Search papers, labs, and topics across Lattice.
This paper investigates the impact of different tactile interaction modes—grasp-releasing, finger-grazing-induced sliding, and palm-rolling—on the efficiency and accuracy of object shape reconstruction. They integrate these contact modes into an information-theoretic exploration framework that strategically selects subsequent contact locations based on a shape completion model. Results demonstrate that finger-grazing and palm-rolling achieve faster convergence and higher accuracy, requiring 34% fewer interactions and improving reconstruction accuracy by 55% compared to grasp-releasing.
Finger-grazing and palm-rolling aren't just fancy robot moves—they slash the number of tactile interactions needed for accurate 3D shape reconstruction by over a third, while boosting accuracy by more than half.
Tactile sensing allows robots to gather detailed geometric information about objects through physical interaction, complementing vision-based approaches. However, efficiently acquiring useful tactile data remains challenging due to the time-consuming nature of physical contact and the need to strategically choose contact locations that maximize information gain while minimizing physical interactions. This paper studies how different contact modes affect object shape reconstruction using a tactile-enabled dexterous gripper. We compare three contact interaction modes: grasp-releasing, sliding induced by finger-grazing, and palm-rolling. These contact modes are combined with an information-theoretic exploration framework that guides subsequent sampling locations using a shape completion model. Our results show that the improved tactile sensing efficiency of finger-grazing and palm-rolling translates into faster convergence in shape reconstruction, requiring 34% fewer physical interactions while improving reconstruction accuracy by 55%. We validate our approach using a UR5e robot arm equipped with an Inspire-Robots Dexterous Hand, showing robust performance across primitive object geometries.
