CRLLK: Constrained Reinforcement Learning for Lane Keeping in Autonomous Driving
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912298980868096 |
|---|---|
| author | Gao, Xinwei Singh, Arambam James Royyuru, Gangadhar Yuhas, Michael Easwaran, Arvind |
| author_facet | Gao, Xinwei Singh, Arambam James Royyuru, Gangadhar Yuhas, Michael Easwaran, Arvind |
| contents | Lane keeping in autonomous driving systems requires scenario-specific weight tuning for different objectives. We formulate lane-keeping as a constrained reinforcement learning problem, where weight coefficients are automatically learned along with the policy, eliminating the need for scenario-specific tuning. Empirically, our approach outperforms traditional RL in efficiency and reliability. Additionally, real-world demonstrations validate its practical value for real-world autonomous driving. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_22248 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CRLLK: Constrained Reinforcement Learning for Lane Keeping in Autonomous Driving Gao, Xinwei Singh, Arambam James Royyuru, Gangadhar Yuhas, Michael Easwaran, Arvind Machine Learning Robotics I.2.6; I.2.9; I.5.1; C.3; I.2.11 Lane keeping in autonomous driving systems requires scenario-specific weight tuning for different objectives. We formulate lane-keeping as a constrained reinforcement learning problem, where weight coefficients are automatically learned along with the policy, eliminating the need for scenario-specific tuning. Empirically, our approach outperforms traditional RL in efficiency and reliability. Additionally, real-world demonstrations validate its practical value for real-world autonomous driving. |
| title | CRLLK: Constrained Reinforcement Learning for Lane Keeping in Autonomous Driving |
| topic | Machine Learning Robotics I.2.6; I.2.9; I.5.1; C.3; I.2.11 |
| url | https://arxiv.org/abs/2503.22248 |