PP-TIL: Personalized Planning for Autonomous Driving with Instance-based Transfer Imitation Learning

TL;DR

This paper introduces PP-TIL, a personalized motion planning method for autonomous driving that leverages transfer imitation learning to improve performance and generalization using expert and limited user data.

Contribution

The paper proposes an instance-based transfer imitation learning approach that transfers knowledge from large-scale expert data to personalize urban driving models.

Findings

Reduces overfitting with sparse user data

Enhances planning performance with a safety protection layer

Effective knowledge transfer from expert to user domain

Abstract

Personalized motion planning holds significant importance within urban automated driving, catering to the unique requirements of individual users. Nevertheless, prior endeavors have frequently encountered difficulties in simultaneously addressing two crucial aspects: personalized planning within intricate urban settings and enhancing planning performance through data utilization. The challenge arises from the expensive and limited nature of user data, coupled with the scene state space tending towards infinity. These factors contribute to overfitting and poor generalization problems during model training. Henceforth, we propose an instance-based transfer imitation learning approach. This method facilitates knowledge transfer from extensive expert domain data to the user domain, presenting a fundamental resolution to these issues. We initially train a pre-trained model using large-scale expert data. Subsequently, during the fine-tuning phase, we feed the batch data, which comprises expert and user data. Employing the inverse reinforcement learning technique, we extract the style feature distribution from user demonstrations, constructing the regularization term for the approximation of user style. In our experiments, we conducted extensive evaluations of the proposed method. Compared to the baseline methods, our approach mitigates the overfitting issue caused by sparse user data. Furthermore, we discovered that integrating the driving model with a differentiable nonlinear optimizer as a safety protection layer for end-to-end personalized fine-tuning results in superior planning performance.