A Versatile and Efficient Reinforcement Learning Framework for Autonomous Driving
This work addresses the problem of developing efficient and generalizable autonomous driving systems for industry and research, though it appears incremental by building on existing hybrid paradigms.
The paper tackles the challenge of combining modular and end-to-end approaches in autonomous driving by proposing a reinforcement learning framework that learns semantic representations for policy tasks, resulting in improved generalizability to real-world scenarios and superior training efficiency compared to baselines.
Heated debates continue over the best autonomous driving framework. The classic modular pipeline is widely adopted in the industry owing to its great interpretability and stability, whereas the fully end-to-end paradigm has demonstrated considerable simplicity and learnability along with the rise of deep learning. As a way of marrying the advantages of both approaches, learning a semantically meaningful representation and then use in the downstream driving policy learning tasks provides a viable and attractive solution. However, several key challenges remain to be addressed, including identifying the most effective representation, alleviating the sim-to-real generalization issue as well as balancing model training cost. In this study, we propose a versatile and efficient reinforcement learning framework and build a fully functional autonomous vehicle for real-world validation. Our framework shows great generalizability to various complicated real-world scenarios and superior training efficiency against the competing baselines.