2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2015
DOI: 10.1109/iros.2015.7353774
|View full text |Cite
|
Sign up to set email alerts
|

Integrating physics-based prediction with Semantic plan Execution Monitoring

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
4
0

Year Published

2016
2016
2020
2020

Publication Types

Select...
4
1
1

Relationship

0
6

Authors

Journals

citations
Cited by 7 publications
(4 citation statements)
references
References 13 publications
0
4
0
Order By: Relevance
“…Naively, this can be achieved by modeling specific thresholds for the manipulation costs. Common physics-based validation methods like the one of Rockel et al [33] determine such thresholds heuristically which signal whether or not some object is currently regarded as toppling. Pastor et al [34], on the other hand, use statistical methods to determine if a particular motion coincides with a predefined spatial envelope.…”
Section: Damage-avoiding Manipulation Sequence Planningmentioning
confidence: 99%
“…Naively, this can be achieved by modeling specific thresholds for the manipulation costs. Common physics-based validation methods like the one of Rockel et al [33] determine such thresholds heuristically which signal whether or not some object is currently regarded as toppling. Pastor et al [34], on the other hand, use statistical methods to determine if a particular motion coincides with a predefined spatial envelope.…”
Section: Damage-avoiding Manipulation Sequence Planningmentioning
confidence: 99%
“…In the robotics community, the idea of using simulators to improve execution is not new. Rockel et al [13] show a system where simulation is integrated into the planner, such that the latter can choose the appropriate action and parameters based on simulation. This allows the robot to learn a new skill such as balancing an object on a tray.…”
Section: Related Workmentioning
confidence: 99%
“…One drawback of using Scene Dynamics Anticipation as a validation method, however, is the fact that it outputs the manipulation costs for the given scene configuration, but classification between positively and negatively validated actions has to be performed manually via a threshold. This is a common problem for Outcome Prediction methods in general, also for Rockel et al's approach [10] where thresholds are defined manually for which an object is considered to be toppling. Another example is [8] where the authors perform statistical tests on whether a planned motion lies within a learned envelope.…”
Section: Manipulation Outcome Predictionmentioning
confidence: 99%
“…In contrast to these works, Rockel et al [10] present an interesting idea of predicting task success on the basis of motion of the manipulated objects. Concretely, their application includes a robot which maximizes its speed moving around in a scene, but without losing the balance of an object which sits on its base.…”
Section: B Manipulation Strategy Planningmentioning
confidence: 99%