|Autonomous navigation in outdoor, off-road environments requires solving complex classification problems. Obstacle detection, road following and terrain classification are examples of tasks which have been successfully approached using supervised machine learning techniques for classification. Large amounts of training data are usually necessary in order to achieve satisfactory generalization. In such cases, manually labeling data becomes an expensive and tedious process.
This paper describes a method for reducing the amount of data that needs to be presented to a human trainer. The algorithm relies on kernel density estimation in order to identify "interesting" scenes in a dataset. Our method does not require any interaction with a human expert for selecting the images, and only minimal amounts of tuning are necessary.
We demonstrate its effectiveness in several experiments using data collected with two different vehicles. We first show that our method automatically selects those scenes from a large dataset that a person would consider "important" for classification tasks. Secondly, we show that by labeling only few of the images selected by our method, we obtain classification performance that is comparable to the one reached after labeling hundreds of images from the same dataset.
|outdoor mobile robotics, outdoor obstacle detection, machine learning, active learning|
Associated Center(s) / Consortia:
Vision and Autonomous Systems Center, National Robotics Engineering Center, and Field Robotics Center
Associated Project(s): CTA Robotics and Vehicle Safeguarding
Number of pages: 7
|Cristian Dima, Martial Hebert, and Anthony (Tony) Stentz, "Enabling Learning From Large Datasets: Applying Active Learning to Mobile Robotics," International Conference on Robotics and Automation, April, 2004, pp. 108 - 114.|
author = "Cristian Dima and Martial Hebert and Anthony (Tony) Stentz",
title = "Enabling Learning From Large Datasets: Applying Active Learning to Mobile Robotics",
booktitle = "International Conference on Robotics and Automation",
pages = "108 - 114",
publisher = "IEEE",
month = "April",
year = "2004",
volume = "1",
|The Robotics Institute is part of the School of Computer Science, Carnegie Mellon University.|
Contact Us | Update Instructions