Trajectory Tracking of Underactuated VTOL Aerial Vehicles With Unknown System Parameters Via IRL

• 成果类型: Article
• 署名作者: Li, Shaobao; Durdevic, Petar; Yang, Zhenyu
• 署名单位: Aalborg University
• 刊物名称: IEEE TRANSACTIONS ON AUTOMATIC CONTROL
• ISSN/ISSBN: 0018-9286
• DOI: 10.1109/TAC.2021.3095031
• 发表日期: 2022
• 页码: 3043-3050
• 关键词: Optimal control; Trajectory tracking; Heuristic algorithms; Vehicle dynamics; trajectory; Tracking loops; STANDARDS; Aerial vehicles; hybrid control; optimal control; reinforcement learning (RL); tracking control

摘要

This article studies the optimal control policy learning for underactuated vertical take-off and landing (VTOL) aerial vehicles subject to the unknown mass and inertia matrix. A novel off-policy integral reinforcement learning (IRL) scheme is presented for simultaneously unknown parameter identification and optimal trajectory tracking. In the outer loop of the VTOL vehicles, a novel off-policy IRL scheme is proposed, where the fixed control policy for data generation is chosen to be different from the iterated control policy and the feedforward term with an unknown mass can be learned along with the optimal control policy. In the inner loop, a hybrid off-policy IRL algorithm is developed to tackle the optimal attitude control policy learning and inertia matrix identification under the hybrid control scheme introduced by the employed inner-outer loop control strategy. A simulation study is finally provided to demonstrate the effectiveness of the proposed algorithm.