Abstract
This video demonstrates a novel imitation learning approach for learning human-robot interactions from human-human demonstrations. During training, the movements of two human interaction partners are recorded via motion capture. From this, an interaction model is learned that inherently captures important spatial relationships as well as temporal synchrony of body movements between the two interacting partners. The interaction model is based on interaction meshes that were first adopted by the computer graphics community for the offline animation of interacting virtual characters. We developed a variant of interaction meshes that is suitable for real-time human-robot interaction scenarios. During humanrobot collaboration, the learned interaction model allows for adequate spatio-temporal adaptation of the robots behavior to the movements of the human cooperation partner. Thus, the presented approach is well suited for collaborative tasks requiring continuous body movement coordination of a human and a robot. The feasibility of the approach is demonstrated with the example of a cooperative Lego rocket assembly task.
| Original language | English (US) |
|---|---|
| Title of host publication | Humanoids 2016 - IEEE-RAS International Conference on Humanoid Robots |
| Publisher | IEEE Computer Society |
| Pages | 142-143 |
| Number of pages | 2 |
| ISBN (Electronic) | 9781509047185 |
| DOIs | |
| State | Published - Dec 30 2016 |
| Event | 16th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2016 - Cancun, Mexico Duration: Nov 15 2016 → Nov 17 2016 |
Other
| Other | 16th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2016 |
|---|---|
| Country | Mexico |
| City | Cancun |
| Period | 11/15/16 → 11/17/16 |
Fingerprint
ASJC Scopus subject areas
- Artificial Intelligence
- Computer Vision and Pattern Recognition
- Hardware and Architecture
- Human-Computer Interaction
- Electrical and Electronic Engineering
Cite this
Learning human-robot interactions from human-human demonstrations (with applications in Lego rocket assembly). / Vogt, David; Stepputtis, Simon; Weinhold, Richard; Jung, Bernhard; Ben Amor, Hani.
Humanoids 2016 - IEEE-RAS International Conference on Humanoid Robots. IEEE Computer Society, 2016. p. 142-143 7803267.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Learning human-robot interactions from human-human demonstrations (with applications in Lego rocket assembly)
AU - Vogt, David
AU - Stepputtis, Simon
AU - Weinhold, Richard
AU - Jung, Bernhard
AU - Ben Amor, Hani
PY - 2016/12/30
Y1 - 2016/12/30
N2 - This video demonstrates a novel imitation learning approach for learning human-robot interactions from human-human demonstrations. During training, the movements of two human interaction partners are recorded via motion capture. From this, an interaction model is learned that inherently captures important spatial relationships as well as temporal synchrony of body movements between the two interacting partners. The interaction model is based on interaction meshes that were first adopted by the computer graphics community for the offline animation of interacting virtual characters. We developed a variant of interaction meshes that is suitable for real-time human-robot interaction scenarios. During humanrobot collaboration, the learned interaction model allows for adequate spatio-temporal adaptation of the robots behavior to the movements of the human cooperation partner. Thus, the presented approach is well suited for collaborative tasks requiring continuous body movement coordination of a human and a robot. The feasibility of the approach is demonstrated with the example of a cooperative Lego rocket assembly task.
AB - This video demonstrates a novel imitation learning approach for learning human-robot interactions from human-human demonstrations. During training, the movements of two human interaction partners are recorded via motion capture. From this, an interaction model is learned that inherently captures important spatial relationships as well as temporal synchrony of body movements between the two interacting partners. The interaction model is based on interaction meshes that were first adopted by the computer graphics community for the offline animation of interacting virtual characters. We developed a variant of interaction meshes that is suitable for real-time human-robot interaction scenarios. During humanrobot collaboration, the learned interaction model allows for adequate spatio-temporal adaptation of the robots behavior to the movements of the human cooperation partner. Thus, the presented approach is well suited for collaborative tasks requiring continuous body movement coordination of a human and a robot. The feasibility of the approach is demonstrated with the example of a cooperative Lego rocket assembly task.
UR - http://www.scopus.com/inward/record.url?scp=85010208247&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85010208247&partnerID=8YFLogxK
U2 - 10.1109/HUMANOIDS.2016.7803267
DO - 10.1109/HUMANOIDS.2016.7803267
M3 - Conference contribution
AN - SCOPUS:85010208247
SP - 142
EP - 143
BT - Humanoids 2016 - IEEE-RAS International Conference on Humanoid Robots
PB - IEEE Computer Society
ER -