Name
Abstract | ||
|---|---|---|
In this paper we present a framework to learn skills from human demonstrations in the form of geometric nullspaces, which can be executed using a robot. We collect data of human demonstrations, fit geometric nullspaces to them, and also infer their corresponding geometric constraint models. These geometric constraints provide a powerful mathematical model as well as an intuitive representation of the skill in terms of the involved objects. To execute the skill using a robot, we combine this geometric skill description with the robot’s kinematics and other environmental constraints, from which poses can be sampled for the robot’s execution. The result of our framework is a system that takes the human demonstrations as input, learns the underlying skill model, and executes the learnt skill with different robots in different dynamic environments. We evaluate our approach on a simulated industrial robot, and execute the final task on the iCub humanoid robot. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/ICRA40945.2020.9197174 | ICRA |
DocType | Volume | Issue |
Conference | 2020 | 1 |
ISSN | Citations | PageRank |
2020 International Conference on Robotics and Automation (ICRA
2020) | 0 | 0.34 |
References | Authors | |
2 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Caixia Cai | 1 | 28 | 5.15 |
| Ying Siu Liang | 2 | 0 | 0.34 |
| Nikhil Somani | 3 | 43 | 7.34 |
| Yan Wu | 4 | 60 | 11.16 |