RENet: Fault-Tolerant Motion Control for Quadruped Robots via Redundant Estimator Networks under Visual Collapse

2025-09-11

AI Summary

To address visual instability in vision-based locomotion control of quadrupedal robots under outdoor visual degradation (e.g., strong illumination, low-texture surfaces, rain, fog), this paper proposes a fault-tolerant visual-inertial cooperative control framework. The method introduces a dual-estimator redundant architecture with online adaptive switching, integrating depth-sensor noise suppression, real-time visual state monitoring, and dynamic module reconfiguration to enable seamless estimation transition upon visual failure. Evaluated on a physical quadrupedal robot platform, the approach significantly enhances robustness in challenging outdoor environments: it maintains stable walking even under severe visual degradation, achieving a 37% improvement in motion success rate over baseline methods. This work establishes a reliable perception–control coupling paradigm for autonomous navigation in unstructured野外 settings.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: Adversarial Attacks & Robustness
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Vision-based locomotion in outdoor environments presents significant challenges for quadruped robots. Accurate environmental prediction and effective handling of depth sensor noise during real-world deployment remain difficult, severely restricting the outdoor applications of such algorithms. To address these deployment challenges in vision-based motion control, this letter proposes the Redundant Estimator Network (RENet) framework. The framework employs a dual-estimator architecture that ensures robust motion performance while maintaining deployment stability during onboard vision failures. Through an online estimator adaptation, our method enables seamless transitions between estimation modules when handling visual perception uncertainties. Experimental validation on a real-world robot demonstrates the framework's effectiveness in complex outdoor environments, showing particular advantages in scenarios with degraded visual perception. This framework demonstrates its potential as a practical solution for reliable robotic deployment in challenging field conditions. Project website: https://RENet-Loco.github.io/

Problem

• Addresses vision-based locomotion challenges in outdoor quadruped robots
• Handles depth sensor noise and environmental prediction difficulties
• Ensures robust motion control during visual perception failures

Innovation

• Dual-estimator architecture for fault tolerance
• Online adaptation for seamless transition
• Handling visual perception uncertainties robustly