Adaptive Probabilistic Vehicle Trajectory Prediction Through Physically Feasible Bayesian Recurrent Neural Network

TL;DR

This paper introduces a Bayesian recurrent neural network that guarantees physically feasible vehicle trajectory predictions and adapts to individual driving policies, enhancing autonomous driving safety.

Contribution

It combines Bayesian neural networks with physical models and online adaptation to improve long-term, feasible, and personalized vehicle trajectory prediction.

Findings

The model produces physically feasible trajectory distributions.

It adapts online to different driving policies.

Demonstrated effectiveness on naturalistic car data.

Abstract

Probabilistic vehicle trajectory prediction is essential for robust safety of autonomous driving. Current methods for long-term trajectory prediction cannot guarantee the physical feasibility of predicted distribution. Moreover, their models cannot adapt to the driving policy of the predicted target human driver. In this work, we propose to overcome these two shortcomings by a Bayesian recurrent neural network model consisting of Bayesian-neural-network-based policy model and known physical model of the scenario. Bayesian neural network can ensemble complicated output distribution, enabling rich family of trajectory distribution. The embedded physical model ensures feasibility of the distribution. Moreover, the adopted gradient-based training method allows direct optimization for better performance in long prediction horizon. Furthermore, a particle-filter-based parameter adaptation algorithm is designed to adapt the policy Bayesian neural network to the predicted target online. Effectiveness of the proposed methods is verified with a toy example with multi-modal stochastic feedback gain and naturalistic car following data.