Learning-Based Real-Time Down-Sampling for Scalable Decentralized Decision-Making in Bayes-Swarm Search

Abstract A swarm of robots working together promises efficient solutions toward searching for signal sources in hazard localization and search-and-rescue applications. An effective class of such swarm search algorithms is one that constructs, progressively refines, and uses a belief model of the signal environment. These algorithms however risk becoming too computationally burdensome for real-time or onboard decentralized implementation as the size of the swarm or mission duration increases. Other applications that involve collecting an increasing amount of spatially distributed data and building belief models thereof to make decisions face this risk as well. To alleviate this risk, this article presents a new learning-based down-sampling approach applied to a notable search algorithm called Bayes-Swarm, which uses a Gaussian process model of the signal environment. The proposed down-sampling approach involves three key elements: (1) a new abstraction of the input encoding visited locations and the down-sampled data, (2) a probabilistic loss function based on Sinkhorn distance to capture the down-sampling performance, and (3) a convolutional neural network (CNN) to perform this down-sampling. These elements enable learning a generalized way to down-sample observations without requiring expensive simulations of the swarm search process. The new Bayes-Swarm implementation with the CNN-based down-sampling (CNN-Bayes-Swarm) is found to be agnostic to increasing dataset size unlike the original Bayes-Swarm, without significant compromise in search completion time. CNN-Bayes-Swarm also outperforms other baseline down-samplers in terms of search performance and computing costs considered together.