Decentralized Distributed Expert Assisted Learning (D2EAL) approach for cooperative target-tracking

TL;DR

This paper introduces D2EAL, a decentralized learning algorithm for cooperative target tracking in multi-robot systems, which enhances prediction accuracy through dynamic information sharing and online weight adaptation.

Contribution

The paper presents a novel decentralized expert-assisted learning algorithm that improves multi-robot target tracking by online weight adaptation and dynamic information fusion.

Findings

D2EAL outperforms covariance-based methods in adverse scenarios.

Theoretical bounds on prediction loss are established.

Simulation results demonstrate improved scalability and accuracy.

Abstract

This paper addresses the problem of cooperative target tracking using a heterogeneous multi-robot system, where the robots are communicating over a dynamic communication network, and heterogeneity is in terms of different types of sensors and prediction algorithms installed in the robots. The problem is cast into a distributed learning framework, where robots are considered as 'agents' connected over a dynamic communication network. Their prediction algorithms are considered as 'experts' giving their look-ahead predictions of the target's trajectory. In this paper, a novel Decentralized Distributed Expert-Assisted Learning (D2EAL) algorithm is proposed, which improves the overall tracking performance by enabling each robot to improve its look-ahead prediction of the target's trajectory by its information sharing, and running a weighted information fusion process combined with online learning of weights based on a prediction loss metric. Theoretical analysis of D2EAL is carried out, which involves the analysis of worst-case bounds on cumulative prediction loss, and weights convergence analysis. Simulation studies show that in adverse scenarios involving large dynamic bias or drift in the expert predictions, D2EAL outperforms well-known covariance-based estimate/prediction fusion methods, both in terms of prediction performance and scalability.