-
[show abstract]
[hide abstract]
ABSTRACT: In this paper, we consider mobile sensor networks that use spatiotemporal Gaussian processes to predict a wide range of spatiotemporal physical phenomena. Nonparametric Gaussian process regression that is based on truncated observations is proposed for mobile sensor networks with limited memory and computational power. We first provide a theoretical foundation of Gaussian process regression with truncated observations. In particular, we demonstrate that prediction using all observations can be well approximated by prediction using truncated observations under certain conditions. Inspired by the analysis, we then propose a centralized navigation strategy for mobile sensor networks to move in order to reduce prediction error variances at points of interest. For the case in which each agent has a limited communication range, we propose a distributed navigation strategy. Particularly, we demonstrate that mobile sensing agents with the distributed navigation strategy produce an emergent, swarming-like, collective behavior for communication connectivity and are coordinated to improve the quality of the collective prediction capability.
IEEE Transactions on Robotics 01/2012; · 2.54 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: This paper presents an explorative navigation method using sparse Gaussian processes for mobile sensor networks. We first show that a near-optimal approximation is possible with a subset of measurements if we select the subset carefully, i.e., if the correlation between the selected measurements and the remaining measurements is small and the correlation between the prediction locations and the remaining measurements is small. An estimation method based on a subset of measurements is desirable for mobile sensor networks since we can always bound computational and memory requirements and unprocessed raw measurements can be easily shared with other agents for further processing (e.g., consensus-based distributed algorithms or distributed learning). We then present an explorative navigation method using sparse Gaussian processes with a subset of measurements. Using the explorative navigation method, mobile sensor networks can actively seek for new measurements to reduce the prediction error and maintain high-quality estimation about the field of interest indefinitely with limited memory.
Decision and Control (CDC), 2010 49th IEEE Conference on; 01/2011
-
IEEE Transactions on Robotics. 01/2011; 27:1118-1131.
-
Proceedings of the 49th IEEE Conference on Decision and Control, CDC 2010, December 15-17, 2010, Atlanta, Georgia, USA; 01/2010
-
[show abstract]
[hide abstract]
ABSTRACT: This paper presents a novel class of self-organizing multi-agent systems that form a swarm and learn a spatio- temporal process through noisy measurements from neighbors for various global goals. The physical spatio-temporal process of interest is modeled by a spatio-temporal Gaussian process. Each agent maintains its own posterior predictive statistics of the Gaussian process based on measurements from neighbors. A set of biologically inspired navigation strategies are identified from the posterior predictive statistics. A unified way to prescribe a global goal for the group of agents is presented. A reference trajectory state that guides agents to achieve the maximum of the objective function is proposed. A switching protocol is proposed for achieving the global maximum of a spatio- temporal Gaussian process over the surveillance region. The usefulness of the proposed multi-agent system with respect to various global goals is demonstrated by several numerical examples.
American Control Conference, 2008; 07/2008
-
[show abstract]
[hide abstract]
ABSTRACT: This paper presents a novel class of self-organizing autonomous sensing agents that form a swarm and learn the static field of interest through noisy measurements from neighbors for gradient climbing. In particular, each sensing agent maintains its own smooth map which estimates the field. It updates its map using measurements from itself and its neighbors and simultaneously moves toward a maximum of the field using the gradient of its map. The proposed cooperatively learning control consists of motion coordination based on the recursive spatial estimation of an unknown field of interest with measurement noise. The convergence properties of the proposed coordination algorithm are analyzed using the ODE approach and verified by a simulation study.
Decision and Control, 2007 46th IEEE Conference on; 01/2008
-
[show abstract]
[hide abstract]
ABSTRACT: This paper presents an algorithm and analysis of distributed learning and cooperative control for a multi-agent system so that a global goal of the overall system can be achieved by locally acting agents. We consider a resource-constrained multi-agent system, in which each agent has limited capabilities in terms of sensing, computation, and communication. The proposed algorithm is executed by each agent independently to estimate an unknown field of interest from noisy measurements and to coordinate multiple agents in a distributed manner to discover peaks of the unknown field. Each mobile agent maintains its own local estimate of the field and updates the estimate using collective measurements from itself and nearby agents. Each agent then moves towards peaks of the field using the gradient of its estimated field while avoiding collision and maintaining communication connectivity. The proposed algorithm is based on a recursive spatial estimation of an unknown field. We show that the closed-loop dynamics of the proposed multi-agent system can be transformed into a form of a stochastic approximation algorithm and prove its convergence using Ljung’s ordinary differential equation (ODE) approach. We also present extensive simulation results supporting our theoretical results.
Automatica.
-
[show abstract]
[hide abstract]
ABSTRACT: This paper presents a novel class of self-organizing sensing agents that form a swarm and learn the static spatial process of interest through noisy measurements from neighbors for various global goals. The spatial phenomenon of interest is modeled by a Gaussian process. Each sensing agent maintains its own prediction of the Gaussian process based on measurements from neighbors. A set of biologically inspired navigation strategies are derived by exploiting the predictive posterior statistics. A unified way to prescribe a global goal for the group of agents so that a high-level behavior builds on a set of low-level simple behavior modules. As a result, collective mobility of agents emerges from a specified global goal. The proposed cooperatively learning control consists of motion coordination based on the recursive estimation of an unknown field of interest with measurement noise. The convergence properties of the proposed coordination algorithm for different situations and global goals are investigated by a simulation study.
