In this talk, we propose the use of an efficient, structured multiresolution representation for robot mapping and planning. We focus on expanding the sensor range of dense local grids for memory-constrained platforms. While multiresolution data structures have been proposed previously, we avoid processing redundant information and use the organization of the grid to improve efficiency. By layering 3D circular buffers that double in resolution at each subsequent level, objects near the robot are represented at finer resolutions while coarse spatial information is maintained at greater distances. We also introduce a novel method for efficiently calculating the Euclidean distance transform on the multiresolution grid by leveraging its structure. Lastly, we utilize our proposed framework to demonstrate improved stereo camera-based MAV obstacle avoidance with an optimization-based planner in simulation.
Michael Kaess (Advisor)
Zoom Participation Enabled. See announcement.