Deep reinforcement learning (DRL) has been demonstrated to be effective for the control of mixed-autonomy platoons. However, incorporating safety considerations into DRL typically relies on designing collision avoidance-based reward functions, which lack collision-free guarantees. To address this research gap, we introduce a differentiable safety layer to convert DRL actions to safe actions with collision-free guarantees, which relies on a differentiable quadratic programming problem featuring Control Barrier Function-based safety constraints. The proposed safety-informed DRL approach explicitly integrates safety constraints into the training process and enables our method to adapt to varying safety-critical scenarios. Simulation results demonstrate that our proposed method effectively ensures CAV safety in mixed platoon environments while simultaneously enhancing traffic capacity and string stability. Furthermore, the safety layer expedites training by reducing the range of exploration.
Safe Reinforcement Learning for Mixed-Autonomy Platoon Control
2023-09-24
605761 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Reinforcement Learning for Mixed Autonomy Intersections
IEEE | 2021
|Wiley | 2023
|DOAJ | 2023
|Safe platoon control of automated highway systems
Tema Archiv | 2001
|A safe stable directional vehicular platoon
SAGE Publications | 2015
|