The RACE Project - Robustness by Autonomous Competence Enhancement

This paper reports on the aims, the approach, and the results of the European project RACE. The project aim was to enhance the behavior of an autonomous robot by having the robot learn from conceptualized experiences of previous performance, based on initial models of the domain and its own actions in it. This paper introduces the general system architecture; it then sketches some results in detail regarding hybrid reasoning and planning used in RACE, and instances of learning from the experiences of real robot task execution. Enhancement of robot competence is operationalized in terms of performance quality and description length of the robot instructions, and such enhancement is shown to result from the RACE system. 1 Project Aim and Demonstration Domain RACE (Robustness by Autonomous Competence Enhancement) is a project funded by the European Commission under the 7th Framework Programme and running from 12/2011 to 11/2014. The partners are those institutes from which this paper is authored. This short project report summarizes the RACE methodology of working towards achieving these aims, and it sketches main project results, as visible about half a year before the end of the project. The overall aim of RACE as set out in the description of work was to develop an artificial cognitive system, embodied by a service robot, able to build a high-level understanding of the world it inhabits by storing and exploiting appropriate memories of its experiences. Experiences will be recorded internally at multiple levels: high-level descriptions in terms of goals, tasks and behaviours, connected to constituting subtasks, and finally to sensory and actuator skills at the lowest level. In this way, experiences provide a detailed account of how the robot has achieved past goals or how it has failed, and what sensory events have accompanied the activities. Contributions were foreseen in the description of work to advance the state of the art along three lines: 1. robots capable of storing experiences in their memory in terms of multi-level representations connecting actuator and sensory experiences with meaningful high-level structures, 2. methods for learning and generalising from experiences obtained from behaviour in realistically scaled real-world environments, J. Hertzberg (&) M. Günther S. Stock Osnabrück University, Osnabrück, Germany e-mail: joachim.hertzberg@uos.de J. Zhang L. Zhang S. Rockel B. Neumann J. Lehmann Hamburg University, Hamburg, Germany e-mail: zhang@informatik.uni-hamburg.de K. S. R. Dubba A. G. Cohn University of Leeds, Leeds, England A. Saffiotti F. Pecora M. Mansouri Š. Konečný Örebro University, Örebro, Sweden L. S. Lopes M. Oliveira G. H. Lim H. Kasaei V. Mokhtari University of Aveiro, Aveiro, Portugal L. Hotz W. Bohlken HITeC Hamburger Informatik Technologie-Center e. V., Hamburg, Germany