Beyond Imitation: A Life-long Policy Learning Framework for Path Tracking Control of Autonomous Driving

TL;DR

This paper introduces a lifelong policy learning framework for autonomous vehicle path tracking that improves control policies over time using incremental data, surpassing traditional imitation learning methods.

Contribution

The paper proposes a novel lifelong learning framework that enhances imitation learning-based control policies for autonomous driving through incremental updates and knowledge evaluation.

Findings

The LLPL framework improves path tracking accuracy over time.

It achieves better control smoothness compared to baseline methods.

It is effective with noisy real-world driving data.

Abstract

Model-free learning-based control methods have recently shown significant advantages over traditional control methods in avoiding complex vehicle characteristic estimation and parameter tuning. As a primary policy learning method, imitation learning (IL) is capable of learning control policies directly from expert demonstrations. However, the performance of IL policies is highly dependent on the data sufficiency and quality of the demonstrations. To alleviate the above problems of IL-based policies, a lifelong policy learning (LLPL) framework is proposed in this paper, which extends the IL scheme with lifelong learning (LLL). First, a novel IL-based model-free control policy learning method for path tracking is introduced. Even with imperfect demonstration, the optimal control policy can be learned directly from historical driving data. Second, by using the LLL method, the pre-trained IL policy can be safely updated and fine-tuned with incremental execution knowledge. Third, a knowledge evaluation method for policy learning is introduced to avoid learning redundant or inferior knowledge, thus ensuring the performance improvement of online policy learning. Experiments are conducted using a high-fidelity vehicle dynamic model in various scenarios to evaluate the performance of the proposed method. The results show that the proposed LLPL framework can continuously improve the policy performance with collected incremental driving data, and achieves the best accuracy and control smoothness compared to other baseline methods after evolving on a 7 km curved road. Through learning and evaluation with noisy real-life data collected in an off-road environment, the proposed LLPL framework also demonstrates its applicability in learning and evolving in real-life scenarios.