Benchmarking Lane-changing Decision-making for Deep Reinforcement Learning

TL;DR

This paper presents a comprehensive benchmarking framework for evaluating deep reinforcement learning methods in lane-changing tasks for autonomous driving, using designed simulation scenarios and standardized metrics.

Contribution

It introduces a novel pipeline with specific training, testing, and evaluation scenarios, and provides benchmark results for multiple deep reinforcement learning approaches.

Findings

Benchmark scenarios enable consistent evaluation of lane-changing algorithms.

State-of-the-art deep reinforcement learning methods are systematically tested.

Benchmark results facilitate comparison between learning and non-learning approaches.

Abstract

The development of autonomous driving has attracted extensive attention in recent years, and it is essential to evaluate the performance of autonomous driving. However, testing on the road is expensive and inefficient. Virtual testing is the primary way to validate and verify self-driving cars, and the basis of virtual testing is to build simulation scenarios. In this paper, we propose a training, testing, and evaluation pipeline for the lane-changing task from the perspective of deep reinforcement learning. First, we design lane change scenarios for training and testing, where the test scenarios include stochastic and deterministic parts. Then, we deploy a set of benchmarks consisting of learning and non-learning approaches. We train several state-of-the-art deep reinforcement learning methods in the designed training scenarios and provide the benchmark metrics evaluation results of the trained models in the test scenarios. The designed lane-changing scenarios and benchmarks are both opened to provide a consistent experimental environment for the lane-changing task.