Autonomous Miniature Aerial Vehicles: Vision-based Obstacle Avoidance

Our algorithms, based on Make3D, have enabled RC cars and MAVs to avoid obstacles using vision, and successfully navigate indoor and outdoor environments with a wide variety of obstacles (trees, buildings, poles, fences,...). Our learning algorithms map visual features from a single image into 3D depths using which the MAV plans a obstacle-free path online.

(Material for media.)

Publications

Low-Power Parallel Algorithms for Single Image based Obstacle Avoidance in Aerial Robots,
Ian Lenz, Mevlana Gemici, Ashutosh Saxena. In International Conference on Intelligent Robots and Systems (IROS), 2012. [PDF] bibtex

@inproceedings{lenz_obsavoid_2012,
  title={Low-Power Parallel Algorithms for Single Image based Obstacle Avoidance in Aerial Robots},
  author={Ian Lenz and Mevlana Gemici and Ashutosh Saxena},
  booktitle={International Conference on Intelligent Robotic Systems (IROS)},
  year={2012}
}

Autonomous MAV Flight in Indoor Environments using Single Image Perspective Cues,
Cooper Bills, Joyce Chen, Ashutosh Saxena. In International Conference on Robotics and Automation (ICRA), 2011. [pdf]

Autonomous Indoor Helicopter Flight using a Single Onboard Camera,
Sai Prasanth Soundararaj, Arvind Sujeeth, Ashutosh Saxena. In International Conference on Intelligent RObots and Systems (IROS), 2009. [pdf]

High Speed Obstacle Avoidance using Monocular Vision and Reinforcement Learning, Jeff Michels, Ashutosh Saxena, Andrew Y. Ng. In 22nd Int'l Conf on Machine Learning (ICML), 2005. [pdf, More]