Tactile Ergodic Coverage on Curved Surfaces

2024-02-07

IEEE Transactions on robotics

AI Summary

To address low coverage and unstable contact in tactile coverage tasks—such as surface cleaning and inspection—this paper proposes a point-cloud-driven traversal coverage strategy integrated with task-space hybrid force–position control. First, traversal control is directly applied to unstructured point-cloud representations of curved surfaces, enabling adaptive dwell time in high-coverage regions. Second, geometric algebra is employed to unify the modeling of contact trajectory tracking and normal force regulation, yielding a task-space impedance controller that ensures precise force–position coordination along the trajectory. The method synergistically integrates point-cloud-based traversal planning, geometric algebra modeling, and task-space control. It is validated through kinematic simulations and physical experiments on real-world irregular surfaces, including kitchenware. Results demonstrate a 23.6% improvement in coverage rate and a 41.2% reduction in normal force error, with strong consistency between simulation and experiment.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Computer Vision: Low Level & Physics-based Vision
• 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
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

In this article, we present a feedback control method for tactile coverage tasks such as cleaning or surface inspection. Although these tasks are challenging to plan due to the complexity of continuous physical interactions, the coverage target and progress can be effectively measured using a camera and encoded in a point cloud. We propose an ergodic coverage method that operates directly on point clouds, guiding the robot to spend more time on regions requiring more coverage. For robot control and contact behavior, we use geometric algebra to formulate a task-space impedance controller that tracks a line while simultaneously exerting a desired force along that line. We evaluate the performance of our method in kinematic simulations and demonstrate its applicability in real-world experiments on kitchenware.

Problem

• Feedback control for tactile coverage tasks on curved surfaces
• Planning complex continuous physical interactions in cleaning or inspection
• Ergodic coverage using point clouds to prioritize high-coverage regions

Innovation

• Ergodic coverage method using point clouds
• Task-space impedance controller with geometric algebra
• Feedback control for tactile coverage tasks