State Estimation for Compliant and Morphologically Adaptive Robots

2025-09-30

AI Summary

For mobile robots exhibiting active/passive compliance and morphological adaptability, conventional rigid-body assumptions fail, and kinematics become dynamically variable—posing significant challenges for state estimation on complex terrain. This paper proposes the first unified state estimation framework integrating both rigid-body and compliant dynamics, innovatively introducing a morphology-aware reference frame. Within a compliance-centered coordinate system, the framework jointly predicts shape deformation, linear/angular velocity, and orientation. A neural network-based architecture models temporal state evolution and enables robust sensor fusion, trained on motion-capture data. Experimental results demonstrate shape prediction error below 4.2% of robot size, linear and angular velocity errors ≤6.3% and ≤2.4%, respectively, and orientation error ≤1.5°. Under sensor anomalies, closed-loop outdoor traversal distance improves by 300%, validating substantial gains in reliability and adaptability.

Technology Category

• Intelligent Robots: State Estimation
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Computer Vision: Motion & Tracking

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Locomotion robots with active or passive compliance can show robustness to uncertain scenarios, which can be promising for agricultural, research and environmental industries. However, state estimation for these robots is challenging due to the lack of rigid-body assumptions and kinematic changes from morphing. We propose a method to estimate typical rigid-body states alongside compliance-related states, such as soft robot shape in different morphologies and locomotion modes. Our neural network-based state estimator uses a history of states and a mechanism to directly influence unreliable sensors. We test our framework on the GOAT platform, a robot capable of passive compliance and active morphing for extreme outdoor terrain. The network is trained on motion capture data in a novel compliance-centric frame that accounts for morphing-related states. Our method predicts shape-related measurements within 4.2% of the robot's size, velocities within 6.3% and 2.4% of the top linear and angular speeds, respectively, and orientation within 1.5 degrees. We also demonstrate a 300% increase in travel range during a motor malfunction when using our estimator for closed-loop autonomous outdoor operation.

Problem

• Estimating robot states without rigid-body assumptions during morphological changes
• Predicting compliance-related states like soft robot shape across morphologies
• Enhancing state estimation reliability for compliant robots in outdoor terrain

Innovation

• Neural network state estimator for compliant robots
• Uses state history and sensor reliability mechanisms
• Predicts shape velocity orientation in morphing robots