2023
DOI: 10.1109/tase.2022.3168542
|View full text |Cite
|
Sign up to set email alerts
|

Motion Planning of Manipulator by Points-Guided Sampling Network

Abstract: Multiple robot systems are favored for object manipulation and transportation, especially for large objects. However, in more complex manipulation such as flipping, these systems encounter a new challenge, configuration disconnectivity of manipulators. Grasping objects by manipulators will impose closedchain constraints on the system, which in turn limits the feasible motions of manipulators and further compromises the configuration connectivity. Multiple mobile manipulator systems show much more flexibility i… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
11
0

Year Published

2024
2024
2024
2024

Publication Types

Select...
3
2

Relationship

0
5

Authors

Journals

citations
Cited by 10 publications
(11 citation statements)
references
References 64 publications
0
11
0
Order By: Relevance
“…Experiment 2 involved utilizing UaMPNet for motion planning in a simple 3D environment for point-mass robots and a more complex environment resembling an office setup for a 7-DoF Franka Emilka Panda robot. We compared the motion planning performance against the state-of-the-art algorithm PG-RRT [22], which utilizes PGSN. Lastly, in Experiment 3, we conducted a study to assess motion planning performance based on different feature extraction methods.…”
Section: Experiments and Resultsmentioning
confidence: 99%
See 4 more Smart Citations
“…Experiment 2 involved utilizing UaMPNet for motion planning in a simple 3D environment for point-mass robots and a more complex environment resembling an office setup for a 7-DoF Franka Emilka Panda robot. We compared the motion planning performance against the state-of-the-art algorithm PG-RRT [22], which utilizes PGSN. Lastly, in Experiment 3, we conducted a study to assess motion planning performance based on different feature extraction methods.…”
Section: Experiments and Resultsmentioning
confidence: 99%
“…MPNet demonstrated promising motion planning performance when combined with bidirectional iterative planning algorithms. PSGN was proposed in [22] to enhance generalization performance in similar environments. PSGN extracted features from 3D point clouds, performed clustering on point clouds with similar features, and modeled a linearly interpolatable latent space using a VAE-based feature extraction net (PointNet [33] encoder and AtlasNet [34] decoder) and multimodal sampling net.…”
Section: Related Workmentioning
confidence: 99%
See 3 more Smart Citations