Interactive and On-Line Learning System for Assembly Task Motion Planning

2013 ◽  
Author(s):  
Yu Yan ◽  
Emilie Poirson ◽  
Fouad Bennis
Keyword(s):  
Motion Planning ◽  
Medial Axis ◽  
Learning System ◽  
Planning System ◽  
Motion Path ◽  
Interaction Layer ◽  
Convex Object ◽  
Narrow Passage ◽  
On Line ◽  
Global Planning

This paper presents a novel interactive motion planning system for assembly/disassembly operations. Our system consists of three layers: interaction layer, learning layer and motion library layer. In interaction layer, user’s manipulation in difficult scenario is liberated by relaxing collision constraints. The resulting path is retracted and connected by random retraction method and BiRRT algorithm. A motion path which successfully passed through the narrow passage or information of geometrical interference in failed case is returned to user. In learning layer, motion primitives corresponding to prior similar scenario are selected by scenario comparison which is based on medial axis, and then transformed to generate new motions. Significant improvement for motion planning of non-convex object in challenging scenarios with narrow passages is obtained by interactive process. The introduction of learning mechanism can reduce global planning time and obtain experiential knowledge.

REMOTE FORM OF EDUCATION, AS ONE OF THE METHODS OF IMPROVING MOTIVATION BY STUDENTS OF DISTANCE LEARNING

2019 ◽  
pp. 73-79
Author(s):  
I. G. Kupnovytska ◽  
V. I. Klymenko ◽  
I. P. Fitkovska ◽  
S. M. Kalugina ◽  
R. I. Belehay ◽  
...  
Keyword(s):  
Distance Learning ◽  
Faculty Members ◽  
Learning System ◽  
Teaching Materials ◽  
Internal Organs ◽  
Technology System ◽  
Course Work ◽  
E Learning ◽  
On Line ◽  
Video And Audio

The development of a modern e-learning system promotes the active introduction of distance education. The organization of a mixed form of education at the department of Clinical Pharmacology and Pharmacotherapy involves an education during the session and using the distance contact between faculty and students during the intersessional period. The information technology system of distance learning is provided by personal computers, video and audio equipment. The web-site of the department presents a set of teaching materials, including curriculas, work programs, lecture notes, test assignments, situational tasks, control and individual course work. Distance learning is supplemented with new teaching materials: web lectures, e-learning textbooks and manuals. Lectures are delivered by faculty members in the form of video conferences or webinars. Consultations are conducted in the on-line mode each week at a certain time by the teachers of the department according to the schedule. The website of the department presents methods for implementing practical skills, video stories of individual urgent states on the pathology of internal organs, demonstrates sets of medicines for seven types of first aid kits to improve the students' knowledge and skills, and to successfully pass the practical part of the state certification of graduates from the discipline "Clinical pharmacy".

ADD-RRV for motion planning in complex environments

Robotica ◽  
2021 ◽  
pp. 1-18
Author(s):  
Peng Cai ◽  
Xiaokui Yue ◽  
Hongwen Zhang
Keyword(s):  
Principal Component Analysis ◽  
Motion Planning ◽  
Configuration Space ◽  
Principal Component ◽  
Component Analysis ◽  
Planning Method ◽  
Complex Environments ◽  
Local Configuration ◽  
Narrow Passage

Abstract In this paper, we present a novel sampling-based motion planning method in various complex environments, especially with narrow passages. We use online the results of the planner in the ADD-RRT framework to identify the types of the local configuration space based on the principal component analysis (PCA). The identification result is then used to accelerate the expansion similar to RRV around obstacles and through narrow passages. We also propose a modified bridge test to identify the entrance of a narrow passage and boost samples inside it. We have compared our method with known motion planners in several scenarios through simulations. Our method shows the best performance across all the tested planners in the tested scenarios.

Sign in / Sign up

Export Citation Format

Share Document