Integration of sensing and motion planning plays a crucial role in autonomous robot operation. We present a framework for sensor-based robot motion planning that uses learning to handle arbitrarily configured sensors and robots. The theoretical basis of this approach is the concept of the Perceptual Control Manifold that extends the notion of the robot configuration space to include sensor space. To overcome modeling uncertainty, the Topology Representing Network algorithm is employed to learn a representation of the Perceptual Control Manifold. By exploiting the topology preserving features of the neural network, a diffusion-based path planning strategy leads to flexible obstacle avoidance. The practical feasibility of the approach is demonstrated on a pneumatically driven robot arm (SoftArm) using visual sensing.
|
1560
|
Robot Motion Planning
– Latombe
- 1991
|
|
483
|
The organization of behavior
– Hebb
- 1949
|
|
420
|
Quantization
– Gray, Neuhoff
- 1998
|
|
362
|
A new approach to visual servoing in robotics
– Espiau, Chaumette, et al.
- 1992
|
|
172
|
Neural-gas Network for Vector Quantization and Its Application to Time-series Prediction
– Martinetz, Berkovich, et al.
- 1993
|
|
128
|
Topology representing networks
– Martinetz, Schulten
- 1994
|
|
112
|
Visual tracking of a moving target by a camera mounted on a robot: a combination of vision and control
– Papanikolopoulos, Khosla, et al.
- 1993
|
|
109
|
Dynamic sensor-based control of robots with visual feedback
– Weiss, Sanderson, et al.
- 1987
|
|
105
|
Neural computation and self-organizing maps: An introduction
– Ritter, Martinetz, et al.
- 1992
|
|
99
|
A survey of sensor planning in computer vision
– Tarabanis, Allen, et al.
- 1995
|
|
88
|
A neural-gas network learns topologies
– Martinetz, Schulten
- 1991
|
|
43
|
Weighted selection of image features for resolved rate visual feedback control
– Feddema, Lee, et al.
- 1991
|
|
41
|
Active, uncalibrated visual servoing
– Yoshimi, Allen
- 1994
|
|
31
|
Synopsis of recent progress on camera calibration for 3-d machine vision. The Robotics Review
– Tsai
- 1989
|
|
31
|
Analysis of a simple self-organizing process
– Kohonen
- 1982
|
|
30
|
Implementation of self-organizing neural networks for visuo-motor control of an industrial robot
– Walter, Schulten
- 1993
|
|
26
|
Real-time feature tracking and projective invariance as a basis for hand-eye coordination
– Hager
- 1994
|
|
16
|
Nonholonomic camera-space manipulation
– Skaar, Yalda-Mooshabad, et al.
- 1992
|
|
11
|
Neural network control of a pneumatic robot arm
– Hesselroth, Sarkar, et al.
- 1994
|
|
10
|
Optimizing hand/eye configuration for visual-servo systems
– Sharma, Hutchinson
- 1995
|
|
4
|
Active vision for visual servoing: A review
– Sharma
- 1994
|
|
3
|
A framework for robot motion planning with sensor constraints
– Sharma, Sutanto
- 1997
|
|
3
|
Unifying configuration space and sensor space for vision-based motion planning
– Sharma, Sutanto
- 1996
|
|
2
|
Planning a dynamic trajectory via path finding in discretized phase space
– Ritter, Schulten
- 1987
|
|
1
|
A survey of kinematic calibration
– Holierbach
- 1989
|
|
1
|
Global perromance evaluation of image features for visual servo control
– Sutanto, Sharma
- 1996
|
|
1
|
Topology representing maps and brain function
– Schulten, Zeller
- 1996
|
|
1
|
Topology representing network in robotics
– Sarkar, Schulten
- 1995
|
|
