Multi-Objective Multi-Agent Planning for Discovering and Tracking Multiple Mobile Objects

被引:5
作者
Nguyen, Hoa Van [1 ]
Vo, Ba-Ngu [1 ]
Vo, Ba-Tuong [1 ]
Rezatofighi, Hamid [2 ]
Ranasinghe, Damith C. [3 ]
机构
[1] Curtin Univ, Dept Elect & Comp Engn, Bentley, WA 6102, Australia
[2] Monash Univ, Dept Data Sci & AI, Clayton, Vic 3800, Australia
[3] Univ Adelaide, Sch Comp Sci, Adelaide, SA 5005, Australia
基金
澳大利亚研究理事会;
关键词
Planning; Aerospace electronics; Radar tracking; Robot sensing systems; Radio frequency; Trajectory; Vectors; Stochastic control; path planning; multi-agent control; MPOMDP; multi-object tracking; APPROXIMATIONS; OPTIMIZATION; ALGORITHM; TARGETS; MODEL;
D O I
10.1109/TSP.2024.3423755
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
We consider the online planning problem for a team of agents to discover and track an unknown and time-varying number of moving objects from onboard sensor measurements with uncertain measurement-object origins. Since the onboard sensors have limited field-of-views, the usual planning strategy based solely on either tracking detected objects or discovering unseen objects is inadequate. To address this, we formulate a new information-based multi-objective multi-agent control problem, cast as a partially observable Markov decision process (POMDP). The resulting multi-agent planning problem is exponentially complex due to the unknown data association between objects and multi-sensor measurements; hence, computing an optimal control action is intractable. We prove that the proposed multi-objective value function is a monotone submodular set function, which admits low-cost suboptimal solutions via greedy search with a tight optimality bound. The resulting planning algorithm has a linear complexity in the number of objects and measurements across the sensors, and quadratic in the number of agents. We demonstrate the proposed solution via a series of numerical experiments with a real-world dataset.
引用
收藏
页码:3669 / 3685
页数:17
相关论文
共 55 条
[1]   Active sensing for motion planning in uncertain environments via mutual information policies [J].
A Macdonald, Ryan ;
Smith, Stephen L. .
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2019, 38 (2-3) :146-161
[2]  
[Anonymous], 2006, Probabilistic Robotics. Intelligent Robotics and Autonomous Agents
[3]   Multi-Sensor Multi-Object Tracking With the Generalized Labeled Multi-Bernoulli Filter [J].
Ba-Ngu Vo ;
Ba-Tuong Vo ;
Beard, Michael .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2019, 67 (23) :5952-5967
[4]   Labeled Random Finite Sets and Multi-Object Conjugate Priors [J].
Ba-Tuong Vo ;
Ba-Ngu Vo .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2013, 61 (13) :3460-3475
[5]   A Solution for Large-Scale Multi-Object Tracking [J].
Beard, Michael ;
Vo, Ba Tuong ;
Vo, Ba-Ngu .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2020, 68 :2754-2769
[6]   The complexity of decentralized control of Markov decision processes [J].
Bernstein, DS ;
Givan, R ;
Immerman, N ;
Zilberstein, S .
MATHEMATICS OF OPERATIONS RESEARCH, 2002, 27 (04) :819-840
[7]   Informative Path Planning for an Autonomous Underwater Vehicle [J].
Binney, Jonathan ;
Krause, Andreas ;
Sukhatme, Gaurav S. .
2010 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2010, :4791-4796
[8]  
Blackman S., 1999, Design and analysis of modern tracking systems, ser. The Artech House radar library
[9]   ConservationBots: Autonomous aerial robot for fast robust wildlife tracking in complex terrains [J].
Chen, Fei ;
Nguyen, Hoa Van ;
Taggart, David A. ;
Falkner, Katrina ;
Rezatofighi, S. Hamid ;
Ranasinghe, Damith C. .
JOURNAL OF FIELD ROBOTICS, 2024, 41 (02) :443-469
[10]   Observer and control design in partially observable finite Markov chains [J].
Clempner, Julio B. ;
Poznyak, Alexander S. .
AUTOMATICA, 2019, 110