Name
Title | ||
|---|---|---|
Contextual learning and sharing autonomy to assist mobile robot by trajectory prediction |
Abstract | ||
|---|---|---|
We propose in this report a novel shared autonomy approach to assist mobile robot teleoperation. Our method learns the motion patterns of human operator performing various contextual tasks from demonstrations in an unsupervised manner, then uses the obtained knowledge with the contextual information to infer the trajectory the human operator intends to take to complete the corresponding tasks with the estimation confidence. The predicted trajectory can be executed as the reference model by the state-of-art motion controller to assist the human operator to carry out the intentional tasks actively and appropriately. The real experimental results indicate that our approach is promising. |
Year | DOI | Venue |
|---|---|---|
2016 | 10.1109/SSRR.2016.7784312 | 2016 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR) |
Keywords | Field | DocType |
contextual learning,sharing autonomy,mobile robot,trajectory prediction,estimation confidence,state-of-art motion controller | Teleoperation,Computer vision,Contextual information,Reference model,Computer science,Simulation,Contextual learning,Autonomy,Artificial intelligence,Motion controller,Trajectory,Mobile robot | Conference |
ISSN | ISBN | Citations |
2374-3247 | 978-1-5090-4350-7 | 1 |
PageRank | References | Authors |
0.35 | 0 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ming Gao | 1 | 1 | 0.69 |
| Ralf Kohlhaas | 2 | 14 | 5.22 |
| Johann Marius Zöllner | 3 | 131 | 24.29 |