Reducing Uncertainty in Collective Perception using Self-organized Hierarchy

This dataset accompanies an article submission and a code repository.

Abstract:
In collective perception, agents sample spatial data and use the samples to agree on some estimate. In this research, we identify the sources of statistical uncertainty that occur in collective perception and note that improving the accuracy of fully decentralized approaches, beyond a certain threshold, might be intractable. We propose self-organized hierarchy as an approach to improve accuracy in collective perception, by reducing or eliminating some of the sources of uncertainty. Using self-organized hierarchy, aspects of centralization and decentralization can be combined: robots can understand their relative positions system-wide and fuse their information at one point, without requiring, e.g., a fully connected or static communication network. In this way, multi-sensor fusion techniques that have been designed for fully centralized systems can be applied to a self-organized system for the first time, without losing the key practical benefits of decentralization. We implement simple proof-of-concept fusion in a self-organized hierarchy approach and test it against three fully decentralized benchmark approaches. We test the perceptual accuracy of the approaches for time-invariant and time-varying absolute conditions, and test the scalability and fault tolerance of their accuracies. We show that the self-organized hierarchy approach is substantially more accurate, more consistent, and faster than the other approaches, but also that it is comparably scalable and fault-tolerant.