Learning an Image-Based Obstacle Detector with Automatic Acquisition of Training Data

Abstract

We detect and localize obstacles in front of a mobile robot by means of a deep neural network that maps images acquired from a forward-looking camera to the outputs of five proximity sensors. The robot autonomously acquires training data in multiple environments; once trained, the network can detect obstacles and their position also in unseen scenarios, and can be used on different robots, not equipped with proximity sensors. We demonstrate both the training and deployment phases on a small modified Thymio robot.

Cite

Text

Toniolo et al. "Learning an Image-Based Obstacle Detector with Automatic Acquisition of Training Data." AAAI Conference on Artificial Intelligence, 2018. doi:10.1609/AAAI.V32I1.11368

Markdown

[Toniolo et al. "Learning an Image-Based Obstacle Detector with Automatic Acquisition of Training Data." AAAI Conference on Artificial Intelligence, 2018.](https://mlanthology.org/aaai/2018/toniolo2018aaai-learning/) doi:10.1609/AAAI.V32I1.11368

BibTeX

@inproceedings{toniolo2018aaai-learning,
  title     = {{Learning an Image-Based Obstacle Detector with Automatic Acquisition of Training Data}},
  author    = {Toniolo, Stefano and Guzzi, Jérôme and Gambardella, Luca Maria and Giusti, Alessandro},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2018},
  pages     = {8220-8221},
  doi       = {10.1609/AAAI.V32I1.11368},
  url       = {https://mlanthology.org/aaai/2018/toniolo2018aaai-learning/}
}