Interactive Robot Trajectory Planning With Augmented Reality for Non-expert Users
- Authors
- Lee, Joosun; Lim, Taeyhang; Kim, Wansoo
- Issue Date
- May-2024
- Publisher
- 제어·로봇·시스템학회
- Keywords
- Augmented reality; collision avoidance; human-robot interaction; trajectory planning
- Citation
- International Journal of Control, Automation, and Systems, pp 1 - 10
- Pages
- 10
- Indexed
- SCIE
SCOPUS
KCI
- Journal Title
- International Journal of Control, Automation, and Systems
- Start Page
- 1
- End Page
- 10
- URI
- https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/119265
- DOI
- 10.1007/s12555-023-0796-6
- ISSN
- 1598-6446
2005-4092
- Abstract
- This paper presents a novel method for path selection by non-expert users in robot trajectory planning using augmented reality (AR). While AR has been used in robot control tasks, current approaches often require manual waypoint specification, limiting their effectiveness for non-expert users. In contrast, our study introduces an innovative AR-based method via a head-mounted display, designed to enhance human-robot interaction by making the process of selecting robotic paths more accessible to users without specialized expertise. The proposed method utilizes the RRT-Connect algorithm to automatically generate pathways from the initial to the goal position, offering choices of 1, 3, or 5 pathways, as well as 3 and 5 pathways with AR text guidance. This guidance provides contextual instructions within the AR environment, displaying the order of pathways from the fewest to the highest number of waypoints. Our findings demonstrate that optimizing the number of AR pathways can reduce user stress and improve operational skills. Path1 exhibited the fastest performance time but had the highest number of obstacle collisions. Methods with AR text guidance showed increased performance time compared to Path1. However, Path3 and Path5 achieved the best balance between performance time and collision avoidance. Qualitative analysis indicated that AR text displays demanded more effort from users. Path3 without AR text guidance was identified as the easiest method for operating the robot. Consequently, Path3 was deemed the most beneficial among the five methods. These results highlight the novelty of our method in enhancing the design of future human-robot interaction systems, focusing on improving efficiency, safety, and user experience for non-expert users using AR interfaces.
- Files in This Item
-
Go to Link
- Appears in
Collections - COLLEGE OF ENGINEERING SCIENCES > DEPARTMENT OF ROBOT ENGINEERING > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.