2019 International Conference on Robotics and Automation (ICRA) 2019
DOI: 10.1109/icra.2019.8793898
|View full text |Cite
|
Sign up to set email alerts
|

MoveIt! Task Constructor for Task-Level Motion Planning

Abstract: A lot of motion planning research in robotics focuses on efficient means to find trajectories between individual start and goal regions, but it remains challenging to specify and plan robotic manipulation actions which consist of multiple interdependent subtasks. The Task Constructor framework we present in this work provides a flexible and transparent way to define and plan such actions, enhancing the capabilities of the popular robotic manipulation framework MoveIt!. 1 Subproblems are solved in isolation in … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
36
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
4
3
2

Relationship

0
9

Authors

Journals

citations
Cited by 76 publications
(36 citation statements)
references
References 17 publications
0
36
0
Order By: Relevance
“…The robot's movements for taking actions are implemented by the MoveIt! ROS library (Görner et al, 2019), that is purposely designed for robot action planning and for modeling manipulation actions.…”
Section: Design and Implementationmentioning
confidence: 99%
“…The robot's movements for taking actions are implemented by the MoveIt! ROS library (Görner et al, 2019), that is purposely designed for robot action planning and for modeling manipulation actions.…”
Section: Design and Implementationmentioning
confidence: 99%
“…Throughout this work, we also use BTs for primitive manipulation tasks after motion planning for simplicity. However, in Section 8, we also suggest using MoveIt task constructor (MTC) [18] for connecting sementicless waypoints in those manipulation primitive tasks, to not only achieve smooth multi-waypoint arm trajectory, but also to give us more information about the black-box probabilistic motion planning process, which provides potential for low-level explanations in the future.…”
Section: Related Work 21 Robot Task Representation: Why Behavior Trees For Robot Explanationsmentioning
confidence: 99%
“…Then, we can find its parent to explain what is being attempted (lines [15][16][17]. Similar to the Fallback node, the failed node is then found to explain what went wrong (lines [18][19][20][21][22]. Lines 25-33 consider the case where a Fallback node has an ancestor Retry node.…”
Section: Supporting Failure Explanation Generationmentioning
confidence: 99%
“…An open-source and research-oriented counter-part to this system, is represented by the MoveIt! Task Constructor used for hierarchical organization of basic stages concerning motion and grasp planning [10]. Moreover, the product of ArtiMinds, a commercial software-suite for robot programming, offers a tool for the manipulability calculation while a part is placed in a robot workcell [11], [12].…”
Section: Related Workmentioning
confidence: 99%