RI | Research | Projects | ALVINN

Text only version of this site

Autonomous Land Vehicle In a Neural Network (ALVINN) This project is no longer active. Head: Dean Pomerleau Mailing address: Carnegie Mellon University Robotics Institute 5000 Forbes Avenue Pittsburgh, PA 15213 Associated center: VASC Associated lab/group: NavLab

Jump to: Project Description | Personnel | Sub-projects | Publications

Project Description

ALVINN is a perception system which learns to control the NAVLAB vehicles by watching a person drive. ALVINN's architecture consists of a single hidden layer back-propagation network. The input layer of the network is a 30x32 unit two dimensional "retina" which receives input from the vehicles video camera. Each input unit is fully connected to a layer of five hidden units which are in turn fully connected to a layer of 30 output units. The output layer is a linear representation of the direction the vehicle should travel in order to keep the vehicle on the road.

Past members

	Name	Title	Email Address
	Richard Carley	Professor, ECE	lrc@andrew.cmu.edu
	Todd Jochem	Systems Scientist	tjochem@foster-miller.com
	Takeo Kanade	U.A. and Helen Whitaker University Prof., RI/CS	tk@cs.cmu.edu
	Dean Pomerleau	Adjunct Research Scientist (Adjunct)	deanp@assistware.com

Past Sub-projects

Distributed Architecture for Mobile Navigation - The Distributed Architecture for Mobile Navigation (DAMN) is a behavior-based architecture similar in spirit to the Subsumption Architecture.

Recent publications [View all 16 publications]

• Applying Advanced Learning Algorithms to ALVINN
  P. Batavia, D. Pomerleau, and C. Thorpe
  tech. report CMU-RI-TR-96-31, Robotics Institute, Carnegie Mellon University, October, 1996. [Abstract]
  Download: pdf [151 KB], ps.gz [79 KB] copyrighted

• Evolution of an artificial neural network based autonomous land vehicle controller
  S. Baluja
  IEEE Transactions on Systems, Man and Cybernetics, Part B, Vol. 26, No. 3, June, 1996, pp. 450 - 463. [Abstract]
  Download: pdf [2258 KB] copyrighted

• Vision Guided Lane Transition
  T. Jochem, D. Pomerleau, and C. Thorpe
  IEEE Symposium on Intelligent Vehicles, September, 1995, pp. 30 - 35. [Abstract]
  Download: pdf [513 KB] copyrighted

• ELVIS: Eigenvectors for Land Vehicle Image System
  J. Hancock and C. Thorpe
  Proceedings of the International Conference on Intelligent Robots and Systems. 'Human Robot Interaction and Cooperative Robots' (IROS '95), Vol. 1, August, 1995, pp. 35 - 40. [Abstract]
  Download: pdf [673 KB] copyrighted

• Vision-Based Neural Network Road and Intersection Detection and Traversal
  T. Jochem, D. Pomerleau, and C. Thorpe
  IEEE Conference on Intelligent Robots and Systems (IROS '95), Vol. 3, August, 1995, pp. 344 - 349. [Abstract]
  Download: pdf [633 KB] copyrighted

• Neural Network Vision for Robot Driving
  D. Pomerleau
  The Handbook of Brain Theory and Neural Networks, M. Arbib, ed., 1995.
  Download: pdf [375 KB], ps.gz [325 KB] copyrighted

• ELVIS: Eigenvectors for Land Vehicle Image System
  J. Hancock and C. Thorpe
  tech. report CMU-RI-TR-94-43, Robotics Institute, Carnegie Mellon University, December, 1994. [Abstract]
  Download: pdf [153 KB], ps.gz [416 KB] copyrighted

• Defense and Civilian Applications of the ALVINN Robot Driving System
  D. Pomerleau
  1994 Government Microcircuit Applications Conference, November, 1994, pp. 358-362. [Abstract]
  Download: pdf [114 KB] copyrighted

• Panacea: An Active Sensor Controller for the ALVINN Autonomous Driving System
  R. Sukthankar, D. Pomerleau, and C. Thorpe
  tech. report CMU-RI-TR-93-09, Robotics Institute, Carnegie Mellon University, April, 1993. [Abstract]
  Download: pdf [272 KB], ps.gz [733 KB] copyrighted

• MANIAC: A Next Generation Neurally Based Autonomous Road Follower
  T. Jochem, D. Pomerleau, and C. Thorpe
  Proceedings of the International Conference on Intelligent Autonomous Systems, February, 1993. [Abstract]
  Download: pdf [21 KB], ps.gz [26 KB] copyrighted