Abstract:
The vision subsystem of an autonomous mobile robot was created using a form of evolutionary computation known as genetic programming. In this form, individuals are algorithms represented as parse trees. The primitives of the representation were specifically chosen to capture the spirit of existing vision algorithms. Thus, the evolutionary computation can be viewed as searching roughly the same space that researchers search when developing their system using trial and error.
Citations
|
713
|
Genetic Programming
– Koza
- 1992
|
|
118
|
Stereo vision for planetary rovers: Stochastic modeling to near realtime implementation
– Matthies
- 1992
|
|
76
|
Obstacle detection for unmanned ground vehicles: A progress report
– Matthies, Kelly, et al.
- 1996
|
|
54
|
Evolving visually guided robots
– Cliff, Husbands, et al.
- 1992
|
|
43
|
I.: Appearance-based obstacle detection with monocular color vision
– Ulrich, Nourbakhsh
|
|
41
|
W.: Visually-guided obstacle avoidance in unstructured environments
– Lorigo, Brooks, et al.
- 1997
|
|
40
|
Evolving visual routines
– Johnson, Maes, et al.
- 1994
|
|
40
|
PADO: A new learning architecture for object recognition
– Teller, Veloso
- 1997
|
|
39
|
Real-Time Obstacle Avoidance Using Central Flow Divergence and
– Coombs, Herman, et al.
|
|
32
|
Analysis of Adaption and Environment
– Horswill
- 1995
|
|
21
|
Stereo perception and dead reckoning for a prototype lunar rover
– Krotkov, Hebert, et al.
- 1995
|
|
10
|
The Simulated Evolution of Robot Perception
– Martin
- 2001
|
|
8
|
On the evolution of interest operators using genetic programming
– Ebner
- 1998
|
|
8
|
Property Mapping: A simple technique for mobile robot programming
– Nourbakhsh
- 2000
|
|
7
|
Visual Obstacle Avoidance using Genetic Programming: First Results
– Martin
- 2001
|
|
4
|
DARPA MARS program research progress
– Moravec
- 2000
|
|
4
|
A sighted robot: Can we ever build a robot that really doesn’t hit (or fall into) obstacles? The robotics practitioner
– Nourbakhsh
- 1996
|