GOLEX - Bridging the Gap between Logic (GOLOG) and a Real Robot

The control of mobile robots acting autonomously in the real world is one of the long-term goals of the field of artificial intelligence. So far the field lacks methods bridging the gap between the sophisticated symbolic techniques to represent and reason about action and more and more reliable low-level robot control and navigation systems. In this paper we present GOLEX, an execution and monitoring system for the logic-based action language GOLOG and the complex and distributed RHINO control software which operates on RWI B21 and B14 mobile robots. GOLEX provides the following features: it maps abstract primitive actions into low-level commands of the robot control system, thus allowing the user to concentrate on the application rather than the inner workings of the robot; it monitors the execution of the primitive GOLOG actions, making it possible to detect simple execution failures and timeouts; and it includes means to deal with sensing and user input and to continue the operation appropriately. We present two different real-world applications in which GOLEX successfully operated a mobile robot in dynamic and even unstructured environments. These results suggest that the time is ripe for using symbolic action languages for mobile robot applications.

[1]  Giuseppe De Giacomo,et al.  Execution Monitoring of High-Level Robot Programs , 1998, KR.

[2]  Raymond Reiter,et al.  The Frame Problem in the Situation Calculus: A Simple Solution (Sometimes) and a Completeness Result for Goal Regression , 1991, Artificial and Mathematical Theory of Computation.

[3]  Raymond Reiter,et al.  Sequential, Temporal GOLOG , 1998, KR.

[4]  Wolfram Burgard,et al.  The Interactive Museum Tour-Guide Robot , 1998, AAAI/IAAI.

[5]  Nils J. Nilsson,et al.  Shakey the Robot , 1984 .

[6]  Wolfram Burgard,et al.  The Mobile Robot Rhino , 1995, SNN Symposium on Neural Networks.

[7]  Kurt Konolige.  COLBERT: A Language for Reactive Control in Sapphira , 1997, KI.

[8]  Wolfram Burgard,et al.  Estimating the Absolute Position of a Mobile Robot Using Position Probability Grids , 1996, AAAI/IAAI, Vol. 2.

[9]  Michael Beetz,et al.  Improving Robot Plans During Their Execution , 1994, AIPS.

[10]  J. McCarthy.  Situations, Actions, and Causal Laws , 1963 .

[11]  Hector J. Levesque,et al.  Reasoning about Concurrent Execution Prioritized Interrupts, and Exogenous Actions in the Situation Calculus , 1997, IJCAI.

[12]  Oren Etzioni,et al.  PRODIGY: an integrated architecture for planning and learning , 1991, SGAR.

[13]  Hector J. Levesque,et al.  An Incremental Interpreter for High-Level Programs with Sensing , 1999 .

[14]  Wolfgang Bibel,et al.  Let's Plan It Deductively! , 1997, IJCAI.

[15]  Fangzhen Lin,et al.  State Constraints Revisited , 1994, J. Log. Comput..

[16]  Wolfram Burgard,et al.  Map learning and high-speed navigation in RHINO , 1998 .

[17]  Wolfram Burgard,et al.  The Museum Tour-Guide Robot RHINO , 1988, AMS.

[18]  Wolfram Burgard,et al.  The dynamic window approach to collision avoidance , 1997, IEEE Robotics Autom. Mag..

[19]  Karen Zita Haigh,et al.  High-level planning and low-level execution: towards a complete robotic agent , 1997, AGENTS '97.

[20]  Hector J. Levesque,et al.  GOLOG: A Logic Programming Language for Dynamic Domains , 1997, J. Log. Program..

[21]  Gerhard Lakemeyer,et al.  On sensing and off-line interpreting in GOLOG , 1999 .