This study describes mobile robot surveillance system using spatial temporal GIS. This paper specially describes the method of collecting spatial temporal data by an autonomous mobile robot system used in a factory premises with some high-rise buildings. This system consists of a wireless LAN network, a base station and an autonomous vehicle. The vehicle is equipped with a GPS/INS navigation system using the network-based Real-Time Kinematic GPS (RTK-GPS) with Positioning Augmentation Services (PAS™, Mitsubishi Electric Corporation 2003), an Area Laser Radar (ALR), a slaved camera, and an Omni-Directional Vision (ODV) sensor for surveillance and reconnaissance. The vehicle switches control modes according to the vehicle navigation error. It has three modes, "Normal", "Road tracking", and "Crossing recognition". A field test result shows that the vehicle can track the planned-path within 0.10 [m] accuracy at straight paths and within 0.25 [m] for curved paths even if RTK fixed solutions are not available. Field experiments and analyses have proved that the proposed navigation method can provide sufficient navigation and guidance accuracy under poor satellite geometry and visibility. Omni-directional image and ALR's scan data, which is synchronized with both position and GPS time, is memorized as spatial temporal. This spatial temporal data enables the operator to search everywhere in the factory premises efficiently by way of arbitrary position or measured time. The field test reveals that the spatial temporal database is confirmed to be useful for remote surveillance.