A Case-based Reward Function Design for Reinforcement Learning-based Pure Pursuit Hybrid Controller

• Item type: Symposium(1)
• 公開日: 2024-10-23
• タイトル: A Case-based Reward Function Design for Reinforcement Learning-based Pure Pursuit Hybrid Controller
• タイトル / 言語: en
• タイトル: A Case-based Reward Function Design for Reinforcement Learning-based Pure Pursuit Hybrid Controller
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: Reinforcement learning, Autonomous driving, Reward function, Adaptive pure pursuit, Path tracking
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_5794
• 資源タイプ: conference paper
• 著者所属: Kyushu University
• 著者所属: Kyushu University
• 著者所属: Kyushu University
• 著者所属(英): en
• 著者所属(英): Kyushu University
• 著者所属(英): en
• 著者所属(英): Kyushu University
• 著者所属(英): en
• 著者所属(英): Kyushu University
• 著者名: Pang, Lixin; Huang, Jianyu; Arakawa, Yutaka
• 著者名(英): Pang, Lixin; Huang, Jianyu; Arakawa, Yutaka
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: This paper presents an innovative approach to enhancing the Pure Pursuit algorithm for path tracking in autonomous vehicles by integrating Reinforcement Learning and curvature information. Traditional Pure Pursuit algorithms, while effective in low-speed scenarios, often require extensive manual tuning of the look-ahead distance to maintain tracking accuracy at varying speeds and complex paths. To address these limitations, we designed an RL-based pure pursuit controller incorporating future curvature into the state space and reward function to enhance learning a proper tracking policy at higher speeds. The controller is trained and evaluated in the CARLA simulator, demonstrating improved performance in terms of path-tracking accuracy and stability across different speeds and path complexities. By comparing the controller which considered curvature improvement with the original one, our results show that the improved method can achieve lower lateral deviation and lateral acceleration while maintaining almost the same average speed.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: This paper presents an innovative approach to enhancing the Pure Pursuit algorithm for path tracking in autonomous vehicles by integrating Reinforcement Learning and curvature information. Traditional Pure Pursuit algorithms, while effective in low-speed scenarios, often require extensive manual tuning of the look-ahead distance to maintain tracking accuracy at varying speeds and complex paths. To address these limitations, we designed an RL-based pure pursuit controller incorporating future curvature into the state space and reward function to enhance learning a proper tracking policy at higher speeds. The controller is trained and evaluated in the CARLA simulator, demonstrating improved performance in terms of path-tracking accuracy and stability across different speeds and path complexities. By comparing the controller which considered curvature improvement with the original one, our results show that the improved method can achieve lower lateral deviation and lateral acceleration while maintaining almost the same average speed.
• 書誌情報: 第32回マルチメディア通信と分散処理ワークショップ論文集; p. 71-77, 発行日 2024-10-23
• 出版者 / 言語: ja
• 出版者: 情報処理学会