|
|
|
|
|
ABSTRACT Even today, navigation in unknown or partially known environments remains one of the biggest challenges in autonomous mobile robotics. Systems based on the geometrical paradigm become problematic if the robot tries to map large environments. My research has put forward a new paradigm towards solving this problem. Fingerprints (i.e. circular list of features around the robot) have been proven to be a very promising approach towards effective place characterization and hence environment modeling. The approach is based on sound probabilistic techniques and thus aims at coping with the uncertainty in the environment. The proposed concept is based on a topological framework. This type of space representation permits a reliable, compact and distinctive environment-modeling. This technique has been used as an approach to solve the localization, mapping and SLAM problems. An exhaustive repertoire of experiments conducted on a mobile robotic platform, has proven this approach to be highly potent. My presentation would detail the complete methodology, experiments conducted, results obtained, problems that have been solved and ongoing research. Adriana Tapus PhD student, EPFL Autonomous Systems Lab URL: http://asl.epfl.ch/member.php?SCIPER=156345 |
|
Back to CRES |