Probabilistic Consensus on Feature Distribution for Multi-robot Systems with Markovian Exploration Dynamics
This addresses the challenge of robust and scalable information fusion for multi-robot teams in applications like navigation or object detection, but it is incremental as it builds on existing consensus and Markov chain methods.
The paper tackles the problem of decentralized multi-robot systems reconstructing a feature distribution in a 2D environment using a consensus-based approach with Markovian exploration, proving that each robot's estimate converges almost surely to the ground truth and showing in simulations that the Hellinger distance converges to zero.
In this paper, we present a consensus-based decentralized multi-robot approach to reconstruct a discrete distribution of features, modeled as an occupancy grid map, that represent information contained in a bounded planar 2D environment, such as visual cues used for navigation or semantic labels associated with object detection. The robots explore the environment according to a random walk modeled by a discrete-time discrete-state (DTDS) Markov chain and estimate the feature distribution from their own measurements and the estimates communicated by neighboring robots, using a distributed Chernoff fusion protocol. We prove that under this decentralized fusion protocol, each robot's feature distribution converges to the ground truth distribution in an almost sure sense. We verify this result in numerical simulations that show that the Hellinger distance between the estimated and ground truth feature distributions converges to zero over time for each robot. We also validate our strategy through Software-In-The-Loop (SITL) simulations of quadrotors that search a bounded square grid for a set of visual features distributed on a discretized circle.