Potential Game-Based Non-Myopic Sensor Network Planning for Multi-Target Tracking

Park, Soon-Seo; Choi, Han‐Lim

doi:10.1109/access.2018.2885027

Cited by 10 publications

(13 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors of [15] and [16] proposed games-based scheme and a distributed strategy with consensus on estimates and missing data in terms of multi-target tracking, respectively. The objective of maximizing information about the target state and of estimating real-time position is designed to service the total mobile sensor network better.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Intelligent Resource Collaboration in Mobile Target Tracking Oriented Mission-Critical Sensor Networks

et al. 2020

View full text Add to dashboard Cite

Mobile target tracking-oriented sensor networks are a special kind of Mission-critical Sensor Networks (MCSN), in which the various missions with the diverse priorities exist. However, it is challenging to achieve real time tracking while keeping the MCSN a long life time with limited energy provision in a complicated environment. In this paper, we develop a collaborative perception and intelligent scheduling scheme, which jointly optimizes the system responding latency and tracking accuracy with the constraint of the available energy. A new hierarchical architecture is proposed to realize the coupled function of perception and computation. In particular, the multi-node collaborative perception scheme is applied to obtain the excellent sensing capacity, and the Unmanned Aerial Vehicles (UAVs) play as the edge nodes to provide the computing service for those resource-constrained sensor nodes. To reach the sustained target tracking, we propose an intelligent tracking policy by exploiting the deep deterministic policy gradient (DDPG) method. Simulation results demonstrate that the proposed intelligent collaboration scheme can improve the tracking accuracy by 45.5% compared with the random selection scheme. The system cost is also reduced approximately by 17.3% while guaranteeing the tracking accuracy. INDEX TERMS Multi-target tracking, energy consumption, collaborative perception, deep reinforcement learning.

show abstract

Section: Related Workmentioning

confidence: 99%

“…To clearly state, the simulation parameters of MMT for executing critical missions are summarized in Table 2. We compare our proposed scheme with the random selection scheme and non-myopic planning (OL) based on the potential game [15].…”

Section: A Simulation Setupmentioning

confidence: 99%

Intelligent Resource Collaboration in Mobile Target Tracking Oriented Mission-Critical Sensor Networks

et al. 2020

View full text Add to dashboard Cite

show abstract

“…This measure of uncertainty is combined with various matrices such as the Fisher information (FIM) [3]- [5], mutual information [6], [7], or trace [8], [9], and is then used to optimize the variables that determine the operation of the sensing agents. In the target tracking problem, sensor planning problems are divided into two major classes: (a) Sensor scheduling [10]- [16] and (b) the trajectory planning of mobile sensors [3]- [6], [8], [9], [17]- [21]. Sensor scheduling attempts to select some of the multiple available static sensors at each time step to minimize the weighted sum of all estimation errors over a certain time horizon.…”

Section: Introductionmentioning

confidence: 99%

“…One approach to solving this problem is to extend the method developed for sensor scheduling purposes. Decision variables, such as selecting the sensor in the sensor scheduling problem, can be treated in the same way as variables such as the control input of the mobile sensor [16], [17], [21]. However, this approach entails the computation time problem that occurs in sensor scheduling and requires an algorithm such as branch-and-bound based pruning [17].…”

Section: Introductionmentioning

confidence: 99%

A Distributed ADMM Approach to Non-Myopic Path Planning for Multi-Target Tracking

Park

Min

et al. 2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

This paper presents a distributed optimization method for informative trajectory planning in multi-target tracking problems. The purpose of such problems is to optimize a sequence of waypoints/control inputs of mobile sensors over a certain future time step to minimize the uncertainty of targets. The planning problem is reformulated as a distributed optimization problem that can be expressed in the form of a subproblem for each target. The subproblems are coupled using the distributed Alternating Direction Method of Multipliers (ADMM). This coupling not only enables the results of each subproblem to be reflected in the optimization process of the other subproblems, but also guides the results of the subproblems to converge to the same solution. In contrast to existing approaches performing trajectory optimization after assigning tasks, the proposed algorithm does not require the design of a heuristic cost function for task assignment, and it can handle both non-myopic trajectory planning and task assignment in multiple target tracking problems simultaneously. In order to reduce the computation time of the algorithm, an edge-cutting method suitable for multiple target tracking problems is proposed, as a receding-horizon control scheme for real-time implementation, which considers the computation time. Numerical examples are presented to demonstrate the applicability of the algorithm.

show abstract

“…The key technical challenge in the operation of such networked mobile sensor systems is to efficiently deploy and maneuver the mobile sensors to maximize the information about the target systems of interest. These kinds of problems can be described as a sensor planning problem that optimizes the utilization of the mobile sensors given current states of the target systems and resources while considering the mobility of the mobile sensors.Information and game theoretic approaches have been extensively explored to solve such problem by efficiently operating mobile sensor networks [3][4][5][6]. For instance, Hoffmann and Tomlin [3] proposed sensor network planning framework which is scalable and capable of accurately capturing and using information.…”

mentioning

confidence: 99%

Informative Planning of Mobile Sensor Networks in GPS-Denied Environments

Min¹,

Park²,

Choi³

2020

AIAA Scitech 2020 Forum

Self Cite

View full text Add to dashboard Cite

This paper considers the problem to plan mobile sensor networks for target localization task in GPS-denied environments. Most researches on mobile sensor networks assume that the states of the sensing agents are precisely known during their missions, which is not feasible under the absence of external infrastructures such as GPS. Thus, we propose a new algorithm to solve this problem by: (i) estimating the states of the sensing agents in addition to the target's through the combination of a particle filter (PF) and extended Kalman filters (EKF) and (ii) involving the uncertainty of the states of the sensing agents in planning the sensor networks based on the combined filters. This approach does not require any additional internal/external sensors nor the prior knowledge of the surrounding environments. We demonstrate the limitations of prior works in GPS-denied environments and the improvements from the proposed algorithm through Monte Carlo experiments. I. IntroductionT chnological advances in mobile sensor networks have enabled the applications of monitoring spatio-temporal phenomena, terrain mapping, and source localization [1-3]. The key technical challenge in the operation of such networked mobile sensor systems is to efficiently deploy and maneuver the mobile sensors to maximize the information about the target systems of interest. These kinds of problems can be described as a sensor planning problem that optimizes the utilization of the mobile sensors given current states of the target systems and resources while considering the mobility of the mobile sensors.Information and game theoretic approaches have been extensively explored to solve such problem by efficiently operating mobile sensor networks [3][4][5][6]. For instance, Hoffmann and Tomlin [3] proposed sensor network planning framework which is scalable and capable of accurately capturing and using information. The mutual information between the sensor measurements and the target state is directly computed using a particle filter representation of the posterior distribution without Gaussian approximation. Mutual information is one popular metric of information gain, which is known as a more fundamental quantity of information than entropy [7]. Choi and Lee [5] and Lee et al.[6] also adopted mutual information to quantify the amount of the information about the target systems and formulated the sensor network planning problems into a potential game. The joint strategy fictitious play method is then applied to obtain a distributed solution that provably converges to a pure strategy Nash equilibrium. Shen et al. [4] proposed a negotiable game-theoretic based sensor management method to deal with the requirements of dynamic sensor management and assignment.However, such approaches generally assume that they have perfect information and control on the state of each agent in the networks through the internal sensors, such as on-board IMU, and external infrastructures, such as Global Positioning System (GPS) [8]. The estimation on the position of an agent...

show abstract

Potential Game-Based Non-Myopic Sensor Network Planning for Multi-Target Tracking

Cited by 10 publications

References 33 publications

Intelligent Resource Collaboration in Mobile Target Tracking Oriented Mission-Critical Sensor Networks

Intelligent Resource Collaboration in Mobile Target Tracking Oriented Mission-Critical Sensor Networks

A Distributed ADMM Approach to Non-Myopic Path Planning for Multi-Target Tracking

Informative Planning of Mobile Sensor Networks in GPS-Denied Environments

Contact Info

Product

Resources

About