Active stereo-vision 3D perception system for precise autonomous vehicle hitching

Michael Feller; Jae Sang Hyun; Song Zhang

doi:10.1109/AIM43001.2020.9158790

Active stereo-vision 3D perception system for precise autonomous vehicle hitching

Michael Feller, Jae Sang Hyun, Song Zhang

Department of Mechanical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper presents a low-cost, low-power 3D optical sensor that is fully integrated for feedback control of an autonomous vehicle to a hitch. The hitching problem is an important challenge for vehicles in agricultural and transportation industries, yet few studies have been carried out in literature. We developed a perception system that combines low-accuracy classical stereo vision sensing with higher accuracy active sensing, as well as incorporating adaptive control strategies to tackle the hitching problem. We tested our proposed method on an RC car to approach a model hitch target. Our experiments demonstrated that our system can successfully control the vehicle from within ±35° of perpendicular to the hitch, to a final position with an overall standard deviation of 3.0 mm of lateral error and 1.5° of angular error.

Original language	English
Title of host publication	2020 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	717-722
Number of pages	6
ISBN (Electronic)	9781728167947
DOIs	https://doi.org/10.1109/AIM43001.2020.9158790
Publication status	Published - 2020 Jul
Event	2020 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2020 - Boston, United States Duration: 2020 Jul 6 → 2020 Jul 9

Publication series

Name	IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM
Volume	2020-July

Conference

Conference	2020 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2020
Country/Territory	United States
City	Boston
Period	20/7/6 → 20/7/9

Bibliographical note

Funding Information:
*This work was funded by NSF (grant No.: IIS-1637961) 1 Michael Feller and Jae-Sang Hyun were graduate students with School of Mechanical Engineering, Purdue University, West Lafayette, IN 47907, USA {feller3,hyun7}@purdue.edu 3 Song Zhang is with Faculty of School of Mechanical Engineering, Purdue University, West Lafayette, IN 47907, USA szhang15@purdue.edu

Publisher Copyright:
© 2020 IEEE.

All Science Journal Classification (ASJC) codes

Electrical and Electronic Engineering
Control and Systems Engineering
Computer Science Applications
Software

Access to Document

10.1109/AIM43001.2020.9158790

Cite this

Feller, M., Hyun, J. S., & Zhang, S. (2020). Active stereo-vision 3D perception system for precise autonomous vehicle hitching. In 2020 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2020 (pp. 717-722). Article 9158790 (IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM; Vol. 2020-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AIM43001.2020.9158790

Feller, Michael ; Hyun, Jae Sang ; Zhang, Song. / Active stereo-vision 3D perception system for precise autonomous vehicle hitching. 2020 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2020. Institute of Electrical and Electronics Engineers Inc., 2020. pp. 717-722 (IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM).

@inproceedings{467a2de07e8b4556bc51797909aca2ad,

title = "Active stereo-vision 3D perception system for precise autonomous vehicle hitching",

abstract = "This paper presents a low-cost, low-power 3D optical sensor that is fully integrated for feedback control of an autonomous vehicle to a hitch. The hitching problem is an important challenge for vehicles in agricultural and transportation industries, yet few studies have been carried out in literature. We developed a perception system that combines low-accuracy classical stereo vision sensing with higher accuracy active sensing, as well as incorporating adaptive control strategies to tackle the hitching problem. We tested our proposed method on an RC car to approach a model hitch target. Our experiments demonstrated that our system can successfully control the vehicle from within ±35° of perpendicular to the hitch, to a final position with an overall standard deviation of 3.0 mm of lateral error and 1.5° of angular error.",

author = "Michael Feller and Hyun, {Jae Sang} and Song Zhang",

note = "Funding Information: *This work was funded by NSF (grant No.: IIS-1637961) 1 Michael Feller and Jae-Sang Hyun were graduate students with School of Mechanical Engineering, Purdue University, West Lafayette, IN 47907, USA {feller3,hyun7}@purdue.edu 3 Song Zhang is with Faculty of School of Mechanical Engineering, Purdue University, West Lafayette, IN 47907, USA szhang15@purdue.edu Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2020 ; Conference date: 06-07-2020 Through 09-07-2020",

year = "2020",

month = jul,

doi = "10.1109/AIM43001.2020.9158790",

language = "English",

series = "IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "717--722",

booktitle = "2020 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2020",

address = "United States",

}

Feller, M, Hyun, JS & Zhang, S 2020, Active stereo-vision 3D perception system for precise autonomous vehicle hitching. in 2020 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2020., 9158790, IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM, vol. 2020-July, Institute of Electrical and Electronics Engineers Inc., pp. 717-722, 2020 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2020, Boston, United States, 20/7/6. https://doi.org/10.1109/AIM43001.2020.9158790

Active stereo-vision 3D perception system for precise autonomous vehicle hitching. / Feller, Michael; Hyun, Jae Sang; Zhang, Song.
2020 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2020. Institute of Electrical and Electronics Engineers Inc., 2020. p. 717-722 9158790 (IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM; Vol. 2020-July).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Active stereo-vision 3D perception system for precise autonomous vehicle hitching

AU - Feller, Michael

AU - Hyun, Jae Sang

AU - Zhang, Song

N1 - Funding Information: *This work was funded by NSF (grant No.: IIS-1637961) 1 Michael Feller and Jae-Sang Hyun were graduate students with School of Mechanical Engineering, Purdue University, West Lafayette, IN 47907, USA {feller3,hyun7}@purdue.edu 3 Song Zhang is with Faculty of School of Mechanical Engineering, Purdue University, West Lafayette, IN 47907, USA szhang15@purdue.edu Publisher Copyright: © 2020 IEEE.

PY - 2020/7

Y1 - 2020/7

N2 - This paper presents a low-cost, low-power 3D optical sensor that is fully integrated for feedback control of an autonomous vehicle to a hitch. The hitching problem is an important challenge for vehicles in agricultural and transportation industries, yet few studies have been carried out in literature. We developed a perception system that combines low-accuracy classical stereo vision sensing with higher accuracy active sensing, as well as incorporating adaptive control strategies to tackle the hitching problem. We tested our proposed method on an RC car to approach a model hitch target. Our experiments demonstrated that our system can successfully control the vehicle from within ±35° of perpendicular to the hitch, to a final position with an overall standard deviation of 3.0 mm of lateral error and 1.5° of angular error.

AB - This paper presents a low-cost, low-power 3D optical sensor that is fully integrated for feedback control of an autonomous vehicle to a hitch. The hitching problem is an important challenge for vehicles in agricultural and transportation industries, yet few studies have been carried out in literature. We developed a perception system that combines low-accuracy classical stereo vision sensing with higher accuracy active sensing, as well as incorporating adaptive control strategies to tackle the hitching problem. We tested our proposed method on an RC car to approach a model hitch target. Our experiments demonstrated that our system can successfully control the vehicle from within ±35° of perpendicular to the hitch, to a final position with an overall standard deviation of 3.0 mm of lateral error and 1.5° of angular error.

UR - http://www.scopus.com/inward/record.url?scp=85090393589&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85090393589&partnerID=8YFLogxK

U2 - 10.1109/AIM43001.2020.9158790

DO - 10.1109/AIM43001.2020.9158790

M3 - Conference contribution

AN - SCOPUS:85090393589

T3 - IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM

SP - 717

EP - 722

BT - 2020 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2020

Y2 - 6 July 2020 through 9 July 2020

ER -

Feller M, Hyun JS, Zhang S. Active stereo-vision 3D perception system for precise autonomous vehicle hitching. In 2020 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2020. Institute of Electrical and Electronics Engineers Inc. 2020. p. 717-722. 9158790. (IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM). doi: 10.1109/AIM43001.2020.9158790

Active stereo-vision 3D perception system for precise autonomous vehicle hitching

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this