A Dual-Mode Electrical Capacitance Tomography Sensor for Robotic Proximity Servoing and Grasping

Venue: RSS 2026 (Sydney, Jul 13–17) · Session: Robot & Sensor Design · paper #197 Authors: Duanpeng Shi, Yuliang Wang, Yuming Huang, Huaping Liu, Di Guo Program page: https://roboticsconference.org/program/papers/197/

No public preprint found (searched arXiv Aug 2026); summary derived from the verified program abstract. Trend placement and neighbors: RSS 2026 survey.

Summary

The paper targets the perception gap between far-field vision and near-field contact in robotic manipulation, where traditional dual-mode tactile/proximity sensors suffer from environmental interference. It presents a versatile sensing system based on Electrical Capacitance Tomography (ECT) that unifies non-contact proximity perception, pre-touch orientation estimation, and material recognition, realized in two configurations: a large-area array (10 cm × 10 cm) for high-dynamic safety feedback and a compact 2 cm × 9 cm module integrated into a gripper. Rather than expensive tomographic reconstruction, the authors propose CapacitiveServo-Net, a physics-informed deep-learning architecture that maps mutual-capacitance perturbations directly to geometric primitives (distance, orientation) and material properties. On a 7-DOF manipulator the system reportedly achieves high-precision non-contact proximity tracking, real-time pose alignment, and concurrent material classification with pre-touch adaptive grasp refinement, offering proactive perception in occluded or visually degraded environments.

Abstract

Tactile and proximity sensing is fundamental for achieving autonomous robotic manipulation and safe human-robot interaction. However, traditional dual-mode sensors often face challenges such as environmental interference and the perception gap between far-field vision and near-field contact. This study presents a versatile sensing system based on Electrical Capacitance Tomography (ECT) principles, providing a unified framework for non-contact proximity perception, pre-touch orientation estimation and material recognition. We implement two distinct sensor configurations: a large-area array (10 cm × 10\text{ cm}) for high-dynamic safety feedback and a compact module integrated into a robotic gripper (2 cm × 9\text{ cm}). Instead of computationally expensive tomographic reconstruction, we propose CapacitiveServo-Net, a physics-informed deep learning architecture that extracts spatial dielectric features directly from mutual capacitance perturbations. This model facilitates a unified pre-touch servoing framework by mapping high-dimensional capacitive transients to geometric primitives (distance and orientation) and material properties. Experimental results on a 7-DOF manipulator demonstrate that our system achieves high-precision, non-contact proximity tracking and real-time pose alignment. Furthermore, the system demonstrates concurrent material classification and pre-touch adaptive grasp refinement during the approach phase, offering a robust, unified solution for proactive perception and manipulation in occluded or degraded visual environments.

Wiki context

Related topic reviews: Review-Tactile-VLA · Review-Dexterous-Manipulation

← Back to RSS 2026 survey · Home