SVM-based discriminative accumulation scheme for place recognition

• Published in: 2008 IEEE International Conference on Robotics and Automation pp. 522 - 529
• Main Authors: Pronobis, A., Martinez Mozos, O., Caputo, B.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.05.2008
• Series: IEEE International Conference On Robotics And Automation
• Subjects: Computer science; Datavetenskap; Indoor environments; Information technology; Informationsteknik; Lighting; Mobile robots; Robot sensing systems; Robotics and automation; Robustness; Support vector machine classification; Support vector machines; TECHNOLOGY; TEKNIKVETENSKAP; USA Councils
• ISBN: 1424416469; 9781424416462
• ISSN: 1050-4729
• DOI: 10.1109/ROBOT.2008.4543260

Integrating information coming from different sensors is a fundamental capability for autonomous robots. For complex tasks like topological localization, it would be desirable to use multiple cues, possibly from different modalities, so to achieve robust performance. This paper proposes a new method for integrating multiple cues. For each cue we train a large margin classifier which outputs a set of scores indicating the confidence of the decision. These scores are then used as input to a support vector machine, that learns how to weight each cue, for each class, optimally during training. We call this algorithm SVM-based discriminative accumulation scheme (SVM-DAS). We applied our method to the topological localization task, using vision and laser-based cues. Experimental results clearly show the value of our approach.