A Polar Neural Map for Mobile Robot Navigation

1
A Polar Neural Map forMobile Robot Navigation

• Michail G. Lagoudakis
• Department of Computer Science
• Duke University

Anthony S. Maida Center for Advanced Computer
Studies University of Southwestern Louisiana
Third International Conference on Cognitive and
Neural Systems May 26-29, 1999 - Boston
University
2
Animal Navigation

• Maximum Gradient Following

The Planarian reaches the food by testing the
water and by moving toward the direction where
chemical stimulation increases.
3
Robot Navigation
Build a model of the robots environment.
Simulate diffusion from the target position.
4
Navigation Landscape
Find a path from any initial position to the
target by steepest ascent (maximum gradient
following) on the navigation landscape.
5
Neural Maps for Path Planning

• A neural map is a localized neural
  representation of signals in the outer world
  Amari, 1989
• The processing units are topologically ordered
  over the configuration space of the robot.

Uniform unit topologies
Path planning with neural maps
6
Neural Map Diffusion Dynamics

• External (Sensory) Input
• Lateral Connections
• Nonlinear Activation Function
• Activation Update Equation

7
Path Planning Example 1
Target (middle) and initial position (upright).
Obstacle-free path from initial position to the
target.
8
Path Planning Example 1
50 x 50 rectangular neural map
Activation landscape formed on the neural map at
equilibrium.
9
Path Planning Example 1
Activation diffusion on the neural map.
Navigation map for the given target.
10
Path Planning Example 2
Initial position (middle) and three targets.
Obstacle-free path to the closest target.
11
Path Planning Example 2
50 x 50 rectangular neural map
Activation landscape formed on the neural map at
equilibrium.
12
Path Planning Example 2
Activation diffusion on the neural map.
Navigation map for the given targets.
13
Mobile Robot Navigation

• Global
• Map-Based
• Deliberative
• Slow

• Local
• Sensory-Based
• Reactive
• Fast

14
Nomad 200 Mobile Robot

• Nonholonomic Mobile Base
• Zero Gyro-Radius
• Max Speeds 24 in/sec, 60 deg/sec
• Diameter 21 in, Height 31 in
• Pentium-Based Master PC
• Linux Operating System
• Full Wireless 1.6 Mbps Ethernet
• 16 Sonar Ring (6 in - 255 in)
• 20 Bump Sensors

15
Neural Maps for Local Navigation

• No global information!
• Sensory information
• Egocentric view
• Circular range
• Decaying resolution
• A neural map can be used if adapted appropriately
  to account for the sensory and motor
  capabilities of the robot!

16
Bad and Good Organization
Rectangular Topology
Polar Topology
17
The Polar Neural Map

• Represents the local space.
• Resembles the distribution of sensory data.
• Provides higher resolution closer to the robot.
• Conventions
• Inner Ring Robot Center
• Outer Ring Target Direction
• Robots Working Memory

18
System Architecture
19
Incremental Path Planning (1)
Target
Obstacle
Sonar Range
Five sonars detect the L-shaped obstacle.
The robot is on the way to the target.
20
Incremental Path Planning (2)
Areas of the map characterized as obstructed by
the sonar data.
The polar neural map superimposed.
21
Incremental Path Planning (3)
The target is specified at the periphery.
Obstacle Units
22
Incremental Path Planning (4)
Angular Displacement
Path of maximum activation propagation.
Radial Displacement
23
Navigation in a Simulated World
24
(Noisy) Sonar Readings
25
U-Shaped Obstacle
Target
Path
Sonar Range
26
Cluttered Environment
Finish
Start
Translational Velocity
Control Input
Rotational Velocity
Control Steps
27
Navigation in the Real World (1)
Start
Finish
Avoiding a walking person.
28
Navigation in the Real World (2)
Start
Finish
The target is distant in the direction of the
arrow.
29
Contributions

• The Polar Neural Map
• Working memory of the robot holding local (in
  spatial and temporal sense) information.
• A complete Local Navigation System
• Implemented and tested on a Nomad 200 robot.

Further Information

• Neural Maps for Mobile Robot Navigation
• Lagoudakis and Maida, IEEE Intl Conf on Neural
  Networks, 1999.
• Mobile Robot Local Navigation with a Polar Neural
  Map
• M. Lagoudakis, M.Sc. Thesis, University of SW
  Louisiana, 1998.

30
Future Work

• Polar and Logarithmic Map
• Self-Organization of the Neural Map
• Explore analogies with the human vision system

Acknowledgments
USL Robotics and Automation Lab Prof. Kimon
P. Valavanis Lilian-Boudouri Foundation
(Greece)