. Towards such goal, we first develop a CPT-driven decision-making model focusing on driving scenarios with two interacting agents. A hierarchical learning algorithm is proposed afterwards to learn the utility function, the value function, and the decision weighting function in the CPT model. A case study for roundabout merging is also provided as verification. With real driving data, the prediction performances of three different models are compared: a predefined model based on time-to-collision (TTC), a learning-based model based on neural networks, and the proposed CPT-based model. The results show that the proposed model outperforms the TTC model and achieves similar performance as the learning-based model with much less training data and better interpretability.

[1]  A. Tversky,et al.  Prospect theory: an analysis of decision under risk — Source link , 2007 .

[2]  Jianping Wu,et al.  Development of a fuzzy logic based microscopic motorway simulation model , 1997, Proceedings of Conference on Intelligent Transportation Systems.

[3]  Junqiang Xi,et al.  Modeling and Recognizing Driver Behavior Based on Driving Data: A Survey , 2014 .

[4]  Wei Zhan,et al.  Generic Vehicle Tracking Framework Capable of Handling Occlusions Based on Modified Mixture Particle Filter , 2018, 2018 IEEE Intelligent Vehicles Symposium (IV).

[5]  A. Tversky,et al.  Prospect Theory : An Analysis of Decision under Risk Author ( s ) : , 2007 .

[6]  Wei Zhan,et al.  Multi-modal Probabilistic Prediction of Interactive Behavior via an Interpretable Model , 2019, 2019 IEEE Intelligent Vehicles Symposium (IV).

[7]  Sethu Vijayakumar,et al.  Proceedings of the twenty-first international conference on Machine learning , 2004 .

[8]  Masayoshi Tomizuka,et al.  Generic Prediction Architecture Considering both Rational and Irrational Driving Behaviors , 2019, 2019 IEEE Intelligent Transportation Systems Conference (ITSC).

[9]  Anind K. Dey,et al.  Maximum Entropy Inverse Reinforcement Learning , 2008, AAAI.

[10]  Anca D. Dragan,et al.  Courteous Autonomous Cars , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[11]  M. Tomasello,et al.  Does the chimpanzee have a theory of mind? 30 years later , 2008, Trends in Cognitive Sciences.

[12]  Jonathan P. How,et al.  Driver Behavior Classification at Intersections and Validation on Large Naturalistic Data Set , 2012, IEEE Transactions on Intelligent Transportation Systems.

[13]  Silvio Savarese,et al.  Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[14]  Najah AbuAli,et al.  Driver Behavior Modeling: Developments and Future Directions , 2016 .

[15]  Dinesh Manocha,et al.  TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents , 2018, AAAI.

[16]  Mashrur Chowdhury,et al.  Review of Microscopic Lane-Changing Models and Future Research Opportunities , 2013, IEEE Transactions on Intelligent Transportation Systems.

[17]  Sergey Levine,et al.  Continuous Inverse Optimal Control with Locally Optimal Examples , 2012, ICML.

[18]  Jeremy A. Salinger,et al.  Status of NHTSA's Rear-End Crash Prevention Research Program , 2005 .

[19]  Dirk Helbing,et al.  General Lane-Changing Model MOBIL for Car-Following Models , 2007 .

[20]  D. Bernoulli.  Exposition of a New Theory on the Measurement of Risk , 1954 .

[21]  Chris L. Baker,et al.  Modeling Human Plan Recognition Using Bayesian Theory of Mind , 2014 .

[22]  Wei Zhan,et al.  Coordination and Trajectory Prediction for Vehicle Interactions via Bayesian Generative Modeling , 2019, 2019 IEEE Intelligent Vehicles Symposium (IV).

[23]  Wei Zhan,et al.  A Framework for Probabilistic Generic Traffic Scene Prediction , 2018, 2018 21st International Conference on Intelligent Transportation Systems (ITSC).

[24]  Wei Zhan,et al.  Probabilistic Prediction of Vehicle Semantic Intention and Motion , 2018, 2018 IEEE Intelligent Vehicles Symposium (IV).

[25]  Wei Zhan,et al.  Probabilistic Prediction of Interactive Driving Behavior via Hierarchical Inverse Reinforcement Learning , 2018, 2018 21st International Conference on Intelligent Transportation Systems (ITSC).

[26]  Pieter Abbeel,et al.  Apprenticeship learning via inverse reinforcement learning , 2004, ICML.

[27]  A. Tversky,et al.  Advances in prospect theory: Cumulative representation of uncertainty , 1992 .

[28]  Helbing,et al.  Congested traffic states in empirical observations and microscopic simulations , 2000, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[29]  Masayoshi Tomizuka,et al.  INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Maps , 2019, ArXiv.

[30]  Masayoshi Tomizuka,et al.  Constructing a Highly Interactive Vehicle Motion Dataset , 2019, 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[31]  Ruzena Bajcsy,et al.  Integrating Intuitive Driver Models in Autonomous Planning for Interactive Maneuvers , 2017, IEEE Transactions on Intelligent Transportation Systems.