Grant: Department of National Defence / NSERC Research Partnership
University of Toronto
$14,000.00
Lidar-Based Visual Odometry, Teach & Repeat, and SLAM for Mobile Robots
EF 2013-14
Résumé
Mobile robots are beginning to be used in a wide variety of situations, including planetary exploration (e.g., NASA Mars Exploration Rovers) and safety-and-security (e.g., bomb disposal robots). As applications become more ambitious, there will be a demand for increased autonomy and robustness of operations, particularly for environments in which the global positioning system (GPS) is not available. Much of the state-of-the-art in autonomy for mobile robots operating in unstructured, three-dimensional environments (e.g., outdoors) is centered around the use of passive camera systems, and in particular stereo cameras (i.e., a pair of cameras used to extract depth information about the world). Techniques based on passive cameras require consistent ambient lighting, which is often not possible in practical situations. This project aims to advance three core vision-based mobile robot skills for GPS-denied environments -- visual odometry (VO), visual teach & repeat (VT\&R), and visual simultaneous localization and mapping (VSLAM) -- through the use of a light detection and ranging (lidar) sensor. Because lidar is an active vision sensor (i.e., it provides its own consistent source of light), the situations in which these critical robot skills may be used will be expanded significantly. Our novel approach will be to use two-dimensional lidar intensity and ranges images directly, rather than to convert the lidar data to conventional three-dimensional points. This will allow us to exploit the vast body of work on two-dimensional vision techniques, thereby allowing efficient online implementations.
Programme
Department of National Defence / NSERC Research Partnership
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
402303-2010
Name nom
Barfoot, Tim
Department département
Aerospace Studies, Institute for
Organization id
31
Institution établissement
University of Toronto
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2013
Competition year année de concours
2010
Award amount
14000
Program id
DNDPJ
Program name en
Department of National Defence / NSERC Research Partnership
Program name fr
Partenariat de recherche du ministère de la Défense nationale et du CRSNG
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
703
Area of application group en
Transportation systems and services
Area of application group fr
Services et systèmes de transport
Area of application en
Aerospace
Area of application fr
Aérospatial
Research subject code
2600
Research subject group en
Robotics
Research subject group fr
Robotique
Research subject en
Robotics
Research subject fr
Robotique
Partie
4
Nb partie
4
Application title
Lidar-Based Visual Odometry, Teach & Repeat, and SLAM for Mobile Robots
Keyword
NSERC
Application summary
Mobile robots are beginning to be used in a wide variety of situations, including planetary exploration (e.g., NASA Mars Exploration Rovers) and safety-and-security (e.g., bomb disposal robots). As applications become more ambitious, there will be a demand for increased autonomy and robustness of operations, particularly for environments in which the global positioning system (GPS) is not available. Much of the state-of-the-art in autonomy for mobile robots operating in unstructured, three-dimensional environments (e.g., outdoors) is centered around the use of passive camera systems, and in particular stereo cameras (i.e., a pair of cameras used to extract depth information about the world). Techniques based on passive cameras require consistent ambient lighting, which is often not possible in practical situations. This project aims to advance three core vision-based mobile robot skills for GPS-denied environments -- visual odometry (VO), visual teach & repeat (VT\&R), and visual simultaneous localization and mapping (VSLAM) -- through the use of a light detection and ranging (lidar) sensor. Because lidar is an active vision sensor (i.e., it provides its own consistent source of light), the situations in which these critical robot skills may be used will be expanded significantly. Our novel approach will be to use two-dimensional lidar intensity and ranges images directly, rather than to convert the lidar data to conventional three-dimensional points. This will allow us to exploit the vast body of work on two-dimensional vision techniques, thereby allowing efficient online implementations.