Policy Learning for Active Target Tracking over Continuous SE(3) Trajectories

2022-12-03 · Pengzhi Yang, Shumon Koga, Arash Asgharivaskasi, Nikolay Atanasov

This paper proposes a novel model-based policy gradient algorithm for tracking dynamic targets using a mobile robot, equipped with an onboard sensor with 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.

📄 PDF Abstract BibTeX arXiv:2212.01498

Code (1)

existentialrobotics/rl_active_multi_target_tracking 공식 구현 pytorch

Tasks

continuous-control Continuous Control

MATT-Diff: Multimodal Active Target Tracking by Diffusion Policy

2025-11-14 · Saida Liu, Nikolay Atanasov, Shumon Koga arxiv

This paper proposes MATT-Diff: Multimodal Active Target Tracking by Diffusion Policy, a control policy for active multi-target tracking using a mobile agent. The policy enables multiple behavior modes for the agent, incl…

Learning to Track Dynamic Targets in Partially Known Environments

2020-06-17 · Heejin Jeong, Hamed Hassani, Manfred Morari, Daniel D. Lee 외

We solve active target tracking, one of the essential tasks in autonomous systems, using a deep reinforcement learning (RL) approach. In this problem, an autonomous agent is tasked with acquiring information about target…

Deep Reinforcement Learning Navigate Reinforcement Learning (RL)

VLM Can Be a Good Assistant: Enhancing Embodied Visual Tracking with Self-Improving Vision-Language Models

2025-05-27 · Kui Wu, Shuhang Xu, Hao Chen, Churan Wang 외

We introduce a novel self-improving framework that enhances Embodied Visual Tracking (EVT) with Vision-Language Models (VLMs) to address the limitations of current active visual tracking systems in recovering from tracki…

Spatial Reasoning Visual Tracking

An Index Policy Based on Sarsa and Q-learning for Heterogeneous Smart Target Tracking

2024-02-19 · Yuhang Hao, Zengfu Wang, Jing Fu, Quan Pan

In solving the non-myopic radar scheduling for multiple smart target tracking within an active and passive radar network, we need to consider both short-term enhanced tracking performance and a higher probability of targ…

Q-Learning Scheduling

Diffusion Policy with Bayesian Expert Selection for Active Multi-Target Tracking

2026-04-03 · Haotian Xiang, Qin Lu, Yaakov Bar-Shalom arxiv

Active multi-target tracking requires a mobile robot to balance exploration for undetected targets with exploitation of uncertain tracked ones. Diffusion policies have emerged as a powerful approach for capturing diverse…