2009 IEEE/RSJ International Conference on Intelligent Robots and Systems 2009
DOI: 10.1109/iros.2009.5354602
| View full text |Cite
|
Sign up to set email alerts
|
Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
193
0

Year Published

2013
2013
2020
2020

Publication Types

Select...
5
2
1

Relationship

0
8

Authors

Journals

citations
Cited by 242 publications
(193 citation statements)
references
References 8 publications
0
193
0
Order By: Relevance
“…Future work will integrate function calls that provide in better cost estimates, either by learning [27] or physics simulations [28]. Currently also the knowledge processing framework KnowRob [29] is being integrated, to enable more extensive reasoning capabilities. On a short term we want to replace the pool of PDDL operators and methods by the globally accesible RoboEarth Action Recipe database, allowing to share and reuse actions with other systems through the common OWL-DL action representation.…”
Section: Discussion and Future Workmentioning
confidence: 99%
See 1 more Smart Citation
“…Future work will integrate function calls that provide in better cost estimates, either by learning [27] or physics simulations [28]. Currently also the knowledge processing framework KnowRob [29] is being integrated, to enable more extensive reasoning capabilities. On a short term we want to replace the pool of PDDL operators and methods by the globally accesible RoboEarth Action Recipe database, allowing to share and reuse actions with other systems through the common OWL-DL action representation.…”
Section: Discussion and Future Workmentioning
confidence: 99%
“…As part of the EU funded RoboEarth and RoboHow 1 projects a first implementation is described in [10], where the Semantic Robot Description Language (SRDL) [11] is used to match robot capabilities against the task related components. Although this capability matching enables the filtration of plans that cannot be executed by platforms missing the required capabilities, it does not project the state of the world into the future, therefore not ensuring that a certain robot feature remains available throughout the execution phase of the plan (e.g.…”
Section: Related Workmentioning
confidence: 99%
“…There has been a lot of work in the field of intelligent systems on developing formalisms for learning and representing actions, ranging from task-space representations [1] to high-level symbolic description of actions and their effects on objects [2]. Many approaches work directly on raw video streams, which is a challenging problem due to high variance in the video emanating from e.g.…”
Section: Related Workmentioning
confidence: 99%
“…The knowledge processing framework KnowRob [20] is used as interlingua to exchange knowledge between different components of the RoboEarth system. When the execution engine queries for a recipe, KnowRob searches the RoboEarth database, downloads recipes, checks for missing components (such as environment maps or object models that are required for the task), and triggers their download.…”
Section: Representations For Exchanging Knowledgementioning
confidence: 99%
“…Recipes are stored in description logic in a language built upon the W3C-standardized Web Ontology Language [22] and the KnowRob knowledge base [20]. The language itself is described in [21].…”
Section: Action Recipesmentioning
confidence: 99%