Towards Programming Tools for Robots That Integrate Probabilistic Computation and Learning

By Sebastian Thrun.

Abstract: This paper describes a programming language extension of C++, called CES, specifically targeted towards mobile robot control. CES's design is motivated by a recent series of successful probabilistic methods for mobile robot control, with the goal of facilitating the development of such probabilistic software in future robot applications. CES extends C++ by two ideas: Computing with probability distributions, and built-in mechanisms for learning from examples as a new means of programming. An example program, used to control a mail-delivering robot with gesture commend interface, illustrates that CES may reduce the code development by two orders of magnitude. CES differs from other special-purpose programming languages in the field, which typically emphasize concurrency and real-time/event-driven processing.

Available for download in

• gzipped Postscript (801,262 bytes) and
• low-res PDF (850,790 bytes).

@INPROCEEDINGS{Thrun00b,
  AUTHOR         = {Thrun, S.},
  TITLE          = {Towards Programming Tools for Robots That Integrate 
                    Probabilistic Computation and Learning},
  YEAR           = {2000},
  BOOKTITLE      = {Proceedings of the IEEE International Conference on 
                    Robotics and Automation (ICRA)},
  PUBLISHER      = {IEEE},
  ADDRESS        = {San Francisco, CA}
}