Abstract
Object transfer through throwing is a classic dynamic manipulation task that necessitates precise control and perception capabilities. However, developing dynamic models for unstructured environments using analytical methods presents challenges. In this study, we present DartBot, a robot that integrates tactile exploration and reinforcement learning to achieve robust throwing skills for nonrigid relatively small objects under the influence of moment of inertia which cause the object to spin in the air. Unlike traditional sim-to-real transfer methods, our approach involves direct training of the agent on a real hardware robot equipped with a high-resolution tactile sensor, enabling reinforced learning in a realistic and dynamic environment. By leveraging tactile perception, we incorporate pseudo-embeddings of the physical properties of objects into the learning process through tilting actions at two distinct angles. This tactile information enables the agent to infer and adapt its throwing strategy, resulting in improved accuracy when handling various objects and targeting distant locations. Furthermore, we demonstrate that the quality of a grasp significantly impacts the success rate of the throwing task. We evaluate the effectiveness of our method through extensive experiments, demonstrating superior performance and generalization capabilities in real-world throwing scenarios. We achieved a success rate of 95% for unseen objects with a mean error of 3.15 cm from the goal.
Keywords
Tactile-based manipulation, force and tactile sensing, perception for grasping and manipulation, reinforcement learning
Date of this Version
3-2025
Recommended Citation
Aslam, Shoaib; Kumar, Krish; Zhou, Pokuang; Yu, Hongyu; Wang, Michael Yu; and She, Yu, "DartBot: Overhand Throwing of Deformable Objects with Tactile Sensing and Reinforcement Learning" (2025). School of Industrial Engineering Faculty Publications. Paper 19.
https://docs.lib.purdue.edu/iepubs/19
Comments
This is the author-accepted manuscript of DartBot: Overhand Throwing of Deformable Objects with Tactile Sensing and Reinforcement Learning, Shoaib Aslam, Pokuang Zhou, Krish Kumar, Hongyu Yu, Michael Wang, and Yu She, IEEE Transactions on Automation Science and Engineering (TASE), 2025.(c) 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works. The version of record can be found at DOI: 10.1109/TASE.2025.3556875.