Litcius/Paper detail

3D traversability analysis and path planning based on mechanical effort for UGVs in forest environments

Afonso E. Carvalho, João Filipe Ferreira, David Portugal

2023Robotics and Autonomous Systems21 citationsDOIOpen Access PDF

Abstract

Autonomous navigation in rough and dynamic 3D environments is a major challenge for modern robotics. This paper presents a novel traversability analysis and path planning technique that processes 3D point cloud maps to compute terrain gradient information and detect the presence of obstacles to generate efficient paths. These avoid unnecessary slope changes when more conservative paths are available, potentially promoting fuel economy, reducing the wear on the equipment and the associated risks. The proposed approach is shown to outperform existing techniques both in realistic 3D simulation scenarios as well as in a real forest dataset, in which it also generates paths that are comparable to the ones drawn by humans with different backgrounds and expertise levels.

Topics & Concepts

Computer scienceMotion planningTerrainRoboticsPoint cloudArtificial intelligencePath (computing)Point (geometry)RobotOperations researchMachine learningProgramming languageMathematicsBiologyEcologyGeometryEngineeringRobotic Path Planning AlgorithmsRobotics and Sensor-Based LocalizationAutonomous Vehicle Technology and Safety