SwingBot: Learning Physical Features from In-hand Tactile Exploration for Dynamic Swing-up Manipulation
| Autor: | Edward H. Adelson, Chen Wang, Branden Romero, Filipe Veiga, Shaoxiong Wang |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
0209 industrial biotechnology Computer Science - Machine Learning Computer science Computer Science - Artificial Intelligence Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology 010501 environmental sciences 01 natural sciences Task (project management) Machine Learning (cs.LG) Computer Science - Robotics 020901 industrial engineering & automation Computer vision 0105 earth and related environmental sciences business.industry Swing Object (philosophy) Pipeline (software) Artificial Intelligence (cs.AI) Feature (computer vision) Task analysis Robot Artificial intelligence business Robotics (cs.RO) |
| Zdroj: | arXiv IROS |
| Popis: | Several robot manipulation tasks are extremely sensitive to variations of the physical properties of the manipulated objects. One such task is manipulating objects by using gravity or arm accelerations, increasing the importance of mass, center of mass, and friction information. We present SwingBot, a robot that is able to learn the physical features of a held object through tactile exploration. Two exploration actions (tilting and shaking) provide the tactile information used to create a physical feature embedding space. With this embedding, SwingBot is able to predict the swing angle achieved by a robot performing dynamic swing-up manipulations on a previously unseen object. Using these predictions, it is able to search for the optimal control parameters for a desired swing-up angle. We show that with the learned physical features our end-to-end self-supervised learning pipeline is able to substantially improve the accuracy of swinging up unseen objects. We also show that objects with similar dynamics are closer to each other on the embedding space and that the embedding can be disentangled into values of specific physical properties. IROS 2020 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|