SandWorm: Event-based Visuotactile Perception with Active Vibration for Screw-Actuated Robot in Granular Media
🤖 AI Summary
This work addresses the challenge of perception in granular media arising from the unpredictable dynamics of particles by introducing SandWorm, a bioinspired screw-driven robot, and SWTac, an event-driven visuotactile sensor. By integrating active vibration of an elastomer, peristaltic locomotion, and a mechanically decoupled spring-isolation structure, combined with an IMU-guided temporal filtering algorithm and a U-Net-based contact interface estimation method leveraging asymmetric edge features, the system significantly enhances tactile imaging quality and environmental adaptability. The proposed approach achieves a tactile resolution of 0.2 mm, 98% accuracy in rock classification, and a force estimation error of 0.15 N. The robot demonstrates a locomotion speed of 12.5 mm/s in granular media and accomplishes dredging and subsurface exploration tasks with over 90% success rate.
Application Category
📝 Abstract
Perception in granular media remains challenging due to unpredictable particle dynamics. To address this challenge, we present SandWorm, a biomimetic screw-actuated robot augmented by peristaltic motion to enhance locomotion, and SWTac, a novel event-based visuotactile sensor with an actively vibrated elastomer. The event camera is mechanically decoupled from vibrations by a spring isolation mechanism, enabling high-quality tactile imaging of both dynamic and stationary objects. For algorithm design, we propose an IMU-guided temporal filter to enhance imaging consistency, improving MSNR by 24%. Moreover, we systematically optimize SWTac with vibration parameters, event camera settings and elastomer properties. Motivated by asymmetric edge features, we also implement contact surface estimation by U-Net. Experimental validation demonstrates SWTac's 0.2 mm texture resolution, 98% stone classification accuracy, and 0.15 N force estimation error, while SandWorm demonstrates versatile locomotion (up to 12.5 mm/s) in challenging terrains, successfully executes pipeline dredging and subsurface exploration in complex granular media (observed 90% success rate). Field experiments further confirm the system's practical performance.
Problem
Research questions and friction points this paper is trying to address.
granular media
visuotactile perception
event-based sensing
robotic perception
tactile sensing
Innovation
Methods, ideas, or system contributions that make the work stand out.
event-based visuotactile sensing
active vibration
screw-actuated robot
granular media perception
IMU-guided temporal filtering
🔎 Similar Papers
No similar papers found.
