ResearchSpace

Visual servo control for a human-following robot

Show simple item record

dc.contributor.author Burke, Michael G
dc.date.accessioned 2011-05-11T06:48:27Z
dc.date.available 2011-05-11T06:48:27Z
dc.date.issued 2011-03
dc.identifier.citation Burke, M.G. 2011. Visual servo control for a human-following robot. Stellenbosch University en_US
dc.identifier.uri http://hdl.handle.net/10204/4997
dc.description Copyright: 2011 Stellenbosch University. Thesis presented in partial fulfilment of the requirements for the degree Master of Science in Engineering at Stellenbosch University en_US
dc.description.abstract This thesis presents work completed on the design of control and vision components for use in a monocular vision-based human-following robot. The use of vision in a controller feedback loop is referred to as vision-based or visual servo control. Typically, visual servo techniques can be categorised into image-based visual servoing and position-based visual servoing. This thesis discusses each of these approaches, and argues that a position-based visual servo control approach is more suited to human following. A position-based visual servo strategy consists of three distinct phases: target recognition, target pose estimation and controller calculations. The thesis discusses approaches to each of these phases in detail, and presents a complete, functioning system combining these approaches for the purposes of human following. Traditional approaches to human following typically involve a controller that causes platforms to navigate directly towards targets, but this work argues that better following performance can be obtained through the use of a controller that incorporates target orientation information. Although a purely direction-based controller, aiming to minimise both orientation and translation errors, suffers from various limitations, this thesis shows that a hybrid, gain-scheduling combination of two traditional controllers offers better target following performance than its components. In the case of human following the inclusion of target orientation information requires that a definition and means of estimating a human's orientation be available. This work presents a human orientation measure and experimental results to show that it is suitable for the purposes of wheeled platform control. Results of human following using the proposed hybrid, gain-scheduling controller incorporating this measure are presented to confirm this. en_US
dc.language.iso en en_US
dc.publisher Stellenbosch University en_US
dc.relation.ispartofseries Workflow request;6035
dc.subject Human following robot en_US
dc.subject Mobile robot en_US
dc.subject Autonomous navigation en_US
dc.subject Homography en_US
dc.subject Monocular vision en_US
dc.subject Stellenbosch University en_US
dc.title Visual servo control for a human-following robot en_US
dc.type Report en_US
dc.identifier.apacitation Burke, M. G. (2011). <i>Visual servo control for a human-following robot</i> (Workflow request;6035). Stellenbosch University. Retrieved from http://hdl.handle.net/10204/4997 en_ZA
dc.identifier.chicagocitation Burke, Michael G <i>Visual servo control for a human-following robot.</i> Workflow request;6035. Stellenbosch University, 2011. http://hdl.handle.net/10204/4997 en_ZA
dc.identifier.vancouvercitation Burke MG. Visual servo control for a human-following robot. 2011 [cited yyyy month dd]. Available from: http://hdl.handle.net/10204/4997 en_ZA
dc.identifier.ris TY - Report AU - Burke, Michael G AB - This thesis presents work completed on the design of control and vision components for use in a monocular vision-based human-following robot. The use of vision in a controller feedback loop is referred to as vision-based or visual servo control. Typically, visual servo techniques can be categorised into image-based visual servoing and position-based visual servoing. This thesis discusses each of these approaches, and argues that a position-based visual servo control approach is more suited to human following. A position-based visual servo strategy consists of three distinct phases: target recognition, target pose estimation and controller calculations. The thesis discusses approaches to each of these phases in detail, and presents a complete, functioning system combining these approaches for the purposes of human following. Traditional approaches to human following typically involve a controller that causes platforms to navigate directly towards targets, but this work argues that better following performance can be obtained through the use of a controller that incorporates target orientation information. Although a purely direction-based controller, aiming to minimise both orientation and translation errors, suffers from various limitations, this thesis shows that a hybrid, gain-scheduling combination of two traditional controllers offers better target following performance than its components. In the case of human following the inclusion of target orientation information requires that a definition and means of estimating a human's orientation be available. This work presents a human orientation measure and experimental results to show that it is suitable for the purposes of wheeled platform control. Results of human following using the proposed hybrid, gain-scheduling controller incorporating this measure are presented to confirm this. DA - 2011-03 DB - ResearchSpace DP - CSIR KW - Human following robot KW - Mobile robot KW - Autonomous navigation KW - Homography KW - Monocular vision KW - Stellenbosch University LK - https://researchspace.csir.co.za PY - 2011 T1 - Visual servo control for a human-following robot TI - Visual servo control for a human-following robot UR - http://hdl.handle.net/10204/4997 ER - en_ZA


Files in this item

This item appears in the following Collection(s)

Show simple item record