Predicted Safety Algorithms for Autonomous Excavators Using a 3D LiDAR Sensor

This paper proposes sensing and safety techniques for autonomous excavators working on construction sites. In autonomous construction equipment, safety is a significant concern to reduce fatal accidents and machinery damage. In taking up this point of view, this paper deals with object tracking, motion prediction, and track management for detected objects that can improve the safety function of autonomous construction equipment. By using the info of predicted motion of detected objects and actual working areas of an excavator, and calculating safety indices, the proposed safety algorithms can evaluate the degree of safety (i.e., potential collision risks).