Multi-agent search improves by skipping early belief sharing
Entropy-Gated Belief Coordination for Decentralized Multi-Agent Search Under Intermittent Communication
Robotics
Summary
Finding targets using many agents can be tricky when they can only talk sometimes. The authors found that if agents share all their guesses too early, they waste chances to search better. Instead, they propose only sharing information when it helps focus the search, measured by how uncertain their collective guesses are. Their method improves the chance of correctly locating targets, even beating approaches that always share all information.
What this means in practice
- •For robotics engineers: Improve coordination in robots that search large areas with limited communication by gating data fusion based on uncertainty levels.
- •For sensor network designers: Design sensor systems that reduce redundant data sharing by coordinating fusion only when collective uncertainty is low, saving bandwidth and energy.
Authors
Mohamed Abdelnaby, Kevin Leahy
Abstract
We study decentralized multi-agent target search where homogeneous agents communicate intermittently at Poisson-distributed times. Standard unconditional belief fusion wastes communication opportunities by synchronizing agents during high-entropy exploration, when diverse independent beliefs provide better coverage than a premature consensus. We introduce \emph{entropy-gated belief coordination}, in which agents skip fusion while their collective entropy ratio exceeds a threshold~\(θ\) and merge only during exploitation, consistent with the bifurcation structure of nonlinear opinion dynamics and the submodular structure of the per-step information gain objective. We further derive \(\Istep(α,β)\), the expected mutual information per observation step between two agents' binary sensors, as an interpretable, communication-free measure of sensor informativeness that motivates the gating design and guides system-level analysis. Experiments across 103{,}680 trials (nine grid sizes up to \(100{\times}100\), Poisson communication timing, four target movement patterns) show that the Entropy-Gated Trust-Decay Planner (\textsc{EG-TDP}), which adds a detection-probability planner switch in exploitation mode, achieves mean belief quality \(\bar{Q}=0.300\) (mean belief mass at the true target cell, averaged across all trials and steps), a \(58.9\%\) gain over arithmetic mean and a \(37.4\%\) gain over visit-weighted fusion. On representative configurations, EG-TDP also outperforms a joint-Bayesian reference that uses all agents'~observations at every step, despite operating under random intermittent contact only.