OHM: GPU Based Occupancy Map Generation
This work addresses the bottleneck of real-time map generation for autonomous robots, particularly in challenging environments, though it is incremental as it adapts existing algorithms to GPU acceleration.
The paper tackles the problem of slow CPU-based occupancy grid map generation for autonomous robotic navigation by introducing OHM, a GPU-based framework, which demonstrates excellent performance improvements in offline and online processing, enabling a second-place finish in the DARPA Subterranean Challenge.
Occupancy grid maps (OGMs) are fundamental to most systems for autonomous robotic navigation. However, CPU-based implementations struggle to keep up with data rates from modern 3D lidar sensors, and provide little capacity for modern extensions which maintain richer voxel representations. This paper presents OHM, our open source, GPU-based OGM framework. We show how the algorithms can be mapped to GPU resources, resolving difficulties with contention to obtain a successful implementation. The implementation supports many modern OGM algorithms including NDT-OM, NDT-TM, decay-rate and TSDF. A thorough performance evaluation is presented based on tracked and quadruped UGV platforms and UAVs, and data sets from both outdoor and subterranean environments. The results demonstrate excellent performance improvements both offline, and for online processing in embedded platforms. Finally, we describe how OHM was a key enabler for the UGV navigation solution for our entry in the DARPA Subterranean Challenge, which placed second at the Final Event.