Real-Time robot tracking and following with neuromorphic vision sensor

Abhishek Mishra, Rohan Ghosh, Ashish Goyal, Nitish V Thakor, Sunil L. Kukreja

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we consider the problem of robotic motion tracking and following with neuromorphic vision sensors. We formulate the problem in a leader-follower paradigm. The objective of the follower robot is to perform real-Time motion segmentation of a scene and follow the leader robot. Motion segmentation using a neuromorphic vision sensor mounted on a mobile robot is a challenging task due to events created by movements of the platform (self-movement). Current approaches for tracking do not perform well during sensor ego-motion or need a priori knowledge about the object being tracked. To address these limitations, we designed an algorithm based on clustering space-Time events induced by a neuromorphic sensor followed by a classification procedure. This technique is based on a distance transformation of existing sets. After clustering, a binary class label is assigned to each: (1) background or (2) moving object. The classifier uses event rates of clusters to determine proper class labels. The proposed technique forms an important module for the creation of collectively intelligent multi-pedal robots that utilize neuromorphic vision sensors. The utility and robustness of our algorithm is demonstrated as a real-Time online system implemented on two hexapod robots.

Original languageEnglish (US)
Title of host publication2016 6th IEEE International Conference on Biomedical Robotics and Biomechatronics, BioRob 2016
PublisherIEEE Computer Society
Pages13-18
Number of pages6
Volume2016-July
ISBN (Electronic)9781509032877
DOIs
StatePublished - Jul 26 2016
Externally publishedYes
Event6th IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics, BioRob 2016 - Singapore, Singapore
Duration: Jun 26 2016Jun 29 2016

Other

Other6th IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics, BioRob 2016
CountrySingapore
CitySingapore
Period6/26/166/29/16

Fingerprint

Robots
Sensors
Labels
Online systems
Real time systems
Mobile robots
Robotics
Classifiers

ASJC Scopus subject areas

  • Artificial Intelligence
  • Biomedical Engineering
  • Mechanical Engineering

Cite this

Mishra, A., Ghosh, R., Goyal, A., Thakor, N. V., & Kukreja, S. L. (2016). Real-Time robot tracking and following with neuromorphic vision sensor. In 2016 6th IEEE International Conference on Biomedical Robotics and Biomechatronics, BioRob 2016 (Vol. 2016-July, pp. 13-18). [7523451] IEEE Computer Society. https://doi.org/10.1109/BIOROB.2016.7523451

Real-Time robot tracking and following with neuromorphic vision sensor. / Mishra, Abhishek; Ghosh, Rohan; Goyal, Ashish; Thakor, Nitish V; Kukreja, Sunil L.

2016 6th IEEE International Conference on Biomedical Robotics and Biomechatronics, BioRob 2016. Vol. 2016-July IEEE Computer Society, 2016. p. 13-18 7523451.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Mishra, A, Ghosh, R, Goyal, A, Thakor, NV & Kukreja, SL 2016, Real-Time robot tracking and following with neuromorphic vision sensor. in 2016 6th IEEE International Conference on Biomedical Robotics and Biomechatronics, BioRob 2016. vol. 2016-July, 7523451, IEEE Computer Society, pp. 13-18, 6th IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics, BioRob 2016, Singapore, Singapore, 6/26/16. https://doi.org/10.1109/BIOROB.2016.7523451
Mishra A, Ghosh R, Goyal A, Thakor NV, Kukreja SL. Real-Time robot tracking and following with neuromorphic vision sensor. In 2016 6th IEEE International Conference on Biomedical Robotics and Biomechatronics, BioRob 2016. Vol. 2016-July. IEEE Computer Society. 2016. p. 13-18. 7523451 https://doi.org/10.1109/BIOROB.2016.7523451
Mishra, Abhishek ; Ghosh, Rohan ; Goyal, Ashish ; Thakor, Nitish V ; Kukreja, Sunil L. / Real-Time robot tracking and following with neuromorphic vision sensor. 2016 6th IEEE International Conference on Biomedical Robotics and Biomechatronics, BioRob 2016. Vol. 2016-July IEEE Computer Society, 2016. pp. 13-18
@inproceedings{fd89abc7975544b6949484964ecc67bf,
title = "Real-Time robot tracking and following with neuromorphic vision sensor",
abstract = "In this paper, we consider the problem of robotic motion tracking and following with neuromorphic vision sensors. We formulate the problem in a leader-follower paradigm. The objective of the follower robot is to perform real-Time motion segmentation of a scene and follow the leader robot. Motion segmentation using a neuromorphic vision sensor mounted on a mobile robot is a challenging task due to events created by movements of the platform (self-movement). Current approaches for tracking do not perform well during sensor ego-motion or need a priori knowledge about the object being tracked. To address these limitations, we designed an algorithm based on clustering space-Time events induced by a neuromorphic sensor followed by a classification procedure. This technique is based on a distance transformation of existing sets. After clustering, a binary class label is assigned to each: (1) background or (2) moving object. The classifier uses event rates of clusters to determine proper class labels. The proposed technique forms an important module for the creation of collectively intelligent multi-pedal robots that utilize neuromorphic vision sensors. The utility and robustness of our algorithm is demonstrated as a real-Time online system implemented on two hexapod robots.",
author = "Abhishek Mishra and Rohan Ghosh and Ashish Goyal and Thakor, {Nitish V} and Kukreja, {Sunil L.}",
year = "2016",
month = "7",
day = "26",
doi = "10.1109/BIOROB.2016.7523451",
language = "English (US)",
volume = "2016-July",
pages = "13--18",
booktitle = "2016 6th IEEE International Conference on Biomedical Robotics and Biomechatronics, BioRob 2016",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Real-Time robot tracking and following with neuromorphic vision sensor

AU - Mishra, Abhishek

AU - Ghosh, Rohan

AU - Goyal, Ashish

AU - Thakor, Nitish V

AU - Kukreja, Sunil L.

PY - 2016/7/26

Y1 - 2016/7/26

N2 - In this paper, we consider the problem of robotic motion tracking and following with neuromorphic vision sensors. We formulate the problem in a leader-follower paradigm. The objective of the follower robot is to perform real-Time motion segmentation of a scene and follow the leader robot. Motion segmentation using a neuromorphic vision sensor mounted on a mobile robot is a challenging task due to events created by movements of the platform (self-movement). Current approaches for tracking do not perform well during sensor ego-motion or need a priori knowledge about the object being tracked. To address these limitations, we designed an algorithm based on clustering space-Time events induced by a neuromorphic sensor followed by a classification procedure. This technique is based on a distance transformation of existing sets. After clustering, a binary class label is assigned to each: (1) background or (2) moving object. The classifier uses event rates of clusters to determine proper class labels. The proposed technique forms an important module for the creation of collectively intelligent multi-pedal robots that utilize neuromorphic vision sensors. The utility and robustness of our algorithm is demonstrated as a real-Time online system implemented on two hexapod robots.

AB - In this paper, we consider the problem of robotic motion tracking and following with neuromorphic vision sensors. We formulate the problem in a leader-follower paradigm. The objective of the follower robot is to perform real-Time motion segmentation of a scene and follow the leader robot. Motion segmentation using a neuromorphic vision sensor mounted on a mobile robot is a challenging task due to events created by movements of the platform (self-movement). Current approaches for tracking do not perform well during sensor ego-motion or need a priori knowledge about the object being tracked. To address these limitations, we designed an algorithm based on clustering space-Time events induced by a neuromorphic sensor followed by a classification procedure. This technique is based on a distance transformation of existing sets. After clustering, a binary class label is assigned to each: (1) background or (2) moving object. The classifier uses event rates of clusters to determine proper class labels. The proposed technique forms an important module for the creation of collectively intelligent multi-pedal robots that utilize neuromorphic vision sensors. The utility and robustness of our algorithm is demonstrated as a real-Time online system implemented on two hexapod robots.

UR - http://www.scopus.com/inward/record.url?scp=84983401244&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84983401244&partnerID=8YFLogxK

U2 - 10.1109/BIOROB.2016.7523451

DO - 10.1109/BIOROB.2016.7523451

M3 - Conference contribution

AN - SCOPUS:84983401244

VL - 2016-July

SP - 13

EP - 18

BT - 2016 6th IEEE International Conference on Biomedical Robotics and Biomechatronics, BioRob 2016

PB - IEEE Computer Society

ER -