A solution for SLAM through augmenting vision and range information

— This paper proposes a method for augmenting the information of a monocular camera and a range finder. This method is a valuable step towards solving the SLAM problem in unstructured environments free from problems of using encoders’ data. Proposed algorithm causes the robot to benefit from a feature-based map for filtering purposes, while it exploits an accurate motion model, based on point-wise raw range scan matching rather than unreliable feature-based range scan matching, in unstructured environments. Moreover, robust loop closure detection procedure is the other consequence of this method. Experiments with a low-cost IEEE 1394 webcam and a range finder illustrate the effectiveness of the proposed method in drift-free SLAM at loop closing motions in unstructured environments.

• Type: Conference
• Year: 2008
• Where: IROS
• Authors: Ali Akbar Aghamohammadi, Amir Hossein Tamjidi, Hamid D. Taghirad
• Keywords: IROS 2008, Range Finder, Robotics, Unreliable Feature-based Range, Unstructured Environments