Open Access. © 2019 H. M. Ravindu T. Bandara et al., published by De Gruyter. This work is licensed under the Creative Commons Attribution alone 4.0 License. Paladyn, J. Behav. Robot. 2019; 10:401ś416 Research Article Open Access H. M. Ravindu T. Bandara*, M. A. Viraj J. Muthugala, A. G. Buddhika P. Jayasekara, and D. P. Chandima Understanding uncertain information in vocal description for creating virtual spatial maps https://doi.org/10.1515/pjbr-2019-0032 Received March 31, 2019; accepted September 12, 2019 Abstract: Assistive robots are developed for supporting daily activities of elderly people to uplift the living stan- dards. The assistive robots should be friendly, reliable, active, and comprehensible in order to satisfy the needs of elderly population. Human activities are frequently re- lated to navigational tasks and human tend to use descrip- tions which include natural language phrases and uncer- tain terms such as łnearž, łlittlež, łfarž, łsmallž, łlargež, łclosežto describe about spatial information. Therefore assistive robots should be capable of analysing and un- derstanding descriptions which contain natural language phrases with uncertain terms and creating a concep- tual map for efective navigation. This paper proposes a method to understand spatial information in a descrip- tion with uncertain terms and creates a conceptual map in a robot memory which can be linked with spatial map for purposeful, efective and human friendly navigation task. Human studies have been carried out to study difer- ent types of descriptions related to navigation tasks. The Virtual Spatial Data Identifer (VSDI) and Uncertain Term Identifer (UTI) modules have been introduced in order to evaluate the spatial information in description to create a virtual map. Results of the system have been compared with the results of a human study in order to evaluate per- formance of the proposed system. Keywords: uncertain information, virtual spatial maps, as- sistive robotics *Corresponding Author: H. M. Ravindu T. Bandara: University of Moratuwa; E-mail: ra-ravindu@uom.lk M. A. Viraj J. Muthugala: Singapore University of Technology and Design; E-mail: muthugala@ieee.org A. G. Buddhika P. Jayasekara: University of Moratuwa; E-mail: buddhikaj@uom.lk D. P. Chandima: University of Moratuwa; E-mail: chandimadp@uom.lk 1 Introduction The world’s growth rate of elderly population continues in an unrivalled scenario [1]. The ageing population faces physical, mental and intellectual impairments [2] and the support of caregivers is an essential matter in uplifting the living standard of the older people [3]. Furthermore, num- ber of experienced human caretakers is far below the re- quired number and the energy and time of the workforce for elderly care can be directed to the development of a country [4]. As a solution to the above-mentioned fact, assistive robots and devices can be used as a substitu- tion for the human caregivers [5]. Assistive robots can pro- vide a support in typical daily activities of elderly people such as support in fnding items, navigational tasks, med- ical schedules, avoidal social issues [6, 7]. In order to per- form assistive service tasks, the assistive robots should be capable of navigating efectively and purposively inside the human populated environments [8, 9]. For efective navigation, primitive low-level of motion predication abil- ities such as collision avoidance are required. However, solving of such primitive low-level navigation functional- ities is no longer a focus problem in indoor robot navi- gation area since the availability of large number of low- level navigation controlling methods and software pack- ages [10]. Nowadays, the main aim is to support for de- veloping human-friendly navigation mechanism, in which robots can understand the human motions and intentions, and react as a companion of human [11]. Natural language is a fexible, intuitive medium that can enable such in- teractions, but language understanding requires robots to learn representations of their environments that are com- patible with the conceptual models used by people [12ś14]. Humans have the cognitive ability to create virtual maps about the environment [15, 16] based on the in- formation received through natural language instructions without actually perceiving the environment. A situation where a deliveryman, who is new to an ofce, is sent to de- liver an item to a completely strange location by his/her workmate (who is well aware of that location) can be con- sidered as an example case for the explanation. In this