Abstract
AcTExplore relies solely on tactile sensation to automatically explore and navigate objects when traditional visual cues fade away. We have trained it on primitive objects(cube, sphere), enhancing its proficiency in fundamental movements and enabling exploration across a diverse range of objects. 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.
Type
Amir-Hossein Shahidzadeh
PhD Student
My research is at the intersection of Robot Perception and Reinforcement Learning.