Robots that Change Their World: Inferring Goals from Semantic Knowledge

A growing body of literature shows that endowing a mobile robot with semantic knowledge, and with the ability to reason from this knowledge, can greatly increase its capabilities. In this paper, we explore a novel use of semantic knowledge: we encode information about how things should be, or norms, to allow the robot to infer deviations from these norms and to generate goals to correct these deviations. For instance, if a robot has semantic knowledge that perishable items must be kept in a refrigerator, and it observes a bottle of milk on a table, this robot will generate the goal to bring that bottle into a refrigerator. Our approach provides a mobile robot with a limited form of goal autonomy: the ability to derive its own goals to pursue generic aims. We illustrate our approach in a full mobile robot system that integrates a semantic map, a knowledge representation and reasoning system, a task planner, as well as standard perception and navigation routines.

[1]  Koen V. Hindriks,et al.  Satisfying Maintenance Goals , 2007, DALT.

[2]  Wolfram Burgard,et al.  From labels to semantics: an integrated system for conceptual spatial representations of indoor environments for mobile robots , 2007 .

[3]  Lars Karlsson,et al.  Conditional progressive planning under uncertainty , 2001, IJCAI.

[4]  Alessandro Saffiotti,et al.  Seamless integration of robots and tiny embedded devices in a PEIS-Ecology , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[5]  Alessandro Saffiotti,et al.  Robot task planning using semantic maps , 2008, Robotics Auton. Syst..

[6]  Robert M. MacGregor,et al.  The Loom Knowledge Representation Language. , 1987 .

[7]  Alessandro Saffiotti,et al.  The PEIS-Ecology project: Vision and results , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[8]  James J. Little,et al.  Curious George: An attentive semantic robot , 2008, Robotics Auton. Syst..

[9]  Frank Dellaert,et al.  Semantic Modeling of Places using Objects , 2007, Robotics: Science and Systems.

[10]  Alessandro Saffiotti,et al.  Autonomous functional configuration of a network robot system , 2008, Robotics Auton. Syst..

[11]  Alessandro Saffiotti,et al.  Semantic Knowledge-Based Execution Monitoring for Mobile Robots , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[12]  Dejan Pangercic,et al.  Web-enabled Robots -- Robots that Use the Web as an Information Resource , 2011, ICRA 2011.

[13]  Federico Pecora,et al.  A Constraint-Based Approach for Plan Management in Intelligent Environments , 2010, Cognitive Robotics.

[14]  Mehdi Dastani,et al.  What Is a Normative Goal?: Towards Goal-Based Normative Agent Architectures , 2002, RASTA.

[15]  Joachim Hertzberg,et al.  3D Mapping with Semantic Knowledge , 2005, RoboCup.

[16]  Cipriano Galindo,et al.  Multiple Abstraction Hierarchies for Mobile Robot Operation in Large Environments , 2007 .

[17]  Masahiro Fujita,et al.  An ethological and emotional basis for human-robot interaction , 2003, Robotics Auton. Syst..

[18]  Guido Boella,et al.  An Architecture for Normative Reactive Agents , 2002, PRIMA.

[19]  Diego Calvanese,et al.  The Description Logic Handbook , 2007 .

[20]  Cipriano Galindo,et al.  Multi-hierarchical semantic maps for mobile robotics , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[21]  Thomas Eiter,et al.  Maintenance goals of agents in a dynamic environment: Formulation and policy construction , 2008, Artif. Intell..

[22]  Derek Long,et al.  Alarms: An Implementation of Motivated Agency , 1995, ATAL.

[23]  Benjamin Kuipers,et al.  Modeling Spatial Knowledge , 1978, IJCAI.

[24]  Ivan Serina,et al.  MADbot: A Motivated and Goal Directed Robot , 2005, AAAI.