Landmark manipulation system for mobile robot navigation

In mobile robot scenarios, it is expected that the robot autonomously navigates through home or office environments and processes objects/landmarks during navigation. Landmark manipulation is identified as one important research area in robot navigation systems. We have developed an online robot landmark processing system (RLPS) to detect, classify, and localize different types of landmarks during robot navigation. The RLPS is based on a two-step classification stage which is robust and invariant towards scaling and translations. It provides a good balance between fast processing time and high detection accuracy by combining the strengths of appearance-based and model-based object classification techniques. The experimental results showed that the RLPS is more powerful as it recognizes a wide range of landmarks and efficiently handles landmarks with occlusions, viewpoint variances, and illumination changes.