Autonomous Land Vehicle In a Neural Network (ALVINN),
1996.
HTML Version. The ALVINN project site.
Pomerleau, D.A.[Dean A.],
Efficient Training of Artificial Neural Networks for
Autonomous Navigation,
NeurComp(3), No. 1, 1991, pp. 88-97.
BibRef
9100
Pomerleau, D.A.[Dean A.],
Neural Network Vision for Robot Driving,
NAVLAB96(Chapter 4).
BibRef
9600
Pomerleau, D.A.[Dean A.],
Neural Network Based Autonomous Navigation,
NAVLAB90(558-614).
BibRef
9000
Pomerleau, D.A.,
Neural Network Perception for Mobile Robot Guidance,
Hingham:
KluwerAcademic, 1993.
ISBN 0-7923-9373-2.
WWW Link.
BibRef
9300
And:
Ph.D.Thesis (CS), February 1992,
BibRef
CMU-CS-TR-92-115.
System: ALVINN. The Neural-Network road follower (ALVINN). Has
run on real highways with light traffic at 55mph.
BibRef
Pomerleau, D.A.,
Understanding Internal Representations through Hidden Unit
Senstivity Analysis,
IAS93(xx-yy).
BibRef
9300
Pomerleau, D.A.,
ALVINN: An Autonomous Land Vehicle in a Neural Network,
CMU-CS-TR-89-107, January 1989.
BibRef
8901
Pomerleau, D.A.[Dean A.],
Visibility Estimation from a Moving Vehicle Using the
RALPH Vision System,
ITSC97(906-911).
IEEE DOI
BibRef
9700
And:
DARPA97(339-344).
BibRef
Crisman, J.D.,
Thorpe, C.E.,
SCARF: A Color Vision System That Tracks Roads and Intersections,
RA(9), 1993, pp. 49-58.
BibRef
9300
Jochem, T.M.,
Pomerleau, D.A.,
Thorpe, C.E.,
Vision-Based Neural Network Road and Intersection Detection
and Traversal,
ARPA96(1365-1371).
BibRef
9600
And:
Vision-Based Neural Network Road and Intersection Detection,
IROS95(xx).
BibRef
And: A1, A2 only:
NAVLAB96(Chapter 5).
Build on ALVINN to track through intersections.
BibRef
Jochem, T.M.[Todd M.],
Vision Based Tactical Driving,
CMU-RI-TR-96-14, January 1996.
BibRef
9601
Ph.D.Thesis.
Add lane changing and intersection traversal to the existing
reliable lane following programs.
BibRef
Jochem, T.M.[Todd M.],
Initial Results in Vision Based Road and Intersection Detection
and Traversal,
CMU-RI-TR-95-21, April 1995.
BibRef
9504
Jochem, T.M.,
Using Virtual Active Vision Tools to Improve Autonomous Driving Tasks,
CMU-RI-TR-94-39, October 1994.
Use the ALVINN system for what it does, but apply geometric transformation
to the imput image and the output steering vector.
BibRef
9410
Jochem, T.M.,
Pomerleau, D.A., and
Thorpe, C.E.,
MANIAC: A Next Generation Neurally Based Autonomous Road Follower,
DARPA93(473-479).
BibRef
9300
And: A1 only:
IAS93(xx-yy).
System: MANIAC.
BibRef
Pomerleau, D.A.[Dean A.],
Baluja, S.[Shumeet],
Non-Intrusive Gaze Tracking Using Artificial Neural Networks,
AAAI-MLCV93
BibRef
9300
And: A2, A1:
CMU-CS-TR-94-102, January 1994.
PS File.
BibRef
Baluja, S.[Shumeet],
Expectation-Based Selective Attention,
Ph.D.Thesis, October 1996.
BibRef
9610
CMU-CS-TR-96-182.
BibRef
Batavia, P.H.[Parag H.],
Pomerleau, D.A.[Dean A.], and
Thorpe, C.E.[Charles E.],
Applying Advanced Learning Algorithms to ALVINN,
CMU-RI-TR-96-31, October 1996.
PDF File.
BibRef
9610
Pomerleau, D.A.,
Gowdy, J., and
Thorpe, C.E.,
Combining Artificial Neural Networks and Symbolic Processing for
Autonomous Robot Guidance,
DARPA92(961-967).
Neural Networks.
System: YARF. YARF plus neural net for road tracking. ALVINN.
BibRef
9200
Sukthankar, R.[Rahul],
Pomerleau, D.A., and
Thorpe, C.E.,
Panacea: An Active Sensor Controller for the ALVINN
Autonomous Driving System,
CMU-RI-TR-93-09, April 1993.
System: ALVINN. Adds steering of the camera to ALVINN, this improves performance
where sharp turns are required.
BibRef
9304
Hancock, J.A., and
Thorpe, C.E.,
ELVIS: Eigenvectors for Land Vehicle Image System,
CMU-RI-TR-94-43, December 1994.
PS File. Based on ALVINN, an attempt to understand why it works.
BibRef
9412
Kluge, K.,
Thorpe, C.E.,
The YARF system for vision-based road following,
MathMod(22), No. 4-7, August-October 1995, pp. 213-233.
Elsevier DOI
BibRef
9508
Earlier:
Intersection Detection in the YARF Road Following System,
IAS93(xx-yy).
BibRef
Earlier:
Explicit Models For Robot Road Following,
NAVLAB90().
BibRef
Kluge, K.,
YARF: An Open-Ended Framework for Robot Road Following,
CMU-CS-TR-93-104, February 1993.
BibRef
9302
Ph.D.Thesis, CS.
The theme of YARF is that using rich models improves performance.
It uses model driven segmentation, model coherence, and data driven
recognition of model changes. Models of road structure are generated
off line.
BibRef
Wallace, R.S.,
Stentz, A.,
Thorpe, C.E.,
Whittaker, W.,
Kanade, T.,
First Results in Robot Road-Following,
IJCAI85(1089-1093).
BibRef
8500
Stentz, A.,
Goto, Y.,
The CMU Navigational Architecture,
DARPA87(440-446).
BibRef
8700
Wallace, R.S.,
Matsuzaki, K.,
Goto, Y.,
Crisman, J.D.,
Webb, J.A.,
Kanade, T.,
Progress in Robot Road-Following,
CRA86(XX-YY).
BibRef
8600
Chapter on Active Vision, Camera Calibration, Mobile Robots, Navigation, Road Following continues in
Obstacle Dectection, Objects on the Road .