Corpus ID: 34206477

Obstacle Avoidance through Deep Networks based Intermediate Perception

@article{Yang2017ObstacleAT,
  title={Obstacle Avoidance through Deep Networks based Intermediate Perception},
  author={Shichao Yang and Sandeep Konam and Chen Ma and Stephanie Rosenthal and Manuela M. Veloso and Sebastian A. Scherer},
  journal={ArXiv},
  year={2017},
  volume={abs/1704.08759}
}
  • Shichao Yang, Sandeep Konam, +3 authors Sebastian A. Scherer
  • Published 2017
  • Computer Science, Engineering
  • ArXiv
  • Obstacle avoidance from monocular images is a challenging problem for robots. Though multi-view structure-from-motion could build 3D maps, it is not robust in textureless environments. Some learning based methods exploit human demonstration to predict a steering command directly from a single image. However, this method is usually biased towards certain tasks or demonstration scenarios and also biased by human understanding. In this paper, we propose a new method to predict a trajectory from… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 20 CITATIONS

    J-MOD2: Joint Monocular Obstacle Detection and Depth Estimation

    VIEW 3 EXCERPTS
    CITES METHODS

    Learning to Fly by MySelf: A Self-Supervised CNN-Based Approach for Autonomous Navigation

    VIEW 1 EXCERPT
    CITES METHODS

    Learn to Steer through Deep Reinforcement Learning

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Automatic Drone Navigation in Realistic 3D Landscapes using Deep Reinforcement Learning

    Visual Navigation for Biped Humanoid Robots Using Deep Reinforcement Learning

    VIEW 2 EXCERPTS
    CITES METHODS

    A Convolutional Neural Network Feature Detection Approach to Autonomous Quadrotor Indoor Navigation

    VIEW 1 EXCERPT
    CITES METHODS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 28 REFERENCES

    Fast robust monocular depth estimation for Obstacle Detection with fully convolutional networks

    VIEW 1 EXCERPT

    A deep-network solution towards model-less obstacle avoidance

    • Lei Tai, Shaohua Li, Ming Liu
    • Computer Science
    • 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
    • 2016
    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    A Machine Learning Approach to Visual Perception of Forest Trails for Mobile Robots

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Real-time 3D scene layout from a single image using Convolutional Neural Networks

    VIEW 1 EXCERPT

    Pop-up SLAM: Semantic monocular plane SLAM for low-texture environments

    VIEW 1 EXCERPT

    DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving

    VIEW 3 EXCERPTS

    Autonomous MAV flight in indoor environments using single image perspective cues

    VIEW 1 EXCERPT