Neural Cellular Automata for Decentralized Sensing using a Soft Inductive Sensor Array for Distributed Manipulator Systems

2025-02-03

AI Summary

To address the poor scalability and low robustness caused by centralized sensing in distributed robotic manipulator systems, this paper proposes a decentralized sensing architecture based on Neural Cellular Automata (NCA). For the first time, NCAs are deployed at the hardware level on a flexible inductive sensor array, enabling global object property estimation through local neighborhood communication and distributed state updates—without requiring a central controller. We innovatively design a dedicated flexible sensing circuit board supporting dynamic node addition/removal and fault tolerance against single-point failures. Hardware validation demonstrates: (i) object position estimation error ≤ 0.24× sensor pitch; and (ii) estimation accuracy remains >92% under 20% sensor failure and strong noise interference. The approach significantly enhances system scalability and robustness.

Technology Category

• Intelligent Robots: State Estimation
• Multiagent Systems: Distributed Problem Solving
• Natural Language Processing: Safety and Robustness

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

In Distributed Manipulator Systems (DMS), decentralization is a highly desirable property as it promotes robustness and facilitates scalability by distributing computational burden and eliminating singular points of failure. However, current DMS typically utilize a centralized approach to sensing, such as single-camera computer vision systems. This centralization poses a risk to system reliability and offers a significant limiting factor to system size. In this work, we introduce a decentralized approach for sensing and in a Distributed Manipulator Systems using Neural Cellular Automata (NCA). Demonstrating a decentralized sensing in a hardware implementation, we present a novel inductive sensor board designed for distributed sensing and evaluate its ability to estimate global object properties, such as the geometric center, through local interactions and computations. Experiments demonstrate that NCA-based sensing networks accurately estimate object position at 0.24 times the inter sensor distance. They maintain resilience under sensor faults and noise, and scale seamlessly across varying network sizes. These findings underscore the potential of local, decentralized computations to enable scalable, fault-tolerant, and noise-resilient object property estimation in DMS

Problem

• Decentralized Perception
• Robustness
• Scalability

Innovation

• Distributed Perception
• Neuronal Cellular Automata
• Soft Sensors