Automated Planning of Industrial Logistics on a Skill-equipped Robot
(2015) IROS 2015 Workshop on Task Planning for Intelligent Robots in Service and Manufacturing- Abstract
- Automated task planning for robots is usually implemented on a motion primitive domain, where the focus is on constructing meaningful, general motion primitives. In this work we propose planning on the higher abstraction level of robot skills. In this context, skills are general, functional blocks that contain both sensing and action, have a welldefined expected outcome and set of preconditions, and are thus immediately useful for planning. By using a world model, which is focused on the skills, we show that this is in fact the case. We show automated task planning and execution, as a sequence of skills and their parameters, based on the desired goal state and the current state from the world model. Experiments show that the approach is... (More)
- Automated task planning for robots is usually implemented on a motion primitive domain, where the focus is on constructing meaningful, general motion primitives. In this work we propose planning on the higher abstraction level of robot skills. In this context, skills are general, functional blocks that contain both sensing and action, have a welldefined expected outcome and set of preconditions, and are thus immediately useful for planning. By using a world model, which is focused on the skills, we show that this is in fact the case. We show automated task planning and execution, as a sequence of skills and their parameters, based on the desired goal state and the current state from the world model. Experiments show that the approach is immediately applicable, given a skill-equipped robot, and that inconsistencies between the world model and physical world are overcome simply by replanning. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/5b138b35-1e5f-4124-8a8d-e41ea4602751
- author
- Pedersen, Mikkel Rath and Krüger, Volker LU
- publishing date
- 2015
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- Workshop on Task Planning for Intelligent Robots in Service and Manufacturing
- publisher
- IROS Hamburg
- conference name
- IROS 2015 Workshop on Task Planning for Intelligent Robots in Service and Manufacturing
- conference location
- Hamburg, Germany
- conference dates
- 2015-10-02 - 2015-10-02
- language
- English
- LU publication?
- no
- id
- 5b138b35-1e5f-4124-8a8d-e41ea4602751
- date added to LUP
- 2019-05-16 21:25:25
- date last changed
- 2019-05-18 02:18:35
@inproceedings{5b138b35-1e5f-4124-8a8d-e41ea4602751, abstract = {{Automated task planning for robots is usually implemented on a motion primitive domain, where the focus is on constructing meaningful, general motion primitives. In this work we propose planning on the higher abstraction level of robot skills. In this context, skills are general, functional blocks that contain both sensing and action, have a welldefined expected outcome and set of preconditions, and are thus immediately useful for planning. By using a world model, which is focused on the skills, we show that this is in fact the case. We show automated task planning and execution, as a sequence of skills and their parameters, based on the desired goal state and the current state from the world model. Experiments show that the approach is immediately applicable, given a skill-equipped robot, and that inconsistencies between the world model and physical world are overcome simply by replanning.}}, author = {{Pedersen, Mikkel Rath and Krüger, Volker}}, booktitle = {{Workshop on Task Planning for Intelligent Robots in Service and Manufacturing}}, language = {{eng}}, publisher = {{IROS Hamburg}}, title = {{Automated Planning of Industrial Logistics on a Skill-equipped Robot}}, year = {{2015}}, }