Probabilistic localization and mapping in appearance space
This thesis is concerned with the problem of place recognition for mobile robots. How can a robot determine its location from an image or sequence of images, without any prior knowledge of its position, even in a world where many places look identical? We outline a new probabilistic approach to the...
| Hoofdauteur: | |
|---|---|
| Andere auteurs: | |
| Formaat: | Thesis |
| Taal: | English |
| Gepubliceerd in: |
2009
|
| Onderwerpen: |
| _version_ | 1826288790918922240 |
|---|---|
| author | Cummins, M |
| author2 | Newman, P |
| author_facet | Newman, P Cummins, M |
| author_sort | Cummins, M |
| collection | OXFORD |
| description | This thesis is concerned with the problem of place recognition for mobile robots. How can a robot determine its location from an image or sequence of images, without any prior knowledge of its position, even in a world where many places look identical? We outline a new probabilistic approach to the problem, which we call Fast Appearance Based Mapping or FAB-MAP. Our map of the environment consists of a set of discrete locations, each with an associated appearance model. For every observation collected by the robot, we compute a probability distribution over the map, and either create a new location or update our belief about the appearance of an existing location. The technique can be seen as a new type of SLAM algorithm, where the appearance of locations (rather than their position) is subject to estimation. Unlike existing SLAM systems, our appearance based technique does not rely on keeping track of the robot in any metric coordinate system. Thus it is applicable even when informative observations are available only intermittently. Solutions to the loop closure detection problem, the kidnapped robot problem and the multi-session mapping problem arise as special cases of our general approach. Abstract Our probabilistic model introduces several technical advances. The model incorporates correlations between visual features in a novel way, which is shown to improve system performance. Additionally, we explicitly compute an approximation to the partition function in our Bayesian formulation, which provides a natural probabilistic measure of when a new observation should be assigned to a location not already present in the map. The technique is applicable even in visually repetitive environments where many places look the same. Abstract Finally, we define two distinct approximate inference procedures for the model. The first of these is based on concentration inequalities and has general applicability beyond the problem considered in this thesis. The second approach, built on inverted index techniques, is tailored to our specific problem of place recognition, but achieves extreme efficiency, allowing us to apply FAB-MAP to navigation problems on the largest scale. The thesis concludes with a visual SLAM experiment on a trajectory 1,000 km long. The system successfully detects loop closures with close to 100% precision and requires average inference time of only 25 ms by the end of the trajectory. |
| first_indexed | 2024-03-07T02:19:02Z |
| format | Thesis |
| id | oxford-uuid:a34370f2-a2a9-40b5-9a2d-1c8c616ff07a |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T02:19:02Z |
| publishDate | 2009 |
| record_format | dspace |
| spelling | oxford-uuid:a34370f2-a2a9-40b5-9a2d-1c8c616ff07a2022-03-27T02:25:45ZProbabilistic localization and mapping in appearance spaceThesishttp://purl.org/coar/resource_type/c_db06uuid:a34370f2-a2a9-40b5-9a2d-1c8c616ff07aRoboticsInformation engineeringImage understandingEnglishOxford University Research Archive - Valet2009Cummins, MNewman, PThis thesis is concerned with the problem of place recognition for mobile robots. How can a robot determine its location from an image or sequence of images, without any prior knowledge of its position, even in a world where many places look identical? We outline a new probabilistic approach to the problem, which we call Fast Appearance Based Mapping or FAB-MAP. Our map of the environment consists of a set of discrete locations, each with an associated appearance model. For every observation collected by the robot, we compute a probability distribution over the map, and either create a new location or update our belief about the appearance of an existing location. The technique can be seen as a new type of SLAM algorithm, where the appearance of locations (rather than their position) is subject to estimation. Unlike existing SLAM systems, our appearance based technique does not rely on keeping track of the robot in any metric coordinate system. Thus it is applicable even when informative observations are available only intermittently. Solutions to the loop closure detection problem, the kidnapped robot problem and the multi-session mapping problem arise as special cases of our general approach. Abstract Our probabilistic model introduces several technical advances. The model incorporates correlations between visual features in a novel way, which is shown to improve system performance. Additionally, we explicitly compute an approximation to the partition function in our Bayesian formulation, which provides a natural probabilistic measure of when a new observation should be assigned to a location not already present in the map. The technique is applicable even in visually repetitive environments where many places look the same. Abstract Finally, we define two distinct approximate inference procedures for the model. The first of these is based on concentration inequalities and has general applicability beyond the problem considered in this thesis. The second approach, built on inverted index techniques, is tailored to our specific problem of place recognition, but achieves extreme efficiency, allowing us to apply FAB-MAP to navigation problems on the largest scale. The thesis concludes with a visual SLAM experiment on a trajectory 1,000 km long. The system successfully detects loop closures with close to 100% precision and requires average inference time of only 25 ms by the end of the trajectory. |
| spellingShingle | Robotics Information engineering Image understanding Cummins, M Probabilistic localization and mapping in appearance space |
| title | Probabilistic localization and mapping in appearance space |
| title_full | Probabilistic localization and mapping in appearance space |
| title_fullStr | Probabilistic localization and mapping in appearance space |
| title_full_unstemmed | Probabilistic localization and mapping in appearance space |
| title_short | Probabilistic localization and mapping in appearance space |
| title_sort | probabilistic localization and mapping in appearance space |
| topic | Robotics Information engineering Image understanding |
| work_keys_str_mv | AT cumminsm probabilisticlocalizationandmappinginappearancespace |