Learning Long-range Terrain Perception for Autonomous Mobile Robots

  title={Learning Long-range Terrain Perception for Autonomous Mobile Robots},
  author={Mingjun Wang and Jun Zhou and Jun Tu and Chengliang Liu},
Long-range terrain perception has a high value in performing efficient autonomous navigation and risky intervention tasks for field robots, such as earlier recognition of hazards, better path planning, and higher speeds. However, Stereo-based navigation systems can only perceive near-field terrain due to the nearsightedness of stereo vision. Many near-to-far learning methods, based on regions’ appearance features, are proposed to predict the far-field terrain. We proposed a statistical… CONTINUE READING
4 Citations
20 References
Similar Papers


Publications referenced by this paper.
Showing 1-10 of 20 references

Hand-labeled DARPA LAGR data sets

  • M. J. Procopio
  • 2007

Optical Flow Approaches for Self-supervised Learning in Autonomous Mobile Robot Navigation, In: Autonomous Navigation in Dynamic Environments

  • Lookingbill, D. Lieb, S. Thrun
  • 2007

Similar Papers

Loading similar papers…