2018
DOI: 10.1007/s10514-018-9799-1
|View full text |Cite
|
Sign up to set email alerts
|

Dynamic grasp and trajectory planning for moving objects

Abstract: This paper shows how a robot arm can follow and grasp moving objects tracked by a vision system, as is needed when a human hands over an object to the robot during collaborative working. While the object is being arbitrarily moved by the human co-worker, a set of likely grasps, generated by a learned grasp planner, are evaluated online to generate a feasible grasp with respect to both: the current configuration of the robot respecting the target grasp; and the constraints of finding a collision-free trajectory… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
41
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
5
4

Relationship

1
8

Authors

Journals

citations
Cited by 78 publications
(41 citation statements)
references
References 29 publications
0
41
0
Order By: Relevance
“…Overall, we define the following conditions as trial failures: F1) If the gripper fingers or any used equipment knocks-off the object from its place while reaching-to-grasp; F2) If the object slips or rolls away while executing the grasp or while lifting the grasped object; F3) If the designed rotational test is failed; F4) If the designed shaking test is failed; F5) If no feasible hypotheses are found, e.g. due to robot kinematics or object placement (which only applies to planners with integrated reachability search, [3], [26]); F6) If the hardware failed to respond due communication drops, process timeouts, etc. For each object the results can be summarized using the format specified in Tables I and II for experiments using single and a group of objects, respectively.…”
Section: B Grasp Execution and Scoringmentioning
confidence: 99%
“…Overall, we define the following conditions as trial failures: F1) If the gripper fingers or any used equipment knocks-off the object from its place while reaching-to-grasp; F2) If the object slips or rolls away while executing the grasp or while lifting the grasped object; F3) If the designed rotational test is failed; F4) If the designed shaking test is failed; F5) If no feasible hypotheses are found, e.g. due to robot kinematics or object placement (which only applies to planners with integrated reachability search, [3], [26]); F6) If the hardware failed to respond due communication drops, process timeouts, etc. For each object the results can be summarized using the format specified in Tables I and II for experiments using single and a group of objects, respectively.…”
Section: B Grasp Execution and Scoringmentioning
confidence: 99%
“…Similarly, Kim [ 41 ] developed an Opti-Track system to track the target ball, load by objects, and quickly predict the trajectory of the target and capture it, where the trajectory of the target was learned and trained by machine-learning algorithms. Furthermore, in [ 42 ], the authors proposed a method of dynamic switching between local and global planners to track and grasp moving objects. The local planner maintained the end-effector with a steady grasping posture to smoothly follow the object motion.…”
Section: Related Workmentioning
confidence: 99%
“…The other is to combine machine learning or deep learning to achieve a more intelligent grasp and better completion. Accordingly, a combination of identification and tracking [6,7] is highly required. As we all know, people are able to recognize the type and location of objects at first glance.…”
Section: Introductionmentioning
confidence: 99%
“…In addition to object recognition, tracking is also indispensable for the robotic arm to make a precise grasp [6]. In order to provide the robotic arm with the position of the next moment, the current measurement, the observation measurement, and the system model in the dynamic system should be known [19].…”
Section: Introductionmentioning
confidence: 99%