2021
DOI: 10.1007/978-3-662-62962-8_28
|View full text |Cite
|
Sign up to set email alerts
|

Using Deep Neural Networks to Separate Entangled Workpieces in Random Bin Picking

Abstract: Entanglements can cause robots to pick multiple parts within random bin picking applications. Previous approaches cope with this problem by shaking the gripped workpiece above the bin. However, these methods increase the cycle time and may decrease the robustness of the application. Therefore we propose a new method to separate entangled workpiece situations by using deep supervised learning. To generate annotated training data for a convolutional neural network we set up a simulation scene. In this scene, bin… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
3
2
1

Relationship

0
6

Authors

Journals

citations
Cited by 9 publications
(1 citation statement)
references
References 9 publications
0
1
0
Order By: Relevance
“…Similarly, Moosmann et al [3] trained a CNN to predict whether an object is free from entanglement during a straight lifting-up motion and avoid grasping entangled objects [3]. The same team further developed supervised [16] and reinforcement learning [4] approaches to manipulating and separating entangled objects given task-agnostic grasp poses. Another recent work proposed a topological solution to compute an entanglement score from a depth image and thus find top-down grasp poses that are free from entanglement [6].…”
Section: Related Workmentioning
confidence: 99%
“…Similarly, Moosmann et al [3] trained a CNN to predict whether an object is free from entanglement during a straight lifting-up motion and avoid grasping entangled objects [3]. The same team further developed supervised [16] and reinforcement learning [4] approaches to manipulating and separating entangled objects given task-agnostic grasp poses. Another recent work proposed a topological solution to compute an entanglement score from a depth image and thus find top-down grasp poses that are free from entanglement [6].…”
Section: Related Workmentioning
confidence: 99%