Moving Object Prediction for Off-Road Autonomous Navigation
Rajmohan Madhavan, Craig I. Schlenoff
The realization of on- and o.-road autonomous navigation of Unmanned Ground Vehicles (UGVs) requiresreal-time motion planning in the presence of dynamic objects with unknown trajectories. To successfully planpaths and to navigate in an unstructured environment, the UGVs should have the di.cult and computationallyintensive competency to predict the future locations of moving objects that could interfere with its path. Thispaper details the development of a combined probabilistic object classi.cation and estimation theoretic frameworkto predict the future location of moving objects, along with an associated uncertainty measure. The developmentof a moving object testbed that facilitates the testing of di.erent representations and prediction algorithms inan implementation-independent platform is also outlined.
and Schlenoff, C.
Moving Object Prediction for Off-Road Autonomous Navigation, SPIE Aerosense Conference, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=823452
(Accessed June 5, 2023)