Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.15790 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929297471569920 |
|---|---|
| author | Lin, Yuan Liu, Xiao Zheng, Zishun |
| author_facet | Lin, Yuan Liu, Xiao Zheng, Zishun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_15790 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Discretionary Lane-Change Decision and Control via Parameterized Soft Actor-Critic for Hybrid Action Space Lin, Yuan Liu, Xiao Zheng, Zishun Robotics Systems and Control 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. |
| title | Discretionary Lane-Change Decision and Control via Parameterized Soft Actor-Critic for Hybrid Action Space |
| topic | Robotics Systems and Control |
| url | https://arxiv.org/abs/2402.15790 |