A representation method based on the probability of collision for safe robot navigation in domestic environments

Research output: Contribution to journalArticleAcademicpeer-review

80 Downloads (Pure)

Abstract

This paper introduces a three-dimensional volumetric representation for safe navigation. It is based on the OctoMap representation framework that probabilistically fuses sensor measurements to represent the occupancy probability of volumes. To achieve safe navigation in a domestic environment this representation is extended with a model of the occupancy probability if no sensor measurements are received, and a proactive approach to deal with unpredictably moving obstacles that can arise from behind occlusions by always expecting obstacles to appear on the robot’s path. By combining the occupancy probability of volumes with the position uncertainty of the robot, a probability of collision is obtained. It is shown that by relating this probability to a safe velocity limit a robot in a real domestic environment can move close to a certain maximum velocity but decides to attain a slower safe velocity limit when it must, analogous to slowing down in traffic when approaching an occluded intersection.
Original languageEnglish
Pages (from-to)601-614
Number of pages14
JournalAutonomous Robots
Volume42
Issue number3
Early online date12 Aug 2017
DOIs
Publication statusPublished - 1 Mar 2018

Fingerprint

Navigation
Robots
Sensors
Electric fuses

Cite this

@article{b25be8928e75457ba11a53be413ce058,
title = "A representation method based on the probability of collision for safe robot navigation in domestic environments",
abstract = "This paper introduces a three-dimensional volumetric representation for safe navigation. It is based on the OctoMap representation framework that probabilistically fuses sensor measurements to represent the occupancy probability of volumes. To achieve safe navigation in a domestic environment this representation is extended with a model of the occupancy probability if no sensor measurements are received, and a proactive approach to deal with unpredictably moving obstacles that can arise from behind occlusions by always expecting obstacles to appear on the robot’s path. By combining the occupancy probability of volumes with the position uncertainty of the robot, a probability of collision is obtained. It is shown that by relating this probability to a safe velocity limit a robot in a real domestic environment can move close to a certain maximum velocity but decides to attain a slower safe velocity limit when it must, analogous to slowing down in traffic when approaching an occluded intersection.",
keywords = "Collision avoidance, Mobile robots, Navigation, Representation",
author = "J. Lunenburg and {van de Molengraft}, R. and M. Steinbuch",
year = "2018",
month = "3",
day = "1",
doi = "10.1007/s10514-017-9653-x",
language = "English",
volume = "42",
pages = "601--614",
journal = "Autonomous Robots",
issn = "0929-5593",
publisher = "Springer",
number = "3",

}

A representation method based on the probability of collision for safe robot navigation in domestic environments. / Lunenburg, J.; van de Molengraft, R.; Steinbuch, M.

In: Autonomous Robots, Vol. 42, No. 3, 01.03.2018, p. 601-614.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - A representation method based on the probability of collision for safe robot navigation in domestic environments

AU - Lunenburg, J.

AU - van de Molengraft, R.

AU - Steinbuch, M.

PY - 2018/3/1

Y1 - 2018/3/1

N2 - This paper introduces a three-dimensional volumetric representation for safe navigation. It is based on the OctoMap representation framework that probabilistically fuses sensor measurements to represent the occupancy probability of volumes. To achieve safe navigation in a domestic environment this representation is extended with a model of the occupancy probability if no sensor measurements are received, and a proactive approach to deal with unpredictably moving obstacles that can arise from behind occlusions by always expecting obstacles to appear on the robot’s path. By combining the occupancy probability of volumes with the position uncertainty of the robot, a probability of collision is obtained. It is shown that by relating this probability to a safe velocity limit a robot in a real domestic environment can move close to a certain maximum velocity but decides to attain a slower safe velocity limit when it must, analogous to slowing down in traffic when approaching an occluded intersection.

AB - This paper introduces a three-dimensional volumetric representation for safe navigation. It is based on the OctoMap representation framework that probabilistically fuses sensor measurements to represent the occupancy probability of volumes. To achieve safe navigation in a domestic environment this representation is extended with a model of the occupancy probability if no sensor measurements are received, and a proactive approach to deal with unpredictably moving obstacles that can arise from behind occlusions by always expecting obstacles to appear on the robot’s path. By combining the occupancy probability of volumes with the position uncertainty of the robot, a probability of collision is obtained. It is shown that by relating this probability to a safe velocity limit a robot in a real domestic environment can move close to a certain maximum velocity but decides to attain a slower safe velocity limit when it must, analogous to slowing down in traffic when approaching an occluded intersection.

KW - Collision avoidance

KW - Mobile robots

KW - Navigation

KW - Representation

U2 - 10.1007/s10514-017-9653-x

DO - 10.1007/s10514-017-9653-x

M3 - Article

VL - 42

SP - 601

EP - 614

JO - Autonomous Robots

JF - Autonomous Robots

SN - 0929-5593

IS - 3

ER -