Robot Task-Constrained Optimization and Adaptation with Probabilistic Movement Primitives

Guanwen Ding, Xizhe Zang, Xuehe Zhang, Changle Li, Yanhe Zhu, Jie Zhao · 2024

Read Robot Task-Constrained Optimization and Adaptation with Probabilistic Movement Primitives by Guanwen Ding, Xizhe Zang, Xuehe Zhang, Changle Li, Yanhe Zhu, Jie Zhao (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11673859.txt.

Description

Guanwen Ding, Xizhe Zang, Xuehe Zhang, Changle Li, Yanhe Zhu, and Jie Zhao teach robots to copy human moves and adjust to new tasks. Their 2024 paper uses a method that stores each move as a spread of likely paths. Only one sample move is needed for each of three move modes.

The team improved how the robot bends a stored path through set points on the way. They also built a math step that folds in limits such as joint range, walls, and blocks in the path. Tests with a seven-joint robot arm showed smooth moves around one block and then around many blocks. The method aims to speed robot use in factories.

Catalog record

CREATORGuanwen Ding, Xizhe Zang, Xuehe Zhang, Changle Li, Yanhe Zhu, Jie Zhao
YEAR2024
COLLECTIONPAPERS
FORMATTXT
FILE SIZE64 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11673859

Browse the full library · About the Tower of Babel