2020 IEEE International Conference on Robotics and Automation (ICRA) 2020
DOI: 10.1109/icra40945.2020.9197545
|View full text |Cite
|
Sign up to set email alerts
|

Informing Multi-Modal Planning with Synergistic Discrete Leads

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
11
0

Year Published

2021
2021
2023
2023

Publication Types

Select...
5
2

Relationship

1
6

Authors

Journals

citations
Cited by 21 publications
(11 citation statements)
references
References 36 publications
0
11
0
Order By: Relevance
“…Additionally, manipulation parameters such as grasping locations are manually selected, resulting in a finite set of manipulation behaviors. This framework has the potential to be generalizable, by automating perception and state inference, learning related object importance for task decomposition [28] to automatically prune causal graph, learning compositional models for symbolic planning [29], and using optimization or sampling techniques to select manipulation parameters [30], [31], such as final object locations.…”
Section: Discussionmentioning
confidence: 99%
“…Additionally, manipulation parameters such as grasping locations are manually selected, resulting in a finite set of manipulation behaviors. This framework has the potential to be generalizable, by automating perception and state inference, learning related object importance for task decomposition [28] to automatically prune causal graph, learning compositional models for symbolic planning [29], and using optimization or sampling techniques to select manipulation parameters [30], [31], such as final object locations.…”
Section: Discussionmentioning
confidence: 99%
“…Essentially, our work is solving a multi-modal planning problem (Hauser and Latombe, 2010; Kingston et al , 2020) that plans across of series of subspaces (identified by contact states). We identify a subspace using evenly sampled contact positions on a table surface.…”
Section: Discussionmentioning
confidence: 99%
“…Though, sampling-based methods without informed exploration are vastly inefficient and suffer from time-complexities associated with over-exploration. Recent work has attempted to address this issue by using informed "leads" to guide exploration [28]. In our work, we build off these observations and constrain our planner's search according to physical properties of the SO(3) rotation group.…”
Section: Related Work 1) Modeling Manipulationmentioning
confidence: 99%