Improvement in Service Robot’s Interaction through Case Based Reasoning Catalina Roncancio , Jose L. Rodr´ ıguez, Eduardo Zalama, Jaime G´ omez G-B Abstract— In order to enable tight interaction and close collaboration between human and service robots it is necessary that robots imitate the cognitive mechanisms of the brain and their role in competent activity control. That goal can only be achieved if robots are capable of observing their environment, reasoning about it, and autonomously deciding the most appropriate action in a given situation. We present a possible application in this broad area: “Sacarino” is a service robot desingned to work as bellboy in a hotel environment as part of the ROSETEL project. In order to tackle the challenge of learning by interaction we define: (i) the scenarios in which our agent have to work, (ii) its prior knowledge in an episodic memory module to be used in a prime dialog interaction, and (iii) the proper architecture that will support intelligent behaviour suitable for the control of our robot. We will use frameworks like JCOLOBRI (Cases and Ontology Libraries Integration for Building Reasoning Infrastructures) to define the agent’s memory structure, taking a deeper look into the episodic memory of the system. I. I NTRODUCTION Our current research interest is the development of a ser- vice robot that will safely coexist with humans, interactively communicate with them and successfully cooperate [1]. For this reason it is necessary that robots imitate the cognitive mechanisms of the brain and their role in competent activity control. The goal of our work is to provide reliable and highly integrated robotic platform which on the one hand allow the implementation and tests of various research and on the other hand the realization of service tasks in a hotel scenario. Indeed, this is a paradigmatic context of application combining both significant social and economic impact and challenging but realistic research objectives. Furthermore our work is aimed to achieve the general objective of social robotics research which is enable people who have never met a real robot to operate and interact with it. Related work in the service robots interaction scenario has been carried out by [2],[3], the RoboCup@home competi- tion 1 and DESIRE [4] proyect just to name a few. In these projects we can see the efforts to create robots capable of performing various tasks in households or public domain, re- liable enough for every-day use. These projects are based on many expert technologies from different robotic domains and different developers. ”DESIRE” project proposes software Catalina Roncancio and Jose Luis Rodr´ ıguez are with Robotics, Computer vision and Biomedical Engineering Department at CARTIF Foundation. Parque Tecnologico de Boecillo Parc 205, Valladolid, Spain; e-mail:(catron, josrod)@cartif.es. Eduardo Zalama and Jaime G´ omez Garc´ ıa-Bermejo are with the ISA Dep. at the University of Valladolid, Valladolid, Spain; e-mail:(eduzal, jaigom)@eis.uva.es. 1 www.robocupathome.org engineering methods and tools that support integration and a new web portal for the distributed development and remote testing of service robots, integrating all software components on one common hardware platform in which more than 14 partners from universities, research institutes and industry supply components to that platform. Inspired in works like those mentioned before and in [5], we define a framework for modeling System of Systems (SoS) architecting [6]. These SoS attempt to integrate several independent complex systems into meta-architectures. From many potential systems with differing objectives, a set must be selected to construct the meta-architecture for SoS. The selection of the set depends on the requirements, functional- ities and capabilities desired from the SoS to achieve the common mission. This requires the creation of a meta- architecture that consists of core components that remain unchanged for a given period as other components that evolved through time. Systems could contain subarchitectures for motor control, vision, action, planning, language etc. Each subarchitecture contains a number of processing components which share information via a working memory. And the knowledge that can be used within a subarchitecture is defined by a set of ontologies for that module. Relationships (not necessarily equivalence) between the entries in the ontologies in different subarchitectures are defined by a set of general ontologies [7]. Sloman’s H-Cogaff cognitive architecture is utilized as a blueprint to design our architecture. II. SCENARIO We envisage our robot being useful in typical hotel sce- nario, in which the robot is expected to be able to interact with hotel guests, staff and environment, changing its known world through physical action and linguistic discourse, while performing the requested services and tasks. Knowledge to be of interest comprises topological representations of the hotel space, models about relevant objects and functional spaces, and about different users (guest and reception desk). The latter aspect is of particular relevance because a robot is considered to be a servant or companion interacting with various members of the hotel. Our bellboy robot will be designed and developed so that it is capable of providing the following services and tasks: • Accompanying the guests to their rooms. • Explaining the services available in the room and the hotel (meals, laundry, etc). • Carrying food, drinks, equipment and newspapers to the rooms.