We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Discretionary Lane-Change Decision and Control via Parameterized Soft Actor–Critic for Hybrid Action Space.
- Authors
Lin, Yuan; Liu, Xiao; Zheng, Zishun
- Abstract
This study focuses on a crucial task in the field of autonomous driving, autonomous lane change. Autonomous lane change plays a pivotal role in improving traffic flow, alleviating driver burden, and reducing the risk of traffic accidents. However, due to the complexity and uncertainty of lane-change scenarios, the functionality of autonomous lane change still faces challenges. In this research, we conducted autonomous lane-change simulations using both deep reinforcement learning (DRL) and model predictive control (MPC). Specifically, we used the parameterized soft actor–critic (PASAC) algorithm to train a DRL-based lane-change strategy to output both discrete lane-change decisions and continuous longitudinal vehicle acceleration. We also used MPC for lane selection based on the smallest predictive car-following costs for the different lanes. For the first time, we compared the performance of DRL and MPC in the context of lane-change decisions. The simulation results indicated that, under the same reward/cost function and traffic flow, both MPC and PASAC achieved a collision rate of 0%. PASAC demonstrated a comparable performance to MPC in terms of average rewards/costs and vehicle speeds.
- Subjects
DEEP reinforcement learning; REINFORCEMENT learning; COST functions; TRAFFIC flow; ACCELERATION (Mechanics); AUTONOMOUS vehicles; LANE changing
- Publication
Machines, 2024, Vol 12, Issue 4, p213
- ISSN
2075-1702
- Publication type
Article
- DOI
10.3390/machines12040213