Local exploration strategies for a mobile robot in a highly dynamic environment

Stanley Tack; Michael Burke; Saurabh Sinha

doi:10.1109/ROBOMECH.2012.6558470

Local exploration strategies for a mobile robot in a highly dynamic environment

Stanley Tack
, Michael Burke
, Saurabh Sinha

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

1 Citation (Scopus)

Abstract

In this paper, three strategies for navigation in highly dynamic environments are developed and their exploration effectiveness compared. These strategies include a collision avoidance strategy, a random wandering strategy and a goal planning strategy. Existing exploration and surveillance techniques make extensive use of metric maps for localisation and navigation which can be of little use in an environment that has many moving obstacles. While the strategies compared here are not specifically designed for exploration, they allow navigation without the need to store and maintain a map. The evenness or positional distribution over time as well as the speed of exploration are taken as measures of exploration efficacy and applicability to surveillance. The comparison of the strategies shows that the goal planning strategy performs far better than the other two, warranting a significant increase in the complexity and thus computational resources required for successful implementation onto physical platforms.

Original language	English
Title of host publication	2012 5th Robotics and Mechatronics Conference of South Africa, ROBMECH 2012
DOIs	https://doi.org/10.1109/ROBOMECH.2012.6558470
Publication status	Published - 2012
Externally published	Yes
Event	2012 5th Robotics and Mechatronics Conference of South Africa, ROBMECH 2012 - Johannesberg, South Africa Duration: 26 Nov 2012 → 27 Nov 2012

Publication series

Name	2012 5th Robotics and Mechatronics Conference of South Africa, ROBMECH 2012

Conference

Conference	2012 5th Robotics and Mechatronics Conference of South Africa, ROBMECH 2012
Country/Territory	South Africa
City	Johannesberg
Period	26/11/12 → 27/11/12

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

ASJC Scopus subject areas

Artificial Intelligence
Electrical and Electronic Engineering
Mechanical Engineering

Access to Document

10.1109/ROBOMECH.2012.6558470

Cite this

@inproceedings{800c9bd38e4e4f3491d6bf73d69f3183,

title = "Local exploration strategies for a mobile robot in a highly dynamic environment",

abstract = "In this paper, three strategies for navigation in highly dynamic environments are developed and their exploration effectiveness compared. These strategies include a collision avoidance strategy, a random wandering strategy and a goal planning strategy. Existing exploration and surveillance techniques make extensive use of metric maps for localisation and navigation which can be of little use in an environment that has many moving obstacles. While the strategies compared here are not specifically designed for exploration, they allow navigation without the need to store and maintain a map. The evenness or positional distribution over time as well as the speed of exploration are taken as measures of exploration efficacy and applicability to surveillance. The comparison of the strategies shows that the goal planning strategy performs far better than the other two, warranting a significant increase in the complexity and thus computational resources required for successful implementation onto physical platforms.",

author = "Stanley Tack and Michael Burke and Saurabh Sinha",

year = "2012",

doi = "10.1109/ROBOMECH.2012.6558470",

language = "English",

isbn = "9781467351836",

series = "2012 5th Robotics and Mechatronics Conference of South Africa, ROBMECH 2012",

booktitle = "2012 5th Robotics and Mechatronics Conference of South Africa, ROBMECH 2012",

note = "2012 5th Robotics and Mechatronics Conference of South Africa, ROBMECH 2012 ; Conference date: 26-11-2012 Through 27-11-2012",

}

Tack, S, Burke, M & Sinha, S 2012, Local exploration strategies for a mobile robot in a highly dynamic environment. in 2012 5th Robotics and Mechatronics Conference of South Africa, ROBMECH 2012., 6558470, 2012 5th Robotics and Mechatronics Conference of South Africa, ROBMECH 2012, 2012 5th Robotics and Mechatronics Conference of South Africa, ROBMECH 2012, Johannesberg, South Africa, 26/11/12. https://doi.org/10.1109/ROBOMECH.2012.6558470

Local exploration strategies for a mobile robot in a highly dynamic environment. / Tack, Stanley; Burke, Michael; Sinha, Saurabh.
2012 5th Robotics and Mechatronics Conference of South Africa, ROBMECH 2012. 2012. 6558470 (2012 5th Robotics and Mechatronics Conference of South Africa, ROBMECH 2012).

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

TY - GEN

T1 - Local exploration strategies for a mobile robot in a highly dynamic environment

AU - Tack, Stanley

AU - Burke, Michael

AU - Sinha, Saurabh

PY - 2012

Y1 - 2012

N2 - In this paper, three strategies for navigation in highly dynamic environments are developed and their exploration effectiveness compared. These strategies include a collision avoidance strategy, a random wandering strategy and a goal planning strategy. Existing exploration and surveillance techniques make extensive use of metric maps for localisation and navigation which can be of little use in an environment that has many moving obstacles. While the strategies compared here are not specifically designed for exploration, they allow navigation without the need to store and maintain a map. The evenness or positional distribution over time as well as the speed of exploration are taken as measures of exploration efficacy and applicability to surveillance. The comparison of the strategies shows that the goal planning strategy performs far better than the other two, warranting a significant increase in the complexity and thus computational resources required for successful implementation onto physical platforms.

AB - In this paper, three strategies for navigation in highly dynamic environments are developed and their exploration effectiveness compared. These strategies include a collision avoidance strategy, a random wandering strategy and a goal planning strategy. Existing exploration and surveillance techniques make extensive use of metric maps for localisation and navigation which can be of little use in an environment that has many moving obstacles. While the strategies compared here are not specifically designed for exploration, they allow navigation without the need to store and maintain a map. The evenness or positional distribution over time as well as the speed of exploration are taken as measures of exploration efficacy and applicability to surveillance. The comparison of the strategies shows that the goal planning strategy performs far better than the other two, warranting a significant increase in the complexity and thus computational resources required for successful implementation onto physical platforms.

UR - https://www.scopus.com/pages/publications/84881653974

U2 - 10.1109/ROBOMECH.2012.6558470

DO - 10.1109/ROBOMECH.2012.6558470

M3 - Conference contribution

AN - SCOPUS:84881653974

SN - 9781467351836

T3 - 2012 5th Robotics and Mechatronics Conference of South Africa, ROBMECH 2012

BT - 2012 5th Robotics and Mechatronics Conference of South Africa, ROBMECH 2012

T2 - 2012 5th Robotics and Mechatronics Conference of South Africa, ROBMECH 2012

Y2 - 26 November 2012 through 27 November 2012

ER -

Local exploration strategies for a mobile robot in a highly dynamic environment

Abstract

Publication series

Conference

UN SDGs

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this