IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004 2004
DOI: 10.1109/robot.2004.1307136
|View full text |Cite
|
Sign up to set email alerts
|

Learning by observation with mobile robots: a computational approach

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
13
0

Year Published

2004
2004
2017
2017

Publication Types

Select...
4
3
1

Relationship

1
7

Authors

Journals

citations
Cited by 22 publications
(13 citation statements)
references
References 6 publications
0
13
0
Order By: Relevance
“…Each linear dynamical system is used to derive a convergent controller, with a small region around the final state considered its goal. The algorithm can be run online and was used in conjunction with several other methods to build a mobile robot system that performed LfD by tracking a human user [Dixon and Khosla, 2004b]. This system differs from CST in three ways.…”
Section: Related Workmentioning
confidence: 99%
“…Each linear dynamical system is used to derive a convergent controller, with a small region around the final state considered its goal. The algorithm can be run online and was used in conjunction with several other methods to build a mobile robot system that performed LfD by tracking a human user [Dixon and Khosla, 2004b]. This system differs from CST in three ways.…”
Section: Related Workmentioning
confidence: 99%
“…The robot is then able to make a decision to execute one of 4 motion primitives(unit actions) based on its sensory readings. In [11] the robot uses a laser sensor to detect and recognize objects of interest. A policy is learned to predict subgoals associated with the detected objects rather than directly predicting the motion primitives.…”
Section: Navigationmentioning
confidence: 99%
“…The LfD literature may be divided into two categories: those which learn plans [22,31] and those which learn (usually stateless) policies [3,19] (for stateful examples see [8,13]). In most cases, the plan literature builds sparse machines describing occasional changes in behavior, whereas many, but not all, policy methods learn fine-grained changes in action, such as might be found in trajectory planning or control.…”
Section: Related Workmentioning
confidence: 99%