Visible Electro-Optical (EO) System and LIDAR Fusion for Low Cost Perception by Autonomous Ground Vehicles

The Toyon-MST team proposes to perform research and development of a system which fuses multi-spectral EO and 3D data collected with a low-cost LIDAR to enable improved perception for unmanned ground vehicles (UGVs). The scope of the proposed work includes development of algorithms and software, and development, implementation, integration, testing, and delivery of a prototype, to perform EO-LIDAR fusion enabling improved navigation and obstacle avoidance by Navy UGVs. The proposed Phase II effort includes development of innovative algorithms and efficient software for auto-calibration of the multi-spectral EO and LIDAR sensors. The purpose of this development is to enable effective multi-sensor fusion, including stereo EO range estimation, multi-spectral EO terrain classification, and fusion of EO and LIDAR data for improved 3D imaging and terrain/obstacle classification. The proposed Phase II effort also includes development of innovative algorithms and efficient software for EO-LIDAR fusion for 3D imaging with improved resolution and accuracy, and for terrain characterization, including detection of obstacles hidden in vegetation such as tall grass. The focus of initial development is on mid-to-large-sized UGVs, such as the EV1 HMMVW and EV2 ITV developmental Navy UGV platforms, capable of carrying large equipment loads and improving mobility for marine expeditionary forces.