Loading...
Please wait, while we are loading the content...
Similar Documents
From Low-Level Trajectory Demonstrations to Symbolic Actions for Planning
| Content Provider | Semantic Scholar |
|---|---|
| Author | Abdo, Nichola Kretzschmar, Henrik Stachniss, Cyrill |
| Copyright Year | 2012 |
| Abstract | Robots that should solve complex manipulation tasks need to reason about their actions on a symbolic level to compute plans comprising sequences of actions. Planning, however, requires knowledge about the preconditions and effects of all the actions. In this work, we present an approach that allows a robot to learn manipulation skills from teacher demonstrations. Our approach enables the robot to learn to physically execute the motion needed to perform the actions, and, most importantly, to infer the preconditions and effects. Our system can express the acquired manipulation action as symbolic planning operators and thus can use any modern planner to solve tasks that are more complex than the individual, demonstrated actions. We implemented our approach on a PR2 robot and present real world manipulation experiments that illustrate that our system allows non-experts to transfer knowledge to robots. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://www.informatik.uni-freiburg.de/~kretzsch/pdf/abdo12tampra.pdf |
| Alternate Webpage(s) | http://www.first-mm.eu/files/abdo12tampra.pdf |
| Alternate Webpage(s) | http://www.informatik.uni-freiburg.de/~stachnis/pdf/abdo12tampra.pdf |
| Alternate Webpage(s) | http://ais.informatik.uni-freiburg.de/publications/papers/abdo12tampra.pdf |
| Alternate Webpage(s) | http://www2.informatik.uni-freiburg.de/~stachnis/pdf/abdo12tampra.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |