Robotics applications of visionbased action selection

1
Robotics applications of vision-based action
selection

• Master Project
• Matteo de Giacomi

2
Contents

• Introduction
• Controller Architecture
• Webots implementation
• Visual System
• Amphibot II implementation
• Conclusion

3
Introduction

• Project Objectives
• Related works
• - Used robots

4
Project Objectives

• Use Stereo Vision to make a real robot
  reactively

• Avoid Obsacles
• Flee from Predators
• Follow Preys

5
Related Works

• Schema-based architecture Arkin
• Potential Field Andrews Kathib
• Steering Reynolds
• Subsumption architecture Brooks

6
Used Robots

• Amphibot II
• 8 body elements
• Salamandra
• body elements and legs elements

Control of Speed through a Drive signal and of
the direction through a Turn signal
7
Controller Architecture

• Overview
• Behavioral Constants
• - Obstacle Avoidance

8
Controller Architecture
DRIVE,TURN
9
Behavioral Constants

• Reactivity (min time between two different
  behaviors)

• Panic (when stuck, time after that the robot
  starts moving randomly)

• Confidence (min distance to an object
• before collision danger is triggered)

• Daring (min distance the robot can approach the
  predator)
• Fear (time in fleeing state after having lost eye
  contact with the predator)

• Persistence (while a prey is lost, time in search
• state before giving up)

10
Obstacle Avoidance (1)

• Avoid Static Obstacles
• Avoid Sudden obsacles (ex. foot)
• Detect Dead-ends (requiring the implementation
  of Backward locomotion)

11
Obstacle Avoidance (2)

• Avoidance is triggered if an obstacle is too
  close (see confidence)

In a clutted environment, one tends to approach
obstacles more than in an open space

• Confidence varies according to an estimation of
  obstacle density

12
Webots Implementation

• - action selection
• - influence of behavioral constants

13
Interaction between behaviors
Video obstacle avoidance, prey and predator
action selection
14
Influence of behavioral constants

• When both a prey and a predator are detected Fear
  and Daring affect robot behavior

15
Visual System

• Distance Measures Analysis
• Prey and Predator Tracking

16
Input Mapping (1)
1

m
Input mxn distance grid
1

Output Polar distance map. Sectors distance
estimation minima between the cells of every
column (pessimist approach)

n
17
Input Mapping (2)

• Issue Filmed area depends on robots head
  position

• Solution Knowing Cam Angle and Angular Speed
  (depending on Turn and Drive) Map Camera Field
  on Visual Field

18
Input Mapping (3)
Video example of depth Map generation
19
Prey and Predator Tracking (1)

• Shape recognition

• Prey
• small circle
• Turn so that circle centre is set in front of the
  robot
• Stop when sufficiently close
• Predator
• big circle
• Turn away as fast as possible

20
Prey and Predator Tracking (2)

• Circular Hough Transform

• Left-Right Size check

21
Prey and Predator Tracking (3)

• Evaluate target expected size according to
  distance and compare with measured size

22
Amphibot II implementation

• Introduction
• Battery charge influence
• Obstacle avoidance results

23
Introduction

• Differences from webots
• Cameras range 60 instead of 120
• Input more noisy
• Frame rate is smaller
• Drive Signal Its relation with amplitude and
  frequency critically depends on the environment
  and the used hardware

24
Battery charge influence

• Estimation or measure of battery charge
  impossible, world rotation phase in mapping must
  be skipped

25
Results
Video setup presentation, obstacle avoidance
26
Conclusion
- Results - Further Works
27
Results

• Stereo-Vision system
• Effective for both obstacle avoidance and target
  recognition

• Behavior
• Scalable (a joystick was added as a new behavior
  with minimal variations)
• Quick, memory inexpensive
• Natural parameters
• One architecture, many behaviors
• Several parameters to trim, aestetic criteria

28
Further works

• Camera-to-Wold mapping can be improved?
• How to define parameter values?
• Possible addition of a planner?
• How can the visual system cope with a water
  enviroment?
• Robot gait may adapt to the type of surface?

29
THE END

• Thank you!
• Any question?

30
(No Transcript)
31
Amphibots Input Mapping

• Polar map containing 19 sectors
• Robot kept on place while oscillating parallel to
  a wall

32
Obstacle Avoidance
Video Dead-end detection
33
Prey Cornering Behavior
Video obstacle is ignored in case a prey is
present (behavior feedback)
34
Turning vs. Reactivity

• Tracking in a webots simulation
• Low Reactivity produces an unnatural behavior
• High Reactivity makes the robot react too slowly

35
Turning Radius vs. Battery charge
Video turning performance along time with
constant drive and turn
36
Drive Signal vs. Amplitude and Frequency
37
Drive vs. Obstacle distance
38
Bonus Hough Transform

• Video circle tracking