RoboCup 2004: Robot Soccer World Cup VIII

This book constitutes the eight official archival publication devoted to RoboCup. It documents the achivements presented at the RoboCup 2004 Symposium, held in Lisbon, Portugal in June/July 2004 in conjunction with the RoboCup Competition. The 36 revised full papers and 26 revised short papers presented together with 2 award winning papers and an introductory overview went through two rounds of reviewing and post-symposium improvements and were selected from 118 paper submissions. The book is a valuable source of reference and inspiration for R & D professionals active or interested in robotics, distributed artificial intelligence, and it is mandatory reading for the rapidly growing RoboCup community.

RoboCup 2004 Overview.- RoboCup 2004 Overview.- Award Winner Papers.- Map-Based Multiple Model Tracking of a Moving Object.- UCHILSIM: A Dynamically and Visually Realistic Simulator for the RoboCup Four Legged League.- Full Papers.- CommLang: Communication for Coachable Agents.- Turning Segways into Robust Human-Scale Dynamically Balanced Soccer Robots.- A Constructive Feature Detection Approach for Robotic Vision.- Illumination Insensitive Robot Self-Localization Using Panoramic Eigenspaces.- A New Omnidirectional Vision Sensor for Monte-Carlo Localization.- Fuzzy Self-Localization Using Natural Features in the Four-Legged League.- A Behavior Architecture for Autonomous Mobile Robots Based on Potential Fields.- An Egocentric Qualitative Spatial Knowledge Representation Based on Ordering Information for Physical Robot Navigation.- Sensor-Actuator-Comparison as a Basis for Collision Detection for a Quadruped Robot.- Learning to Drive and Simulate Autonomous Mobile Robots.- RoboCupJunior — Four Years Later.- Evolution of Computer Vision Subsystems in Robot Navigation and Image Classification Tasks.- Towards Illumination Invariance in the Legged League.- Using Layered Color Precision for a Self-Calibrating Vision System.- Getting the Most from Your Color Camera in a Color-Coded World.- Combining Exploration and Ad-Hoc Networking in RoboCup Rescue.- Robust Multi-robot Object Localization Using Fuzzy Logic.- Visual Robot Detection in RoboCup Using Neural Networks.- Extensions to Object Recognition in the Four-Legged League.- Predicting Opponent Actions by Observation.- A Model-Based Approach to Robot Joint Control.- Evolutionary Gait-Optimization Using a Fitness Function Based on Proprioception.- Optic Flow Based Skill Learning for a Humanoid to Trap, Approach to, and Pass a Ball.- Learning to Kick the Ball Using Back to Reality.- Cerebellar Augmented Joint Control for a Humanoid Robot.- Dynamically Stable Walking and Kicking Gait Planning for Humanoid Soccer Robots.- An Algorithm That Recognizes and Reproduces Distinct Types of Humanoid Motion Based on Periodically-Constrained Nonlinear PCA.- Three-Dimensional Smooth Trajectory Planning Using Realistic Simulation.- Plug and Play: Fast Automatic Geometry and Color Calibration for Cameras Tracking Robots.- Real-Time Adaptive Colour Segmentation for the RoboCup Middle Size League.- Visual Tracking and Localization of a Small Domestic Robot.- A Vision Based System for Goal-Directed Obstacle Avoidance.- Object Tracking Using Multiple Neuromorphic Vision Sensors.- Interpolation Methods for Global Vision Systems.- A Method of Pseudo Stereo Vision from Images of Cameras Shutter Timing Adjusted.- Automatic Distance Measurement and Material Characterization with Infrared Sensors.- Posters.- A Novel Search Strategy for Autonomous Search and Rescue Robots.- World Modeling in Disaster Environments with Constructive Self-Organizing Maps for Autonomous Search and Rescue Robots.- Approaching Urban Disaster Reality: The ResQ Firesimulator.- Stochastic Map Merging in Rescue Environments.- Orpheus – Universal Reconnaissance Teleoperated Robot.- Navigation Controllability of a Mobile Robot Population.- Sharing Belief in Teams of Heterogeneous Robots.- Formulation and Implementation of Relational Behaviours for Multi-robot Cooperative Systems.- Cooperative Planning and Plan Execution in Partially Observable Dynamic Domains.- Exploring Auction Mechanisms for Role Assignment in Teams of Autonomous Robots.- A Descriptive Language for Flexible and Robust Object Recognition.- Modular Learning System and Scheduling for Behavior Acquisition in Multi-agent Environment.- Realtime Object Recognition Using Decision Tree Learning.- Optimizing Precision of Self-Localization in the Simulated Robotics Soccer.- Path Optimisation Considering Dynamic Constraints.- Analysis by Synthesis, a Novel Method in Mobile Robot Self-Localization.- Robots from Nowhere.- Design and Implementation of Live Commentary System in Soccer Simulation Environment.- Towards a League-Independent Qualitative Soccer Theory for RoboCup.- Motion Detection and Tracking for an AIBO Robot Using Camera Motion Compensation and Kalman Filtering.- The Use of Gyroscope Feedback in the Control of the Walking Gaits for a Small Humanoid Robot.- The UT Austin Villa 2003 Champion Simulator Coach: A Machine Learning Approach.- ITAS and the Reverse RoboCup Challenge.- SPQR-RDK: A Modular Framework for Programming Mobile Robots.- Mobile Autonomous Robots Play Soccer – An Intercultural Comparison of Different Approaches Due to Different Prerequisites.- From Games to Applications: Component Reuse in Rescue Robots.