Non-parametric workspace modelling for mobile robots using push broom lasers
<p>This thesis is about the intelligent compression of large 3D point cloud datasets. The non-parametric method that we describe simultaneously generates a continuous representation of the workspace surfaces from discrete laser samples and decimates the dataset, retaining only locally salient...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
2011
|
| Subjects: |
| _version_ | 1817933126478856192 |
|---|---|
| author | Smith, M |
| author2 | Newman, P |
| author_facet | Newman, P Smith, M |
| author_sort | Smith, M |
| collection | OXFORD |
| description | <p>This thesis is about the intelligent compression of large 3D point cloud datasets. The non-parametric method that we describe simultaneously generates a continuous representation of the workspace surfaces from discrete laser samples and decimates the dataset, retaining only locally salient samples. Our framework attains decimation factors in excess of two orders of magnitude without significant degradation in fidelity.</p> <p>The work presented here has a specific focus on gathering and processing laser measurements taken from a moving platform in outdoor workspaces. We introduce a somewhat unusual parameterisation of the problem and look to Gaussian Processes as the fundamental machinery in our processing pipeline. Our system compresses laser data in a fashion that is naturally sympathetic to the underlying structure and complexity of the workspace. In geometrically complex areas, compression is lower than that in geometrically bland areas. We focus on this property in detail and it leads us well beyond a simple application of non-parametric techniques. Indeed, towards the end of the thesis we develop a non-stationary GP framework whereby our regression model adapts to the local workspace complexity.</p> <p>Throughout we construct our algorithms so that they may be efficiently implemented. In addition, we present a detailed analysis of the proposed system and investigate model parameters, metric errors and data compression rates. Finally, we note that this work is predicated on a substantial amount of robotics engineering which has allowed us to produce a high quality, peer reviewed, dataset - the first of its kind.</p> |
| first_indexed | 2024-03-06T22:05:56Z |
| format | Thesis |
| id | oxford-uuid:50224eb9-73e8-4c8a-b8c5-18360d11e21b |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-12-09T03:48:51Z |
| publishDate | 2011 |
| record_format | dspace |
| spelling | oxford-uuid:50224eb9-73e8-4c8a-b8c5-18360d11e21b2024-12-08T11:59:54ZNon-parametric workspace modelling for mobile robots using push broom lasersThesishttp://purl.org/coar/resource_type/c_db06uuid:50224eb9-73e8-4c8a-b8c5-18360d11e21bInformation EngineeringRoboticsElectronicsMechanical EngineeringEnglishOxford University Research Archive - Valet2011Smith, MNewman, P<p>This thesis is about the intelligent compression of large 3D point cloud datasets. The non-parametric method that we describe simultaneously generates a continuous representation of the workspace surfaces from discrete laser samples and decimates the dataset, retaining only locally salient samples. Our framework attains decimation factors in excess of two orders of magnitude without significant degradation in fidelity.</p> <p>The work presented here has a specific focus on gathering and processing laser measurements taken from a moving platform in outdoor workspaces. We introduce a somewhat unusual parameterisation of the problem and look to Gaussian Processes as the fundamental machinery in our processing pipeline. Our system compresses laser data in a fashion that is naturally sympathetic to the underlying structure and complexity of the workspace. In geometrically complex areas, compression is lower than that in geometrically bland areas. We focus on this property in detail and it leads us well beyond a simple application of non-parametric techniques. Indeed, towards the end of the thesis we develop a non-stationary GP framework whereby our regression model adapts to the local workspace complexity.</p> <p>Throughout we construct our algorithms so that they may be efficiently implemented. In addition, we present a detailed analysis of the proposed system and investigate model parameters, metric errors and data compression rates. Finally, we note that this work is predicated on a substantial amount of robotics engineering which has allowed us to produce a high quality, peer reviewed, dataset - the first of its kind.</p> |
| spellingShingle | Information Engineering Robotics Electronics Mechanical Engineering Smith, M Non-parametric workspace modelling for mobile robots using push broom lasers |
| title | Non-parametric workspace modelling for mobile robots using push broom lasers |
| title_full | Non-parametric workspace modelling for mobile robots using push broom lasers |
| title_fullStr | Non-parametric workspace modelling for mobile robots using push broom lasers |
| title_full_unstemmed | Non-parametric workspace modelling for mobile robots using push broom lasers |
| title_short | Non-parametric workspace modelling for mobile robots using push broom lasers |
| title_sort | non parametric workspace modelling for mobile robots using push broom lasers |
| topic | Information Engineering Robotics Electronics Mechanical Engineering |
| work_keys_str_mv | AT smithm nonparametricworkspacemodellingformobilerobotsusingpushbroomlasers |