Decentralized Nested Gaussian Processes for Multi-Robot Systems

In this paper, we propose two decentralized approximate algorithms for nested Gaussian processes in multi-robot systems. The distributed implementation is achieved with iterative and consensus methods that facilitate local computations at the expense of inter-robot communications. Moreover, we propose a covariance-based nearest neighbor robot selection strategy that enables a subset of agents to perform predictions. In addition, both algorithms are proved to be consistent. Empirical evaluations with real data illustrate the efficiency of the proposed algorithms.

Authors

• George P. Kontoudis
• Daniel J. Stilwell

Keywords

• Automation
• Conferences
• Gaussian processes
• Prediction algorithms
• Topology
• Computational efficiency
• Multi-robot systems
• Gaussian Process
• Multi-agent Systems
• Local Computing
• Consensus Method
• Number Of Observations
• Information Exchange
• Linear Equation
• Network Topology
• Time Complexity
• Sea Surface Temperature
• Local Method
• Autonomous Vehicles
• Central Node
• Mean Prediction
• Space Complexity
• Calculation Of Mean
• Unknown Vector
• Linear Graph
• RMSE Values
• Graph Topology
• Robotic Network
• Subset Of Observations
• Communication Requirements
• Local Input
• Predictor Variables
• Strong Connection
• Covariance Matrix
• Element Of Vector
• Mean Square Error