Wandering Standpoint Algorithm

1
Wandering Standpoint Algorithm
2
Wandering Standpoint Algorithm for local path
planning

• Description
• Local path planning algorithm.
• Required
• Local distance sensor.
• Algorithm
• Try to reach goal from start in direct line.
• When encountering an obstacle, measure avoidance
  angle for turning left and for turning right,
  turn to smaller angle.
• Continue with boundary-following around the
  object, until goal direction is clear again.

3

• Variant on robot
• Variant with existing map or vision from ceiling

• Try to reach goal from start in direct line.

4

• Mapping
• algorithms

5
Mapping

• Mapping an unknown environment is similar to the
  maze problem
• However, maze is very simple
• fixed size cells
• only 90º angles
• Now let us look at general environments

6
Mapping ideas

• Explore unknown environment
• Use infra-red PSD and infra-red proxy sensors
  only
• Apply DistBug algorithm for wall following once
  an obstacle is encountered
• Enter sensor measurement data in map
• Use visibility graph with configuration space
  representation

7
Grid or no grid?

• Exploring cells of the map grid based

8
continued
Exploring obstacles in the map - general maps,
shapes, no grid.
9
Mapping based on Grids
This slide explains how to use grids to draw the
map based on sensor information and actions
executed.
10
This slide explains how to use grids to draw the
map based on sensor information and actions
executed.

• Such parts can be next fixed based on general
  predetermined knowledge of the nature of walls,
  obstacles and sizes.

11
Fixing errors from measurements
The smaller the error the more accurate the map
12
Experimental evaluation of errors for your
labyrinths
13
(No Transcript)
14
You should collect these kinds of data for your
robot environment of the demo. Think in advance
where our robots will be demonstrated. Deans
attrium? Near elevators? Not the lab!!
15
DistBug Algorithm
16
DistBug Algorithm

• Description
• Algorithm combining local planning with global
  information,
• guarantees convergence.
• Required
• Local sensor data plus global information.
• Algorithm
• Similar to wandering standpoint algorithm,
• but boundary-following stops only if goal is
  directly reachable
• or if future hit-point with next obstacle would
  be closer to goal.
• This global information together with detection
  of unreachable goal if robot has turned 360
  guarantees convergence.
• Although this algorithm has very nice theoretical
  properties, it is not always usable in practice,
  since it requires global information in the form
  of path intersection points of future possible
  collision points with objects.

17
Conclusions and to think about

1. Search algorithms. Now that you understand one
   application of search, go read again the slides
   about search algorithms and think how they can be
   used in applications from last few sets of
   slides.
2. Fitness function. What can be the cost (fitness)
   functions?
3. Mapping. Think about other mapping algorithms.
   Can you use randomness?

18
(No Transcript)