OpenRatSLAM source code

RatSLAM is a robot navigation and SLAM system based on computational models of the hippocampus. The approach uses a combination of appearance based visual scene matching, competitive attractor networks, and a semi-metric topological map representation. The approach has been proven in a real time 40 hour robot delivery task, mapping an entire Australian suburb and on Oxford's New College dataset. Notably, RatSLAM works well on images obtained from cheap cameras. The RatSLAM system contrasts many of the other SLAM approaches that involve expensive precision laser sensors and occupancy grids.