Resource-constrained decentralized active sensing for multi-robot systems using distributed Gaussian processes

Abstract

We consider the problem of area coverage for robot teams operating under resource constraints, while modeling spatio-temporal environmental phenomena. The aim of the mobile robot team is to avoid exhaustive search and only visit the most important locations that can improve the prediction accuracy of a spatio-temporal model. We use a Gaussian Process (GP) to model spatially varying and temporally evolving dynamics of the target phenomenon. Each robot of the team is allocated a dedicated search area wherein the robot autonomously optimizes its prediction accuracy. We present this as a Decentralized Computation and Centralized Data Fusion approach wherein the trajectory sampled by the robot is generated using our proposed Resource-Constrained Decentralized Active Sensing (RC-DAS). Since each robot possesses its own independent prediction model, at the end of robot's mission time, we fuse all the prediction models from all robots to have a global model of the spatio-temporal phenomenon. Previously, all robots and GPs needed to be synchronized, such that the GPs can be jointly trained. However, doing so defeats the purpose of a fully decentralized mobile robot team. Thus, we allow the robots to independently gather new measurements and update their model parameters irrespective of other members of the team. To evaluate the performance of our model, we compare the trajectory traced by the robot using active and passive (e.g., nearest neighbor selection) sensing. We compare the performance and cost incurred by a resource constrained optimization with the unconstrained entropy maximization version

Multi-Step Predictions for Adaptive Sampling using Proximal ADMM

“…For instance, the authors in [14] presented a method to partition a MRSN into several small groups in which each group is responsible for finding its optimal sampling locations. Likewise, Tiwari et al, [15] considered a decentralized multi-robot system where each robot is allocated in a local sensing zone for the monitoring purpose. By exploiting Voronoi concepts, the work [16] proposes a method that allows each sensing agent to conduct the adaptive sampling tasks within its dynamic cell area.…”

“…The augmented Lagrangian function of the problem ( 15) is defined by 16) where u is a vector of the associated dual variables and ρ is a regularization parameter. And the nonconvex conventional ADMM algorithm [40] can be utilized to solve the optimization problem (15) in the following steps at each iteration.…”

“…Proof: From Lemmas 4 and 5 aforementioned and Theorem 1 in [12], Algorithm 1 can converge the solution of the problem (15) to a stationary point if ρ > 5L.…”

Multi-Step Predictions for Adaptive Sampling using Proximal ADMM

“…For instance, the authors of [14] presented a method to partition an MRSN into several small groups, in which each group is responsible for finding its own optimal sampling locations. Likewise, Tiwari et al, [15] considered a decentralized multirobot system where each robot is allocated a local sensing zone for monitoring. By exploiting the Voronoi concept, the authors of [16] proposed a method that allows each sensing agent to conduct its adaptive sampling tasks within its dynamic cell area.…”

A laser-based multi-robot collision avoidance approach in unknown environments

“…1 It possesses the characteristics of parallelism, robustness, and flexibility with a wide variety of applications such as autonomous warehouse, 2,3 military, aerospace, and search and rescue. Existing researches focus on the problems including tasks and resource distribution, sensing, conflict resolution, formation, coordinated planning, and so on.…”