Corpus ID: 211096687

BADGR: An Autonomous Self-Supervised Learning-Based Navigation System

@article{Kahn2020BADGRAA,
  title={BADGR: An Autonomous Self-Supervised Learning-Based Navigation System},
  author={Gregory Kahn and Pieter Abbeel and Sergey Levine},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.05700}
}
  • Gregory Kahn, Pieter Abbeel, Sergey Levine
  • Published in ArXiv 2020
  • Computer Science, Engineering
  • Mobile robot navigation is typically regarded as a geometric problem, in which the robot's objective is to perceive the geometry of the environment in order to plan collision-free paths towards a desired goal. However, a purely geometric view of the world can can be insufficient for many navigation problems. For example, a robot navigating based on geometry may avoid a field of tall grass because it believes it is untraversable, and will therefore fail to reach its desired goal. In this work… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Citations

    Publications citing this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 41 REFERENCES

    Self-Supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation

    VIEW 5 EXCERPTS

    Deep Visual MPC-Policy Learning for Navigation

    VIEW 1 EXCERPT

    Learning Navigation Behaviors End-to-End With AutoRL

    VIEW 1 EXCERPT

    Learning to Drive in a Day

    VIEW 1 EXCERPT

    Neural Autonomous Navigation with Riemannian Motion Policy

    VIEW 1 EXCERPT

    Where Should I Walk? Predicting Terrain Properties From Images Via Self-Supervised Learning

    VIEW 1 EXCERPT

    Deep Ordinal Regression Network for Monocular Depth Estimation