Using physical analogies when solving computational problems is not uncommon. The Electric Field Approach is such an analogy using potential fields for describing the situation in a robotic soccer match and for proposing the next step in optimizing the situation. The approach was developed and implemented during the summer of 2000 and was later used and tested during the fourth Robot Soccer World Cup in Melbourne, Australia. The results of the games prove that the approach is applicable in this narrow but interesting domain, combining artificial intelligence and robotics…
Contents
1 INTRODUCTION
1.1 BACKGROUND
1.1.1 The Electric Field Approach
1.1.2 The RoboCup Domain
1.1.3 AIBO
1.2 PROBLEM DESCRIPTION
1.3 RESULTS
1.4 TERMS AND ABBREVIATIONS
1.5 OUTLINE OF THE THESIS
2 THE TEAM SWEDEN EFFORT IN ROBOCUP
2.1 ROBOCUP
2.1.1 Purpose of RoboCup
2.1.2 History
2.1.3 The Leagues
2.1.4 Sony Legged Robot League
2.2 TEAM SWEDEN
2.2.1 History
2.2.2 Members
3 THE ELECTRIC FIELD APPROACH
3.1 INTRODUCTION
3.2 STATIC CHARGES
3.3 DYNAMIC CHARGES
3.3.1 Undirected charges
3.3.2 Agent-oriented charges
3.3.3 Environment-oriented charges
3.4 THE PROBE
3.5 BEHAVIORS
3.6 BEHAVIOR PREDICTION
3.7 THE EVALUATION LOOP
4 THE EFA AS IMPLEMENTED IN THE REACTIVE PLANNER MODULE
4.1 SOFTWARE ARCHITECTURE OF TEAM SWEDEN 2000
4.1.1 Global Map
4.1.2 Perceptual Anchoring Module
4.1.3 Hierarchical Behavior Module
4.1.4 Commander
4.2 THE REACTIVE PLANNER MODULE
4.2.1 Inputs and outputs (communication with other modules)
4.2.2 Static Charge Configuration
4.2.3 Dynamic Charge Configuration
4.2.4 Available Behaviors
4.2.5 The Evaluation Loop
5 EVALUATION OF THE ELECTRIC FIELD APPROACH
5.1 TESTING THE REACTIVE PLANNER MODULE
5.1.1 Prototypes
5.1.2 Tools
5.1.3 Debugging
5.1.4 Calibration
5.2 PERFORMANCE OF TEAM SWEDEN
5.2.1 The matches
5.2.2 RoboCup Challenge 1
5.2.3 RoboCup Challenge 2
5.2.4 RoboCup Challenge 3
5.3 OTHER STRATEGIES
5.3.1 The matches
5.3.2 The RoboCup Challenge
6 DISCUSSION
6.1 THE TEAM SWEDEN REQUIREMENTS
6.1.1 Scientific value
6.1.2 Generality
6.1.3 Effectiveness
6.1.4 Robustness
6.2 OTHER ATTRIBUTES
6.2.1 Configurability
6.3 SIMILAR APPROACHES
7 CONCLUSION
7.1 THE ELECTRIC FIELD APPROACH IN THE ROBOCUP DOMAIN
7.2 THE ELECTRIC FIELD APPROACH AS AUTONOMOUS AGENT CONTROL
7.3 STRENGTHS AND WEAKNESSES
7.4 FUTURE WORK
ACKNOWLEDGEMENTS
APPENDIX A
APPENDIX B
Author: John Johansson
Source: Blekinge Institute of Technology
Download URL 2: Visit Now