Sökning: id:"swepub:oai:DiVA.org:umu-9300" >
Behavior recognitio...
Behavior recognition for segmentation of demonstrated tasks
-
- Billing, Erik, 1981- (författare)
- Umeå universitet,Institutionen för datavetenskap,Umeå universitet, Institutionen för datavetenskap
-
- Hellström, Thomas, 1956- (författare)
- Umeå universitet,Institutionen för datavetenskap,Umeå universitet, Institutionen för datavetenskap
-
(creator_code:org_t)
- 2008
- 2008
- Engelska.
-
Ingår i: IEEE SMC International Conference on Distributed Human-Machine Systems (DHMS). - 9788001040270
- Relaterad länk:
-
https://www8.cs.umu....
-
visa fler...
-
https://urn.kb.se/re...
-
https://urn.kb.se/re...
-
visa färre...
Abstract
Ämnesord
Stäng
- One common approach to the robot learning technique Learning From Demonstration, is to use a set of pre-programmed skills as building blocks for more complex tasks. One important part of this approach is recognition of these skills in a demonstration comprising a stream of sensor and actuator data. In this paper, three novel techniques for behavior recognition are presented and compared. The first technique is function-oriented and compares actions for similar inputs. The second technique is based on auto-associative neural networks and compares reconstruction errors in sensory-motor space. The third technique is based on S-Learning and compares sequences of patterns in sensory-motor space. All three techniques compute an activity level which can be seen as an alternative to a pure classification approach. Performed tests show how the former approach allows a more informative interpretation of a demonstration, by not determining "correct" behaviors but rather a number of alternative interpretations.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- Learning from demonstration
- Segmentation
- Generalization
- Sequence Learning
- Auto-associative neural networks
- S-Learning
- Computer science
- Datavetenskap
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)
Hitta via bibliotek
Till lärosätets databas