BayesCPF: Enabling Collective Perception in Robot Swarms with Degrading Sensors

2025-04-07

AI Summary

Addressing the challenge of accurately estimating environmental features—such as spatial occupancy rate—and achieving consensus in multi-robot swarms with continuously degrading sensors, this paper proposes BayesCPF, the first distributed collective perception filtering framework supporting time-varying sensor degradation. BayesCPF integrates extended Kalman filtering into Bayesian Consensus Probabilistic Filtering to enable online self-calibration and robust state estimation, jointly incorporating distributed consensus, sensor degradation modeling, and real-time calibration. Simulations and physical experiments demonstrate that, under unknown degradation patterns, occupancy rate estimation accuracy approaches that of ideal (non-degrading) sensors, while maintaining strong robustness against diverse degradation models, initial estimation errors, and time-varying communication topologies. The core contribution is the first principled integration of dynamic sensor degradation modeling with distributed Bayesian filtering, yielding a provably convergent theoretical framework and a practical algorithm for collaborative swarm perception in degraded environments.

Technology Category

• Intelligent Robots: State Estimation
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

The collective perception problem -- where a group of robots perceives its surroundings and comes to a consensus on an environmental state -- is a fundamental problem in swarm robotics. Past works studying collective perception use either an entire robot swarm with perfect sensing or a swarm with only a handful of malfunctioning members. A related study proposed an algorithm that does account for an entire swarm of unreliable robots but assumes that the sensor faults are known and remain constant over time. To that end, we build on that study by proposing the Bayes Collective Perception Filter (BayesCPF) that enables robots with continuously degrading sensors to accurately estimate the fill ratio -- the rate at which an environmental feature occurs. Our main contribution is the Extended Kalman Filter within the BayesCPF, which helps swarm robots calibrate for their time-varying sensor degradation. We validate our method across different degradation models, initial conditions, and environments in simulated and physical experiments. Our findings show that, regardless of degradation model assumptions, fill ratio estimation using the BayesCPF is competitive to the case if the true sensor accuracy is known, especially when assumptions regarding the model and initial sensor accuracy levels are preserved.

Problem

• Enabling robot swarms with degrading sensors to achieve collective perception
• Estimating environmental feature fill ratio despite time-varying sensor degradation
• Validating method across degradation models and environments

Innovation

• BayesCPF estimates fill ratio with degrading sensors
• Extended Kalman Filter calibrates time-varying sensor degradation
• Validated across diverse degradation models and environments