Rating is available when the video has been rented.
This feature is not available right now. Please try again later.
Published on Oct 4, 2016
Autonomous vehicles should reliably detect obstacles and plan paths without always relying on extensive manually labelled datasets or expensive sensors. In this video we present our work towards segmenting path proposals and obstacles using a driver to implicitly label valid paths at train time, then only using monocular camera at run time. Details of the approach can be found at: https://arxiv.org/abs/1610.01238
D. Barnes, W. Maddern and I. Posner: "Find Your Own Way: Weakly-Supervised Segmentation of Path Proposals for Urban Autonomy," arXiv preprint arXiv:1610.01238, 2016
Presented at the IEEE International Conference on Robotics and Automation (ICRA) 2017.