ArXiv TLDR

TouchDrive: Electronics-Free Tactile Sensing Interface for Assistive Grasping

🐦 Tweet
2605.06432

Jing Xu, Xuezhi Niu, Didem Gurdur Broo, Klas Hjort

cs.RO

TLDR

TouchDrive enables precise assistive robotic grasping using an electronics-free tactile sensing interface with pneumatic feedback.

Key contributions

  • Introduces TouchDrive, a passive mechanical tactile sensing interface without electronics.
  • Converts contact forces into pneumatic feedback via valve-mediated switching.
  • Enables users to modulate grasp force for delicate object manipulation.
  • Validated on multiple robots handling up to 20 diverse objects reliably.

Why it matters

This paper presents a simpler, cost-effective tactile sensing method that reduces system complexity and improves accessibility in assistive robotics. It enables safer, more precise grasping without electronic sensors.

Original Abstract

Assistive robotic grasping plays an important role in enabling safe and adaptive manipulation of diverse objects. However, existing systems often rely on electronic sensing and multi-stage processing pipelines, increasing system complexity and reducing accessibility. To address these limitations, we present TouchDrive, a cost-effective, electronics-free tactile sensing interface for assistive grasping. TouchDrive directly converts contact forces into pneumatic feedback through valve-mediated switching, integrating sensing, signal generation, and feedback within a single passive mechanical loop. The system can be employed using a pneumatic normally closed valve, a compressed air tank, sensing element, and haptic feedback actuator without electronics. By delivering tactile cues, TouchDrive empowers users to modulate grasp forces, enabling precise and robust delicate manipulation of compliant and fragile objects. The interface has been validated across diverse robotic platforms, consistently demonstrating reliable performance and practical applicability in assistive grasping tasks, such as handling fruits and everyday items (up to 20 objects).

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.