RoTip: A Finger-Shaped Tactile Sensor with Active Rotation

2024-10-01

arXiv.org

AI Summary

Existing tactile sensors exhibit insufficient flexibility and perception accuracy for dexterous manipulation of thin, soft objects, limiting fine manipulation performance. This paper introduces RoTip—a finger-shaped tactile sensor integrating an active rotational joint with full-surface vision-based tactile sensing—enabling, for the first time in a finger-like structure, synergistic dynamic motion and real-time deformation feedback during contact. Methodologically, RoTip combines miniature servo actuation, elastomer-camera coupled deformation modeling, and real-time contact pose estimation. Experiments demonstrate its capability to stably grasp, reorient, and precisely manipulate thin sheets, cables, and small rigid objects. RoTip breaks from conventional static tactile sensing paradigms by introducing rotation-augmented tactile perception, providing a novel solution for dexterous manipulation of soft and deformable objects.

Technology Category

• Intelligent Robots: Manipulation
• Computer Vision: Motion & Tracking
• Planning, Routing, and Scheduling: Activity and Plan Recognition

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
• Search and Retrieval-Augmented AI: Agentic search

Abstract

In recent years, advancements in optical tactile sensor technology have primarily centred on enhancing sensing precision and expanding the range of sensing modalities. To meet the requirements for more skilful manipulation, there should be a movement towards making tactile sensors more dynamic. In this paper, we introduce RoTip, a novel vision-based tactile sensor that is uniquely designed with an independently controlled joint and the capability to sense contact over its entire surface. The rotational capability of the sensor is particularly crucial for manipulating everyday objects, especially thin and flexible ones, as it enables the sensor to mobilize while in contact with the object's surface. The manipulation experiments demonstrate the ability of our proposed RoTip to manipulate rigid and flexible objects, and the full-finger tactile feedback and active rotation capabilities have the potential to explore more complex and precise manipulation tasks.

Problem

• Flexible Sensors
• Perception Accuracy
• Soft Object Manipulation

Innovation

• Rotatable Tactile Sensor
• Self-rotating Functionality
• Precision Object Manipulation