Policy Learning for Active Target Tracking over Continuous $SE(3)$ Trajectories
Abstract
This paper proposes a novel \emph{model-based policy gradient algorithm} for tracking dynamic targets using a mobile robot, equipped with an onboard sensor with a limited field of view. The task is to obtain a continuous control policy for the mobile robot to collect sensor measurements that reduce uncertainty in the target states, measured by the target distribution entropy. We design a neural network control policy with the robot $SE(3)$ pose and the mean vector and information matrix of the joint target distribution as inputs and attention layers to handle variable numbers of targets. We also derive the gradient of the target entropy with respect to the network parameters explicitly, allowing efficient model-based policy gradient optimization.
Cite
Text
Yang et al. "Policy Learning for Active Target Tracking over Continuous $SE(3)$ Trajectories." Proceedings of The 5th Annual Learning for Dynamics and Control Conference, 2023.Markdown
[Yang et al. "Policy Learning for Active Target Tracking over Continuous $SE(3)$ Trajectories." Proceedings of The 5th Annual Learning for Dynamics and Control Conference, 2023.](https://mlanthology.org/l4dc/2023/yang2023l4dc-policy/)BibTeX
@inproceedings{yang2023l4dc-policy,
title = {{Policy Learning for Active Target Tracking over Continuous $SE(3)$ Trajectories}},
author = {Yang, Pengzhi and Koga, Shumon and Asgharivaskasi, Arash and Atanasov, Nikolay},
booktitle = {Proceedings of The 5th Annual Learning for Dynamics and Control Conference},
year = {2023},
pages = {64-75},
volume = {211},
url = {https://mlanthology.org/l4dc/2023/yang2023l4dc-policy/}
}