Describing Physics For Physical Reasoning: Force-Based Sequential Manipulation Planning
| Autor: | Jung-Su Ha, Marc Toussaint, Danny Driess |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
0209 industrial biotechnology
Control and Optimization Physical reasoning Mechanical Engineering Biomedical Engineering Ranging 02 engineering and technology Solver Computer Science Applications law.invention Computer Science::Robotics Human-Computer Interaction 020901 industrial engineering & automation Artificial Intelligence Control and Systems Engineering law Human–computer interaction 0202 electrical engineering electronic engineering information engineering Robot Leverage (statistics) 020201 artificial intelligence & image processing Animal cognition Contact dynamics Computer Vision and Pattern Recognition Wrench |
| Zdroj: | IEEE Robotics and Automation Letters. 5:6209-6216 |
| ISSN: | 2377-3774 |
| DOI: | 10.1109/lra.2020.3010462 |
| Popis: | Physical reasoning is a core aspect of intelligence in animals and humans. A central question is what model should be used as a basis for reasoning. Existing work considered models ranging from intuitive physics and physical simulators to contact dynamics models used in robotic manipulation and locomotion. In this work we propose descriptions of physics which directly allow us to leverage optimization methods for physical reasoning and sequential manipulation planning. The proposed multi-physics formulation enables the solver to mix various levels of abstraction and simplifications for different objects and phases of the solution. As an essential ingredient, we propose a specific parameterization of wrench exchange between object surfaces in a path optimization framework, introducing the point-of-attack as decision variable. We demonstrate the approach on various robot manipulation planning problems, such as grasping a stick in order to push or lift another object to a target, shifting and grasping a book from a shelve, and throwing an object to bounce towards a target. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|