Decentralized Coordinated Tracking with Mixed Discrete–Continuous Decisions

Abstract

In this paper, we study the problem of dynamically positioning a team of mobile robots for target tracking. We treat the coordination of mobile robots for target tracking as a joint team optimization to minimize uncertainty in target state estimates over a fixed horizon. The optimization is inherently a function of both the positioning of robots in continuous space and the assignment of robots to targets in discrete space. Thus, the robot team must make decisions over discrete and continuous variables. In contrast to methods that decouple target assignments and robot positioning, our approach avoids the strong assumption that a robot's utility for observing a target is independent of other robots’ observations. We formulate the optimization as a mixed integer nonlinear program and apply integer relaxation to develop an approximate solution in decentralized form. We demonstrate our coordinated multirobot tracking algorithm both in simulation and using a pair of mobile robotic sensor platforms to track moving pedestrians. Our results show that coupling target assignment and robot positioning realizes coordinated behaviors that are not possible with decoupled methods.

Multi-robot path planning for budgeted active perception with self-organising maps

“…Coverage tasks are most similar to our problem, which require a team of robots to collectively observe every location in an environment [25]. Target tracking and search problems require using the sensing capabilities of multiple robots to locate and maintain contact with targets [8], [10], [11]. Mapping tasks require adaptively exploring unobserved regions [10].…”

“…The informativeness of observations, and therefore the performance of perception algorithms, can be improved by judiciously selecting observation locations [4]. Performance can be significantly improved by using longer planning horizons [5], [6], [7], jointly planning for multiple robots [8], [9], [10], [11] and considering larger sets of candidate sensing locations. However, current planning algorithms with these properties are often too computationally expensive for practical use in large scale and more complex active perception tasks; we propose a self-organising map algorithm as a solution to bridge this gap.…”

Online planning for multi-robot active perception with self-organising maps

“…The informativeness of observations, and therefore the performance of perception algorithms, can be improved by judiciously selecting observation locations (Chen et al, 2011). Performance can be significantly improved by using longer planning horizons (Singh et al, 2009;Becerra et al, 2016;Atanasov et al, 2014), jointly planning for multiple robots (Best et al, 2016a;Charrow, 2015;Garg and Ayanian, 2014;Xu et al, 2013;Hollinger et al, 2009) and considering larger sets of candidate sensing locations. However, current planning algorithms with these properties are often too computationally expensive for practical use in large scale, online and more complex active perception tasks; we propose a self-organising map algorithm as a solution to bridge this gap.…”

Viewpoint Evaluation for Online 3-D Active Object Classification

“…A CTIVE perception seeks to control the acquisition of sensor data in order to improve the performance of perception algorithms. Although certain perception tasks such as searching [1] and tracking [2] are routinely cast as active information maximisation problems, object classification is traditionally studied as a passive perception problem where data are collected during robot navigation and fed into a perception pipeline. We wish to improve the performance of object classification algorithms, particularly in cluttered and occluded environments, by taking an active approach.…”