Towards Generalizing Sensorimotor Control Across Weather Conditions

@article{Khan2019TowardsGS,
  title={Towards Generalizing Sensorimotor Control Across Weather Conditions},
  author={Qadeer Ahmad Khan and Patrick Wenzel and Daniel Cremers and Laura Leal-Taix{\'e}},
  journal={2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  year={2019},
  pages={4497-4503}
}
  • Qadeer Ahmad Khan, Patrick Wenzel, +1 author Laura Leal-Taixé
  • Published 2019
  • Computer Science, Mathematics
  • 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • The ability of deep learning models to generalize well across different scenarios depends primarily on the quality and quantity of annotated data. Labeling large amounts of data for all possible scenarios that a model may encounter would not be feasible; if even possible. We propose a framework to deal with limited labeled training data and demonstrate it on the application of vision-based vehicle control. We show how limited steering angle data available for only one condition can be… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 35 REFERENCES

    End-to-End Learning of Driving Models from Large-Scale Video Datasets

    VIEW 2 EXCERPTS

    End-to-End Training of Deep Visuomotor Policies

    VIEW 1 EXCERPT

    DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving

    VIEW 1 EXCERPT

    End-to-End Driving Via Conditional Imitation Learning

    VIEW 1 EXCERPT

    End to End Learning for Self-Driving Cars

    VIEW 2 EXCERPTS

    Are we ready for autonomous driving? The KITTI vision benchmark suite

    VIEW 2 EXCERPTS