By Topic

A Robot Ping-Pong Player:Experiments in Real-Time Intelligent Control

Cover Image Copyright Year: 2003
Author(s): Russell L. Andersson
Publisher: MIT Press
Content Type : Books & eBooks
Topics: Computing & Processing
  • Print

Abstract

This tour de force in experimental robotics paves the way toward understanding dynamic environments in vision and robotics. It describes the first robot able to play, and even beat, human ping-pong players.Constructing a machine to play ping-pong was proposed years ago as a particularly difficult problem requiring fast, accurate sensing and actuation, and the intelligence to play the game. The research reported here began as a series of experiments in building a true real-time vision system. The ping-pong machine incorporates sensor and processing techniques as well as the techniques needed to intelligently plan the robot's response in the fraction of a second available. It thrives on a constant stream of new data. Subjectively evaluating and improving its motion plan as the data arrives, it presages future robot systems with many joints and sensors that must do the same, no matter what the task.Contents: Introduction. Robot Ping-Pong. System Design. Real-Time Vision System Robot Controller. Expert Controller Preliminaries. Expert Controller. Robot Ping-Pong Application. Conclusion.A Robot Ping-Pong Player is included in the Artificial Intelligence Series, edited by Patrick Winston and Michael Brady.

  •   Click to expandTable of Contents

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Front Matter

      Russell L. Andersson Page(s): i - xv
      Copyright Year: 2003

      MIT Press eBook Chapters

      This chapter contains sections titled: Half Title, The MIT Press Series in Artificial Intelligence, Title, Copyright, Dedication, Contents, Series Foreword, Preface, Half Title View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Introduction

      Russell L. Andersson Page(s): 1 - 12
      Copyright Year: 2003

      MIT Press eBook Chapters

      This chapter contains sections titled: Introduction to Robots and Their Limitations, Introduction to Robot Ping-Pong, Why Ping-Pong is a Good Problem, A Preview of the Work, Implications and Application Areas, Organization of This Book View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Robot Ping-Pong

      Russell L. Andersson Page(s): 13 - 25
      Copyright Year: 2003

      MIT Press eBook Chapters

      This chapter contains sections titled: Robot Ping-Pong Rules, Comparison to Human Ping-Pong, Ping-Pong Physics View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      System Design

      Russell L. Andersson Page(s): 27 - 38
      Copyright Year: 2003

      MIT Press eBook Chapters

      This chapter contains sections titled: Task Partitioning, Processors and Network, Achieving Accurate Timing, Data Logging Systems, Real-Time Debugger, Summary View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Real-Time Vision System

      Russell L. Andersson Page(s): 39 - 73
      Copyright Year: 2003

      MIT Press eBook Chapters

      This chapter contains sections titled: Current Vision Techniques, Basic Approach to the Vision System, Moment Generator, Stereo and Calibration Techniques, Imaging Dynamic Scene, Three-Dimensional Trajectory Analysis, Vision System Accuracy, Summary View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Robot Controller

      Russell L. Andersson Page(s): 75 - 109
      Copyright Year: 2003

      MIT Press eBook Chapters

      This chapter contains sections titled: Robot Mechanism, Controller Electronics Architecture, Robot Software Architecture, Basic Elements, Trajectory Generation, Trajectory Following: Prediction and Control, Robot Controller Performance, Summary View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Expert Controller Preliminaries

      Russell L. Andersson Page(s): 111 - 129
      Copyright Year: 2003

      MIT Press eBook Chapters

      This chapter contains sections titled: What is an Expert Controller?, Rule-Based Systems, Actual Architecture, Model Data Structure, Summary View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Expert Controller

      Russell L. Andersson Page(s): 131 - 160
      Copyright Year: 2003

      MIT Press eBook Chapters

      This chapter contains sections titled: Functionality Required, Initial Planning, Temporal Updating, Exception Recovery, Learning?, Summary View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Robot Ping-Pong Application

      Russell L. Andersson Page(s): 161 - 203
      Copyright Year: 2003

      MIT Press eBook Chapters

      This chapter contains sections titled: Program Overview, Examination of Program Components, Execution Case Studies, Implementation Limitations, Summary View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Conclusion

      Russell L. Andersson Page(s): 205 - 208
      Copyright Year: 2003

      MIT Press eBook Chapters

      This chapter contains sections titled: Synopsis, Future Research Topics, Man versus Machine View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Robat - The Official Rules

      Russell L. Andersson Page(s): 209 - 211
      Copyright Year: 2003

      MIT Press eBook Chapters

      This tour de force in experimental robotics paves the way toward understanding dynamic environments in vision and robotics. It describes the first robot able to play, and even beat, human ping-pong players.Constructing a machine to play ping-pong was proposed years ago as a particularly difficult problem requiring fast, accurate sensing and actuation, and the intelligence to play the game. The research reported here began as a series of experiments in building a true real-time vision system. The ping-pong machine incorporates sensor and processing techniques as well as the techniques needed to intelligently plan the robot's response in the fraction of a second available. It thrives on a constant stream of new data. Subjectively evaluating and improving its motion plan as the data arrives, it presages future robot systems with many joints and sensors that must do the same, no matter what the task.Contents: Introduction. Robot Ping-Pong. System Design. Real-Time Vision System Robot Controller. Expert Controller Preliminaries. Expert Controller. Robot Ping-Pong Application. Conclusion.A Robot Ping-Pong Player is included in the Artificial Intelligence Series, edited by Patrick Winston and Michael Brady. View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Vision Performance Plots

      Russell L. Andersson Page(s): 213 - 223
      Copyright Year: 2003

      MIT Press eBook Chapters

      This tour de force in experimental robotics paves the way toward understanding dynamic environments in vision and robotics. It describes the first robot able to play, and even beat, human ping-pong players.Constructing a machine to play ping-pong was proposed years ago as a particularly difficult problem requiring fast, accurate sensing and actuation, and the intelligence to play the game. The research reported here began as a series of experiments in building a true real-time vision system. The ping-pong machine incorporates sensor and processing techniques as well as the techniques needed to intelligently plan the robot's response in the fraction of a second available. It thrives on a constant stream of new data. Subjectively evaluating and improving its motion plan as the data arrives, it presages future robot systems with many joints and sensors that must do the same, no matter what the task.Contents: Introduction. Robot Ping-Pong. System Design. Real-Time Vision System Robot Controller. Expert Controller Preliminaries. Expert Controller. Robot Ping-Pong Application. Conclusion.A Robot Ping-Pong Player is included in the Artificial Intelligence Series, edited by Patrick Winston and Michael Brady. View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Robot Performance Plots

      Russell L. Andersson Page(s): 225 - 235
      Copyright Year: 2003

      MIT Press eBook Chapters

      This tour de force in experimental robotics paves the way toward understanding dynamic environments in vision and robotics. It describes the first robot able to play, and even beat, human ping-pong players.Constructing a machine to play ping-pong was proposed years ago as a particularly difficult problem requiring fast, accurate sensing and actuation, and the intelligence to play the game. The research reported here began as a series of experiments in building a true real-time vision system. The ping-pong machine incorporates sensor and processing techniques as well as the techniques needed to intelligently plan the robot's response in the fraction of a second available. It thrives on a constant stream of new data. Subjectively evaluating and improving its motion plan as the data arrives, it presages future robot systems with many joints and sensors that must do the same, no matter what the task.Contents: Introduction. Robot Ping-Pong. System Design. Real-Time Vision System Robot Controller. Expert Controller Preliminaries. Expert Controller. Robot Ping-Pong Application. Conclusion.A Robot Ping-Pong Player is included in the Artificial Intelligence Series, edited by Patrick Winston and Michael Brady. View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Ping-Pong Top Level

      Russell L. Andersson Page(s): 237 - 239
      Copyright Year: 2003

      MIT Press eBook Chapters

      This tour de force in experimental robotics paves the way toward understanding dynamic environments in vision and robotics. It describes the first robot able to play, and even beat, human ping-pong players.Constructing a machine to play ping-pong was proposed years ago as a particularly difficult problem requiring fast, accurate sensing and actuation, and the intelligence to play the game. The research reported here began as a series of experiments in building a true real-time vision system. The ping-pong machine incorporates sensor and processing techniques as well as the techniques needed to intelligently plan the robot's response in the fraction of a second available. It thrives on a constant stream of new data. Subjectively evaluating and improving its motion plan as the data arrives, it presages future robot systems with many joints and sensors that must do the same, no matter what the task.Contents: Introduction. Robot Ping-Pong. System Design. Real-Time Vision System Robot Controller. Expert Controller Preliminaries. Expert Controller. Robot Ping-Pong Application. Conclusion.A Robot Ping-Pong Player is included in the Artificial Intelligence Series, edited by Patrick Winston and Michael Brady. View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Initial Planning and Updating

      Russell L. Andersson Page(s): 241 - 249
      Copyright Year: 2003

      MIT Press eBook Chapters

      This tour de force in experimental robotics paves the way toward understanding dynamic environments in vision and robotics. It describes the first robot able to play, and even beat, human ping-pong players.Constructing a machine to play ping-pong was proposed years ago as a particularly difficult problem requiring fast, accurate sensing and actuation, and the intelligence to play the game. The research reported here began as a series of experiments in building a true real-time vision system. The ping-pong machine incorporates sensor and processing techniques as well as the techniques needed to intelligently plan the robot's response in the fraction of a second available. It thrives on a constant stream of new data. Subjectively evaluating and improving its motion plan as the data arrives, it presages future robot systems with many joints and sensors that must do the same, no matter what the task.Contents: Introduction. Robot Ping-Pong. System Design. Real-Time Vision System Robot Controller. Expert Controller Preliminaries. Expert Controller. Robot Ping-Pong Application. Conclusion.A Robot Ping-Pong Player is included in the Artificial Intelligence Series, edited by Patrick Winston and Michael Brady. View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Flight Path Correction

      Russell L. Andersson Page(s): 251 - 252
      Copyright Year: 2003

      MIT Press eBook Chapters

      This tour de force in experimental robotics paves the way toward understanding dynamic environments in vision and robotics. It describes the first robot able to play, and even beat, human ping-pong players.Constructing a machine to play ping-pong was proposed years ago as a particularly difficult problem requiring fast, accurate sensing and actuation, and the intelligence to play the game. The research reported here began as a series of experiments in building a true real-time vision system. The ping-pong machine incorporates sensor and processing techniques as well as the techniques needed to intelligently plan the robot's response in the fraction of a second available. It thrives on a constant stream of new data. Subjectively evaluating and improving its motion plan as the data arrives, it presages future robot systems with many joints and sensors that must do the same, no matter what the task.Contents: Introduction. Robot Ping-Pong. System Design. Real-Time Vision System Robot Controller. Expert Controller Preliminaries. Expert Controller. Robot Ping-Pong Application. Conclusion.A Robot Ping-Pong Player is included in the Artificial Intelligence Series, edited by Patrick Winston and Michael Brady. View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Acceleration Limit Correction

      Russell L. Andersson Page(s): 253 - 260
      Copyright Year: 2003

      MIT Press eBook Chapters

      This tour de force in experimental robotics paves the way toward understanding dynamic environments in vision and robotics. It describes the first robot able to play, and even beat, human ping-pong players.Constructing a machine to play ping-pong was proposed years ago as a particularly difficult problem requiring fast, accurate sensing and actuation, and the intelligence to play the game. The research reported here began as a series of experiments in building a true real-time vision system. The ping-pong machine incorporates sensor and processing techniques as well as the techniques needed to intelligently plan the robot's response in the fraction of a second available. It thrives on a constant stream of new data. Subjectively evaluating and improving its motion plan as the data arrives, it presages future robot systems with many joints and sensors that must do the same, no matter what the task.Contents: Introduction. Robot Ping-Pong. System Design. Real-Time Vision System Robot Controller. Expert Controller Preliminaries. Expert Controller. Robot Ping-Pong Application. Conclusion.A Robot Ping-Pong Player is included in the Artificial Intelligence Series, edited by Patrick Winston and Michael Brady. View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      References

      Russell L. Andersson Page(s): 261 - 267
      Copyright Year: 2003

      MIT Press eBook Chapters

      This tour de force in experimental robotics paves the way toward understanding dynamic environments in vision and robotics. It describes the first robot able to play, and even beat, human ping-pong players.Constructing a machine to play ping-pong was proposed years ago as a particularly difficult problem requiring fast, accurate sensing and actuation, and the intelligence to play the game. The research reported here began as a series of experiments in building a true real-time vision system. The ping-pong machine incorporates sensor and processing techniques as well as the techniques needed to intelligently plan the robot's response in the fraction of a second available. It thrives on a constant stream of new data. Subjectively evaluating and improving its motion plan as the data arrives, it presages future robot systems with many joints and sensors that must do the same, no matter what the task.Contents: Introduction. Robot Ping-Pong. System Design. Real-Time Vision System Robot Controller. Expert Controller Preliminaries. Expert Controller. Robot Ping-Pong Application. Conclusion.A Robot Ping-Pong Player is included in the Artificial Intelligence Series, edited by Patrick Winston and Michael Brady. View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Index

      Russell L. Andersson Page(s): 269 - 275
      Copyright Year: 2003

      MIT Press eBook Chapters

      This tour de force in experimental robotics paves the way toward understanding dynamic environments in vision and robotics. It describes the first robot able to play, and even beat, human ping-pong players.Constructing a machine to play ping-pong was proposed years ago as a particularly difficult problem requiring fast, accurate sensing and actuation, and the intelligence to play the game. The research reported here began as a series of experiments in building a true real-time vision system. The ping-pong machine incorporates sensor and processing techniques as well as the techniques needed to intelligently plan the robot's response in the fraction of a second available. It thrives on a constant stream of new data. Subjectively evaluating and improving its motion plan as the data arrives, it presages future robot systems with many joints and sensors that must do the same, no matter what the task.Contents: Introduction. Robot Ping-Pong. System Design. Real-Time Vision System Robot Controller. Expert Controller Preliminaries. Expert Controller. Robot Ping-Pong Application. Conclusion.A Robot Ping-Pong Player is included in the Artificial Intelligence Series, edited by Patrick Winston and Michael Brady. View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Back Matter

      Russell L. Andersson Page(s): 276
      Copyright Year: 2003

      MIT Press eBook Chapters

      This tour de force in experimental robotics paves the way toward understanding dynamic environments in vision and robotics. It describes the first robot able to play, and even beat, human ping-pong players.Constructing a machine to play ping-pong was proposed years ago as a particularly difficult problem requiring fast, accurate sensing and actuation, and the intelligence to play the game. The research reported here began as a series of experiments in building a true real-time vision system. The ping-pong machine incorporates sensor and processing techniques as well as the techniques needed to intelligently plan the robot's response in the fraction of a second available. It thrives on a constant stream of new data. Subjectively evaluating and improving its motion plan as the data arrives, it presages future robot systems with many joints and sensors that must do the same, no matter what the task.Contents: Introduction. Robot Ping-Pong. System Design. Real-Time Vision System Robot Controller. Expert Controller Preliminaries. Expert Controller. Robot Ping-Pong Application. Conclusion.A Robot Ping-Pong Player is included in the Artificial Intelligence Series, edited by Patrick Winston and Michael Brady. View full abstract»