Journal Home Online First Current Issue Archive For Authors Journal Information 中文版

Frontiers of Information Technology & Electronic Engineering >> 2023, Volume 24, Issue 1 doi: 10.1631/FITEE.2200128

Stochastic pedestrian avoidance for autonomous vehicles using hybrid reinforcement learning

Affiliation(s): School of Vehicle and Mobility, Tsinghua University, Beijing 100084, China; Chinese Academy of Engineering, Beijing 100088, China; less

Received: 2022-04-03 Accepted: 2023-01-21 Available online: 2023-01-21

Next Previous

Abstract

Ensuring the safety of s is essential and challenging when are involved. Classical avoidance strategies cannot handle uncertainty, and learning-based methods lack performance guarantees. In this paper we propose a (HRL) approach for to safely interact with s behaving uncertainly. The method integrates the rule-based strategy and reinforcement learning strategy. The confidence of both strategies is evaluated using the data recorded in the training process. Then we design an activation function to select the final policy with higher confidence. In this way, we can guarantee that the final policy performance is not worse than that of the rule-based policy. To demonstrate the effectiveness of the proposed method, we validate it in simulation using an accelerated testing technique to generate stochastic s. The results indicate that it increases the success rate for avoidance to 98.8%, compared with 94.4% of the baseline method.

Related Research