Uploaded March 2021 | Updated September 2026, 2 hours ago
Video for the IROS 2021 submission.
Preprint: arxiv.org/abs/2103.06742.
Code: github.com/ZJU-FAST-Lab/visPlanner.
The visibility of targets determines the performance and even success rate of various applications, such as active slam, exploration, and target tracking. Therefore, it is crucial to take the visibility of targets into explicit account in trajectory planning. In this paper, we propose a general metric for target visibility, considering observation distance and angle as well as the occlusion effect. We formulate this metric into a differentiable visibility cost function, with which spatial trajectory and yaw can be jointly optimized. Furthermore, this visibility-aware trajectory optimization handles the dynamic feasibility of position and yaw simultaneously. To validate that our method is practical and generic, we integrate it into a customized quadrotor tracking system. The experimental results show that our visibility-aware planner performs more robustly and observes targets better. In order to benefit related researches, we release our code to the public.
Video for the IROS 2021 submission.
Preprint: arxiv.org/abs/2103.06742.
Code: github.com/ZJU-FAST-Lab/visPlanner.
The visibility of targets determines the performance and even success rate of various applications, such as active slam, exploration, and target tracking. Therefore, it is crucial to take the visibility of targets into explicit account in trajectory planning. In this paper, we propose a general metric for target visibility, considering observation distance and angle as well as the occlusion effect. We formulate this metric into a differentiable visibility cost function, with which spatial trajectory and yaw can be jointly optimized. Furthermore, this visibility-aware trajectory optimization handles the dynamic feasibility of position and yaw simultaneously. To validate that our method is practical and generic, we integrate it into a customized quadrotor tracking system. The experimental results show that our visibility-aware planner performs more robustly and observes targets better. In order to benefit related researches, we release our code to the public.
