AcTExplore: Active Tactile Exploration of Unknown Objects
This addresses the challenge of limited sensing coverage in tactile exploration for robotics, though it is incremental as it builds on existing reinforcement learning approaches.
The paper tackles the problem of efficiently exploring unknown objects using tactile sensors for robotics tasks by presenting AcTExplore, a reinforcement learning-driven method that achieves an average of 95.97% IoU coverage on unseen YCB objects after training on primitive shapes.
Tactile exploration plays a crucial role in understanding object structures for fundamental robotics tasks such as grasping and manipulation. However, efficiently exploring such objects using tactile sensors is challenging, primarily due to the large-scale unknown environments and limited sensing coverage of these sensors. To this end, we present AcTExplore, an active tactile exploration method driven by reinforcement learning for object reconstruction at scales that automatically explores the object surfaces in a limited number of steps. Through sufficient exploration, our algorithm incrementally collects tactile data and reconstructs 3D shapes of the objects as well, which can serve as a representation for higher-level downstream tasks. Our method achieves an average of 95.97% IoU coverage on unseen YCB objects while just being trained on primitive shapes. Project Webpage: https://prg.cs.umd.edu/AcTExplore