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

TL;DR

This paper introduces an interpretable CPT-based model for predicting human driving behavior in interactive scenarios, capturing irrational decisions better than traditional models and requiring less training data.

Contribution

The work formulates a CPT-driven decision-making model for driving, develops a hierarchical learning algorithm for its parameters, and demonstrates improved prediction with interpretability.

Findings

CPT model outperforms TTC-based model in prediction accuracy.

CPT model achieves similar performance to neural networks with less data.

Model provides better interpretability of human driving decisions.

Abstract

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 a goal, we first develop a CPT-driven decision-making model focusing on driving scenarios with two interacting agents. A hierarchical learning algorithm is proposed afterward 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.