Sensorized gecko adhesives sense grip states for orbital robots
Towards Interaction State Recognition in Sensorized Gecko-Inspired Adhesive Interfaces for Orbital Servicing
RoboticsMachine Learning
Summary
Grabbing and holding things in space is tricky because robots often don't know if they are really touching or holding an object. The authors worked on special sticky pads inspired by gecko feet that have tiny sensors inside them to tell what kind of contact they have. By using smart computer programs to read the sensors, the pads can figure out if they are near, touching, gripping, or letting go of a surface. This helps space robots better know when they successfully catch or release objects without needing extra help.
What this means in practice
- •For space robotics engineers: Enable spacecraft robots to detect and monitor their grip state when capturing targets using sensorized adhesive pads.
- •For robotics hardware developers: Integrate capacitive sensing and lightweight classifiers into adhesive interfaces to improve robotic manipulation feedback in confined environments.
Authors
Eduart Abdullahu, Francesco Grella, Carol Martinez
Abstract
Reliable contact establishment remains a critical challenge for autonomous on-orbit servicing (OOS), particularly when interacting with non-cooperative targets. Gecko-inspired dry adhesives provide a lightweight, passive, and residue-free solution for robotic capture in space, yet current systems operate in open loop, without the ability to estimate their own contact or adhesion state during interaction. This paper presents a real-time interaction-awareness framework that enables sensorized gecko-inspired adhesive interfaces to estimate their contact state throughout the adhesion lifecycle using embedded capacitive sensing. Five discrete interaction states (idle, proximity, contact, engaged, and disengaged) are classified using experimentally collected and augmented sensor data, enabling a comparative evaluation of six lightweight machine learning models suitable for embedded deployment. Among the evaluated models, Random Forest achieved the highest offline classification accuracy of 95.65%. For online deployment, combining Random Forest with a rule-based state machine improved accuracy from 78.02% to 93.14%, achieving a macro F1-score of 0.9343 while maintaining a 53 ms inference cycle. These results demonstrate that incorporating physics-consistent state constraints significantly improves robustness during realtime inference, representing a step toward interaction-aware capture in future autonomous orbital servicing missions.