CaRoBio: 3D Cable Routing with a Bio-inspired Gripper Fingernail

2025-08-13

AI Summary

Automated 3D cable routing of deformable linear flexible objects (e.g., cables) suffers from excessive compression, slippage, and uncontrolled tension. Method: We propose a bio-inspired, eagle-claw-inspired gripper featuring nail-like surface structures, enabling simultaneous fingertip surface grasping and in-hand continuous guiding in a single grasp—first of its kind. Integrated with vision-based state estimation, motion-primitive-driven offline trajectory planning, and continuous closed-loop control, it forms an end-to-end robotic cable-routing framework that abandons the conventional pick-and-place paradigm. Contribution/Results: The method significantly improves manipulation stability and routing efficiency across diverse cable types and complex conduit configurations. Experiments demonstrate strong robustness under equivalent sensing conditions and cross-scenario generalizability. It provides a reconfigurable, highly adaptive solution for industrial 3D autonomous cable routing of flexible linear objects.

Technology Category

• Intelligent Robots: Manipulation
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Computer Vision: Vision for Robotics & Autonomous Driving

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

The manipulation of deformable linear flexures has a wide range of applications in industry, such as cable routing in automotive manufacturing and textile production. Cable routing, as a complex multi-stage robot manipulation scenario, is a challenging task for robot automation. Common parallel two-finger grippers have the risk of over-squeezing and over-tension when grasping and guiding cables. In this paper, a novel eagle-inspired fingernail is designed and mounted on the gripper fingers, which helps with cable grasping on planar surfaces and in-hand cable guiding operations. Then we present a single-grasp end-to-end 3D cable routing framework utilizing the proposed fingernails, instead of the common pick-and-place strategy. Continuous control is achieved to efficiently manipulate cables through vision-based state estimation of task configurations and offline trajectory planning based on motion primitives. We evaluate the effectiveness of the proposed framework with a variety of cables and channel slots, significantly outperforming the pick-and-place manipulation process under equivalent perceptual conditions. Our reconfigurable task setting and the proposed framework provide a reference for future cable routing manipulations in 3D space.

Problem

• Challenges in robot automation for cable routing tasks
• Risks of over-squeezing cables with common grippers
• Need for efficient 3D cable manipulation framework

Innovation

• Bio-inspired gripper fingernail for cable handling
• End-to-end 3D routing with vision-based control
• Offline trajectory planning using motion primitives