Stochastic surveillance strategies for spatial quickest detection

Srivastava, Vaibhav; Bullo, Francesco

doi:10.1109/cdc.2011.6160479

Cited by 9 publications

(13 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Srivastava [5]. For anomalies that might appear at nodes in a random manner, Srivastava et al have designed persistent surveillance strategies [6]. In addition, Agharkar et al have proposed efficient routing algorithms for robot surveillance using Markov chains [7].…”

Section: Introductionmentioning

confidence: 98%

Patrolling robot based on Bayesian learning for multiple intruders

Hoshino

Ugajin

Ishiwata

2015

2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Patrolling is an important task for autonomous mobile robots. In this paper, we focus on a single patrolling robot in indoor environments composed of rooms. For the robot, it is required to visit the rooms and detect unknown intruders as many as possible. However, the robot does not have correct information about intruders in the initiation step of patrolling. Therefore, the robot first acquires the information through the patrolling trials. As for the information, the robot focuses on intrusion probabilities into the rooms. Subsequently, target rooms are determined on the basis of the intrusion probabilities. This so-called explore/exploit tradeoff in reinforcement learning is a challenge for the intelligent patrolling. In this paper, we tackle the patrolling problem as a part of the learning issues. Thus a multi-armed bandit problem is introduced. For the challenge, we propose stochastic patrolling strategies based on Bayesian learning. Simulation experiments show that the robot is enabled to estimate the correct intrusion probabilities of the rooms. Through the discussion of the patrolling results, finally, we present the most effective patrolling strategy.

show abstract

Section: Introductionmentioning

confidence: 98%

Patrolling robot based on Bayesian learning for multiple intruders

Hoshino

Ugajin

Ishiwata

2015

2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

show abstract

“…T HERE has been a growing interest in recent years in the analysis and control of multi agent and networked systems. The potential of such systems stems from the societal impact that they promise to deliver: from medicine [2] to surveillance [3], from future mobility [4] to food production [5], to name a few. The typical challenge in the control of such systems is the design of agent-level decision rules that are capable of achieving a desirable joint objective by relying solely on local information.…”

Section: Introductionmentioning

confidence: 99%

Utility Design for Distributed Resource Allocation -- Part II: Applications to Submodular, Covering, and Supermodular Problems

Paccagnan¹,

Marden²

2018

Preprint

View full text Add to dashboard Cite

A fundamental component of the game theoretic approach to distributed control is the design of local utility functions. In Part I of this work we showed how to systematically design local utilities so as to maximize the induced worst case performance. The purpose of the present manuscript is to specialize the general results obtained in Part I to a class of monotone submodular, supermodular and set covering problems. In the case of set covering problems, we show how any distributed algorithm capable of computing a Nash equilibrium inherits a performance certificate matching the well known 1 − 1/e approximation of [1]. Relative to the class of submodular maximization problems considered here, we show how the performance offered by the game theoretic approach improves on existing approximation algorithms. We briefly discuss the algorithmic complexity of computing (pure) Nash equilibria and show how our approach generalizes and subsumes previously fragmented results in the area of optimal utility design. Two applications and corresponding numerics are presented: the vehicle target assignment problem and a coverage problem arising in distributed caching for wireless networks.

show abstract

“…The fusion center runs parallel CUSUM tests to detect any anomaly in any of the regions. For stationary region selection probabilities, that the worst case expected detection delay [15] at region k is…”

Section: A Spatial Quickest Detectionmentioning

confidence: 99%

“…The adaptive spatial quickest detection Algorithm 1 utilizes the current observations to adapt the region selection policy (see [15] for details.) …”

Section: A Spatial Quickest Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive attention allocation in human-robot systems

Srivastava

Surana²,

Bullo

2012

2012 American Control Conference (ACC)

View full text Add to dashboard Cite

Abstract-We propose an optimization framework to study two fundamental attention control aspects in human-robot systems: Where and how much attention should the operator allocate? In other words, which information source should be observed by the operator, and how much time duration should be allocated to the information feed in order to optimize the overall performance of the human-robot system? The proposed framework incorporates (i) operator performance constraints, such as error rates and service times based utilization history, (ii) sensor constraints, such as processing/travel time, and (iii) task constraints, such as prioritization. We use a receding horizon approach to solve the resulting dynamic program, leading to efficient policies for operator time duration allocation and sensor selection. We demonstrate our methodology in a distributed surveillance problem.

show abstract

Stochastic surveillance strategies for spatial quickest detection

Cited by 9 publications

References 36 publications

Patrolling robot based on Bayesian learning for multiple intruders

Patrolling robot based on Bayesian learning for multiple intruders

Utility Design for Distributed Resource Allocation -- Part II: Applications to Submodular, Covering, and Supermodular Problems

Adaptive attention allocation in human-robot systems

Contact Info

Product

Resources

About