Learning to Track Dynamic Targets in Partially Known Environments
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.
Code (1)
Tasks
Deep Reinforcement LearningNavigateReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Active Scout: Multi-Target Tracking Using Neural Radiance Fields in Dense Urban Environments
We study pursuit-evasion games in highly occluded urban environments, e.g. tall buildings in a city, where a scout (quadrotor) tracks multiple dynamic targets on the ground. We show that we can build a neural radiance fi…
NeRFBandit Submodular Maximization for Multi-Robot Coordination in Unpredictable and Partially Observable Environments
We study the problem of multi-agent coordination in unpredictable and partially observable environments, that is, environments whose future evolution is unknown a priori and that can only be partially observed. We are mo…
Autonomous Drone Swarm Navigation and Multi-target Tracking in 3D Environments with Dynamic Obstacles
Autonomous modeling of artificial swarms is necessary because manual creation is a time intensive and complicated procedure which makes it impractical. An autonomous approach employing deep reinforcement learning is pres…
Deep Reinforcement LearningManagementreinforcement-learningReinforcement Learning (RL)Collaborative State Fusion in Partially Known Multi-agent Environments
In this paper, we study the collaborative state fusion problem in a multi-agent environment, where mobile agents collaborate to track movable targets. Due to the limited sensing range and potential errors of on-board sen…
State EstimationA Cross-Scene Benchmark for Open-World Drone Active Tracking
Drone Visual Active Tracking aims to autonomously follow a target object by controlling the motion system based on visual observations, providing a more practical solution for effective tracking in dynamic environments. …
Domain Generalization