Coordinated Target Tracking via a Hybrid Optimization Approach

Abstract

Recent advances in computer science and electronics have greatly expanded the capabilities of unmanned aerial vehicles (UAV) in both defense and civil applications, such as moving ground object tracking. Due to the uncertainties of the application environments and objects’ motion, it is difficult to maintain the tracked object always within the sensor coverage area by using a single UAV. Hence, it is necessary to deploy a group of UAVs to improve the robustness of the tracking. This paper investigates the problem of tracking ground moving objects with a group of UAVs using gimbaled sensors under flight dynamic and collision-free constraints. The optimal cooperative tracking path planning problem is solved using an evolutionary optimization technique based on the framework of chemical reaction optimization (CRO). The efficiency of the proposed method was demonstrated through a series of comparative simulations. The results show that the cooperative tracking paths determined by the newly developed method allows for longer sensor coverage time under flight dynamic restrictions and safety conditions.

Information-driven Persistent Sensing of a Non-cooperative Mobile Target Using UAVs

“…The work from Yu et al [45] obtained an 85% of visibility by using a single UAV and unmanned ground vehicle (UGV) with a target following a simple rectangular trajectory. Note that the results in [33,45] are not directly comparable to those of the proposed approach as the simulation conditions are different.…”

“…Game theory has also been successfully applied by Zhang and Liu [32] in order to address the persistent tracking problem by modelling the problem as a pursuit-evasion game. Wang and Cao [33] proposed a new framework technique based on chemical reaction optimization and considering flight dynamic and collision-free constraints . Tang and Ozguner [34] analysed the problem of multi target tracking proposing a gradient-approximation algorithm to travel through a series of defined target points achieving a cooperative tracking.…”

“…As discussed in Section 2, there have been some existing results reported. A persistent sensing algorithm, which is proposed by Wang and Cao [33], achieved a constant sensing an average 95 % of the time. This result are slightly better than the results obtained by the framework proposed in this paper, but the algorithm in [33] used 3 UAVs, not 2 UAVs, and are simulated in an urban environment with a reduced building density.…”

“…A persistent sensing algorithm, which is proposed by Wang and Cao [33], achieved a constant sensing an average 95 % of the time. This result are slightly better than the results obtained by the framework proposed in this paper, but the algorithm in [33] used 3 UAVs, not 2 UAVs, and are simulated in an urban environment with a reduced building density. The work from Yu et al [45] obtained an 85% of visibility by using a single UAV and unmanned ground vehicle (UGV) with a target following a simple rectangular trajectory.…”

Adaptation of Dubins Paths for UAV Ground Obstacle Avoidance When Using a Low Cost On-Board GNSS Sensor

“…If a camera is used, the methods for obstacle detection, avoidance and UAV control can be implemented in areas even without a Global Navigation Satellite System (GNSS) signal [ 14 ]. Camera images can be used for ground obstacle detection and identification, tracking of other UAVs, and, if needed, as a navigation data sensor for other ground obstacle avoidance algorithms [ 15 ]. The image depth may be used to predict the distance to the obstacle [ 16 ] and, in some cases, can be shared between several unmanned vehicles [ 17 ].…”