ErgoSurf: Ergodic Control for the Coverage of Unknown Surfaces

2026-08-06

AI Summary

This work addresses the challenge of simultaneously achieving stable contact and comprehensive coverage when robots perform contact-based tasks on unknown surfaces lacking prior geometric information. The authors propose a tactile-driven online coverage control framework that, for the first time, integrates Gaussian Process Implicit Surface (GPIS) modeling with ergodic control. Relying solely on proprioceptive tactile sensing, the method incrementally reconstructs surface geometry and generates coverage trajectories by approximating the local surface with point clouds on tangent planes and employing a heat-diffusion-inspired potential field for real-time motion planning. Both simulation and physical experiments demonstrate that the approach enables high-fidelity geometric reconstruction—yielding errors close to ground truth—and efficient full coverage, all without requiring visual input or prior models, thereby proving effective in dynamic, unstructured environments.

Abstract

Contact-centric tasks on surfaces, ranging from inspection and cleaning to sanding and polishing, require robots to systematically cover the surface while maintaining stable contact. Ergodic control generates trajectories that spend time at a location proportional to a desired, task-specific spatial distribution, enabling efficient information gathering and coverage. However, traditional ergodic control methods rely on prior knowledge of surface geometry or require a vision sensory input to scan the geometry beforehand, limiting their applicability in real-world scenarios with unknown or dynamic environments. This paper introduces a novel online ergodic control framework that achieves systematic surface coverage while simultaneously reconstructing unknown surface geometry. We employ a Gaussian Process Implicit Surface (GPIS) model that learns global surface geometry from intrinsic tactile sensing during execution. For efficient online planning, we approximate the surface locally using point clouds sampled from tangent planes at observed contact points and iteratively fit them to the Gaussian Process. This approximation simultaneously serves as the sampling domain for both the target and the coverage distributions. We employ a heat-diffusion analogy to compute potential fields that guide ergodic exploration, translating spatial coverage objectives into smooth robot trajectories. We demonstrate our framework through simulation and real-robot experiments, validating simultaneous ergodic coverage and online surface geometry learning with reconstruction errors approaching the ground truth.

Problem

• ergodic control
• surface coverage
• unknown surfaces
• tactile sensing
• online reconstruction

Innovation

• ergodic control
• Gaussian Process Implicit Surface
• tactile sensing
• online surface reconstruction
• coverage planning