Learning long‐range vision for autonomous off‐road driving

Citations Over TimeTop 1% of 2009 papers

Abstract

Abstract Most vision‐based approaches to mobile robotics suffer from the limitations imposed by stereo obstacle detection, which is short range and prone to failure. We present a self‐supervised learning process for long‐range vision that is able to accurately classify complex terrain at distances up to the horizon, thus allowing superior strategic planning. The success of the learning process is due to the self‐supervised training data that are generated on every frame: robust, visually consistent labels from a stereo module; normalized wide‐context input windows; and a discriminative and concise feature representation. A deep hierarchical network is trained to extract informative and meaningful features from an input image, and the features are used to train a real‐time classifier to predict traversability. The trained classifier sees obstacles and paths from 5 to more than 100 m, far beyond the maximum stereo range of 12 m, and adapts very quickly to new environments. The process was developed and tested on the LAGR (Learning Applied to Ground Robots) mobile robot. Results from a ground truth data set, as well as field test results, are given. © 2009 Wiley Periodicals, Inc.

Related Papers

• → The Study of the Impact of Obstacle on the Efficiency of Evacuation under Different Competitive Conditions(2018)13 cited
• → Efficient field courses around an obstacle(1989)8 cited
• The Analysis and Countermeasures on the Obstacle of Communicate with Human Relation in Colleges and Universities Ideological Political Work(2002)
• Study of safety in airports operation through the development of an automatic tool for the design of obstacle limitation surfaces and procedure obstacle free areas(2015)
• → Efficient field courses around an obstacle(1989)