Efficient Representation in Three-Dimensional Environment Modeling for Planetary Robotic Exploration

Abstract

Good situational awareness is an absolute must when operating mobile robots for planetary exploration. Three-dimensional (3-D) sensing and modeling data gathered by the robot are, hence, crucial for the operator. However, standard methods based on stereo vision have their limitations, especially in scenarios where there is no or only very limited visibility, e.g., due to extreme light conditions. Three-dimensional laser range finders (3-D-LRFs) provide an interesting alternative, especially as they can provide very accurate, high-resolution data at very high sampling rates. However, the more 3-D range data are acquired, the harder it becomes to transmit the data to the operator station. Here, a fast and robust method to fit planar surface patches into the data is presented. The usefulness of the approach is demonstrated in two different sets of experiments. The first set is based on data from our participation at the European Space Agency Lunar Robotics Challenge 2008. The second one is based on data from a Velodyne 3-D-LRF in a high-fidelity simulation with ground truth data from Mars.