Learning to Track Dynamic Targets in Partially Known Environments

2020/06/17 by Heejin Jeong, Jeong, Heejin, Hamed Hassani +7 · 8 citations
Computer Science · Mathematics · #Anomaly Detection Techniques and Applications #Computer science #Machine Learning and Algorithms #Operating system #Reinforcement Learning in Robotics #Track (disk drive) #cs.LG #cs.RO #stat.ML

paper · pdf · doi:10.48550/arxiv.2006.10190

published in arXiv (Cornell University) (Cornell University) · IEEE Transaction on Robotics (under review); Demo video: https://youtu.be/0ZFyOWJ2ulo ; Source code: https://github.com/coco66/ttenv

arxiv created 2020/06/17 · openalex publication_date 2020/06/17 · arxiv updated 2020/06/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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 targets of interests using its onboard sensors. The classical challenges in this problem are system model dependence and the difficulty of computing information-theoretic cost functions for a long planning horizon. RL provides solutions for these challenges as the length of its effective planning horizon does not affect the computational complexity, and it drops the strong dependency of an algorithm on system models. In particular, we introduce Active Tracking Target Network (ATTN), a unified RL policy that is capable of solving major sub-tasks of active target tracking -- in-sight tracking, navigation, and exploration. The policy shows robust behavior for tracking agile and anomalous targets with a partially known target model. Additionally, the same policy is able to navigate in obstacle environments to reach distant targets as well as explore the environment when targets are positioned in unexpected locations.

Citations

• Planning and acting in partially observable stochastic domains

Cited by

• Reinforcement Learning for Heterogeneous Sensor Selection in Maritime Surveillance
• Detection of Static and Mobile Targets by an Autonomous Agent with Deep Q-Learning Abilities

Related

• Reinforcement Learning for Agile Active Target Sensing with a UAV
• Spatio-Temporal Attention Network for Persistent Monitoring of Multiple Mobile Targets
• Stone Soup Multi-Target Tracking Feature Extraction For Autonomous Search And Track In Deep Reinforcement Learning Environment
• Active Robotic Mapping through Deep Reinforcement Learning
• Track-MDP: Reinforcement Learning for Target Tracking with Controlled Sensing