Negative Obstacle Detection - Robotics Institute Carnegie Mellon University
Negative Obstacle Detection

Successful autonomous navigation requires detection not only of stationary and moving positive obstacles (guard rails, vehicles, people), but also the detection of negative obstacles (holes and ditches) at ranges that are nearly impossible for ladar and difficult for cameras.

Advanced Negative Obstacle Detection System testing includes different scenarios and takes place at different times, night and day. The goal is to learn to learn to detect negative obstacles more certainly and at a greater distance so that the UGV can travel on safer and faster paths.

past contact

  • Thomas Gordon