|
|||||
|
|
Loop-closing: A typicality approach |
|
| Authors: | E Jauregi I Irigoien B Sierra E Lazkano C Arenas |
| Affiliation: | 2. Department of Statistics, University of Barcelona, Spain;1. Pediatric Emergency Department, Assistance Publique Hôpitaux de Paris, Robert Debré Hospital, Paris, France;2. INSERM, U1141, Paris, France;3. Department of Neurology, University of California San Francisco, San Francisco, California;4. University of Udine, Udine, Italy;5. University Paris Diderot, Sorbonne Paris Cité, Paris, France;6. PremUP, Paris, France;7. Centre for the Developing Brain, King''s College, St Thomas'' Campus, London UK;1. Department of Aeronautics and Astronautics, Fudan University, Shanghai, China;2. Department of Mechanical and Industrial Engineering, Concordia University, Montreal, Canada;1. Cardiff University, United Kingdom;2. CSC, University of Luxembourg, Luxembourg;3. University of Cape Town and CAIR, South Africa;4. CRIL, Univ. Artois & CNRS, France |
| Abstract: | Loop-closing has long been identified as a critical issue when building maps from local observations. Topological mapping methods abstract the problem of how loops are closed from the problem of how to determine the metrical layout of places in the map and how to deal with noisy sensors.The typicality problem refers to the identification of new classes in a general classification context. This typicality concept is used in this paper to help a robot acquire a topological representation of the environment during its exploration phase. The problem is addressed using the INCA statistic which follows a distance-based approach.In this paper we describe a place recognition approach based on match testing by means of the INCA test. We describe the theoretical basis of the approach and present extensive experimental results performed in both a simulated and a real robot-environment system; Behaviour Based philosophy is used to construct the whole control architecture. Obtained results show the validity of the approach. |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ | |