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

@article{Kahn2021BADGRAA,
  title={BADGR: An Autonomous Self-Supervised Learning-Based Navigation System},
  author={G. Kahn and P. Abbeel and Sergey Levine},
  journal={IEEE Robotics and Automation Letters},
  year={2021},
  volume={6},
  pages={1312-1319}
}
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 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, we… Expand
Robot Perception enables Complex Navigation Behavior via Self-Supervised Learning
Model-Based Visual Planning with Self-Supervised Functional Distances
Learning-Based Methods of Perception and Navigation for Ground Vehicles in Unstructured Environments: A Review
Motion Control for Mobile Robot Navigation Using Machine Learning: a Survey
High-Speed Robot Navigation using Predicted Occupancy Maps
...
1
2
3
...

References

SHOWING 1-10 OF 44 REFERENCES
Self-Supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation
Deep Visual MPC-Policy Learning for Navigation
Learning Navigation Behaviors End-to-End With AutoRL
Learning monocular reactive UAV control in cluttered natural environments
Learning long-range vision for autonomous off-road driving
Neural Autonomous Navigation with Riemannian Motion Policy
Safe Visual Navigation via Deep Learning and Novelty Detection
(CAD)$^2$RL: Real Single-Image Flight without a Single Real Image
...
1
2
3
4
5
...