Speed-range dilemmas for vision-based navigation in unstructured terrain

Pierre Sermanet, Raia Hadsell, Jan Ben, Ayse Naz Erkan, Beat Flepp, Urs Muller, Yann LeCun

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

Abstract

The performance of vision-based navigation systems for off-road mobile robots depends crucially on the resolution of the camera, the sophistication of the visual processing, the latency between image and sensor capture to actuator control, and the period of the control loop. One particularly important design question is whether one should increase the resolution of the camera images, and the range of the obstacle detection algorithms, at the expense of latency and control loop period. We first report experimental results on the resolution-period trade-off with a stereo vision-based navigation system implemented on the LAGR mobile robot platform. We propose a multi-agent perception and control architecture that combines a sophisticated long-range path detection method operating at high resolution and low frame rate, with a simple stereo-based obstacle detection method operating at low resolution, high frame rate, and low latency. The system combines the advantages of the long-range module for strategic path planning, with the advantages of the short-range module for tactical driving.

Original languageEnglish (US)
Title of host publication6th IFAC Symposium on Intelligent Autonomous Vehicles, IAV 200707 - Proceedings
Pages300-305
Number of pages6
Volume6
EditionPART 1
StatePublished - 2007
Event6th IFAC Symposium on Intelligent Autonomous Vehicles, IAV2007 - Toulouse, France
Duration: Sep 3 2007Sep 5 2007

Other

Other6th IFAC Symposium on Intelligent Autonomous Vehicles, IAV2007
CountryFrance
CityToulouse
Period9/3/079/5/07

Fingerprint

Navigation
Navigation systems
Mobile robots
Cameras
Stereo vision
Motion planning
Actuators
Sensors
Processing

Keywords

  • Autonomous navigation
  • Control architecture
  • LAGR
  • Robotics
  • Vision

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Sermanet, P., Hadsell, R., Ben, J., Erkan, A. N., Flepp, B., Muller, U., & LeCun, Y. (2007). Speed-range dilemmas for vision-based navigation in unstructured terrain. In 6th IFAC Symposium on Intelligent Autonomous Vehicles, IAV 200707 - Proceedings (PART 1 ed., Vol. 6, pp. 300-305)

Speed-range dilemmas for vision-based navigation in unstructured terrain. / Sermanet, Pierre; Hadsell, Raia; Ben, Jan; Erkan, Ayse Naz; Flepp, Beat; Muller, Urs; LeCun, Yann.

6th IFAC Symposium on Intelligent Autonomous Vehicles, IAV 200707 - Proceedings. Vol. 6 PART 1. ed. 2007. p. 300-305.

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

Sermanet, P, Hadsell, R, Ben, J, Erkan, AN, Flepp, B, Muller, U & LeCun, Y 2007, Speed-range dilemmas for vision-based navigation in unstructured terrain. in 6th IFAC Symposium on Intelligent Autonomous Vehicles, IAV 200707 - Proceedings. PART 1 edn, vol. 6, pp. 300-305, 6th IFAC Symposium on Intelligent Autonomous Vehicles, IAV2007, Toulouse, France, 9/3/07.
Sermanet P, Hadsell R, Ben J, Erkan AN, Flepp B, Muller U et al. Speed-range dilemmas for vision-based navigation in unstructured terrain. In 6th IFAC Symposium on Intelligent Autonomous Vehicles, IAV 200707 - Proceedings. PART 1 ed. Vol. 6. 2007. p. 300-305
Sermanet, Pierre ; Hadsell, Raia ; Ben, Jan ; Erkan, Ayse Naz ; Flepp, Beat ; Muller, Urs ; LeCun, Yann. / Speed-range dilemmas for vision-based navigation in unstructured terrain. 6th IFAC Symposium on Intelligent Autonomous Vehicles, IAV 200707 - Proceedings. Vol. 6 PART 1. ed. 2007. pp. 300-305
@inproceedings{221e05d84a1a40fd85622ebe0aaf59a3,
title = "Speed-range dilemmas for vision-based navigation in unstructured terrain",
abstract = "The performance of vision-based navigation systems for off-road mobile robots depends crucially on the resolution of the camera, the sophistication of the visual processing, the latency between image and sensor capture to actuator control, and the period of the control loop. One particularly important design question is whether one should increase the resolution of the camera images, and the range of the obstacle detection algorithms, at the expense of latency and control loop period. We first report experimental results on the resolution-period trade-off with a stereo vision-based navigation system implemented on the LAGR mobile robot platform. We propose a multi-agent perception and control architecture that combines a sophisticated long-range path detection method operating at high resolution and low frame rate, with a simple stereo-based obstacle detection method operating at low resolution, high frame rate, and low latency. The system combines the advantages of the long-range module for strategic path planning, with the advantages of the short-range module for tactical driving.",
keywords = "Autonomous navigation, Control architecture, LAGR, Robotics, Vision",
author = "Pierre Sermanet and Raia Hadsell and Jan Ben and Erkan, {Ayse Naz} and Beat Flepp and Urs Muller and Yann LeCun",
year = "2007",
language = "English (US)",
isbn = "9783902661654",
volume = "6",
pages = "300--305",
booktitle = "6th IFAC Symposium on Intelligent Autonomous Vehicles, IAV 200707 - Proceedings",
edition = "PART 1",

}

TY - GEN

T1 - Speed-range dilemmas for vision-based navigation in unstructured terrain

AU - Sermanet, Pierre

AU - Hadsell, Raia

AU - Ben, Jan

AU - Erkan, Ayse Naz

AU - Flepp, Beat

AU - Muller, Urs

AU - LeCun, Yann

PY - 2007

Y1 - 2007

N2 - The performance of vision-based navigation systems for off-road mobile robots depends crucially on the resolution of the camera, the sophistication of the visual processing, the latency between image and sensor capture to actuator control, and the period of the control loop. One particularly important design question is whether one should increase the resolution of the camera images, and the range of the obstacle detection algorithms, at the expense of latency and control loop period. We first report experimental results on the resolution-period trade-off with a stereo vision-based navigation system implemented on the LAGR mobile robot platform. We propose a multi-agent perception and control architecture that combines a sophisticated long-range path detection method operating at high resolution and low frame rate, with a simple stereo-based obstacle detection method operating at low resolution, high frame rate, and low latency. The system combines the advantages of the long-range module for strategic path planning, with the advantages of the short-range module for tactical driving.

AB - The performance of vision-based navigation systems for off-road mobile robots depends crucially on the resolution of the camera, the sophistication of the visual processing, the latency between image and sensor capture to actuator control, and the period of the control loop. One particularly important design question is whether one should increase the resolution of the camera images, and the range of the obstacle detection algorithms, at the expense of latency and control loop period. We first report experimental results on the resolution-period trade-off with a stereo vision-based navigation system implemented on the LAGR mobile robot platform. We propose a multi-agent perception and control architecture that combines a sophisticated long-range path detection method operating at high resolution and low frame rate, with a simple stereo-based obstacle detection method operating at low resolution, high frame rate, and low latency. The system combines the advantages of the long-range module for strategic path planning, with the advantages of the short-range module for tactical driving.

KW - Autonomous navigation

KW - Control architecture

KW - LAGR

KW - Robotics

KW - Vision

UR - http://www.scopus.com/inward/record.url?scp=79960965283&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79960965283&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:79960965283

SN - 9783902661654

VL - 6

SP - 300

EP - 305

BT - 6th IFAC Symposium on Intelligent Autonomous Vehicles, IAV 200707 - Proceedings

ER -