Identifying spatial terminology and boundaries for human robot interaction: A human study

Service robots have been widely adopted to the domestic environment over the past few years. Pertaining to this sudden growth, a high interest has been exerted upon the service robots deployed in the domestic circle. The domestic users are not overly cohabitated with technology and use natural language habitually in their daily tasks. Instead of a set of machine specific instructions, natural language contains spatial terms with ambiguous meaning which gets altered depending on the environment and users themselves. Therefore the competence of the robot to understand and interpret the natural language instructions used by humans becomes a fact of substantial importance in the domestic environment. This paper contributes in a human study which helps in understanding three of the main aspects that alter the meaning of these spatial terms namely; the effect of size of the surface, the effect of user's position and the effect of the restricted reachability due to objects in the surrounding area. Furthermore this study helps to understand the references used by humans when issuing commands and also builds up a corpus of natural spatial terms frequently used in object manipulation. After statistically analysing the results, the study reveals the extent to which the object placement task is affected by the above mentioned three aspects.

[1]  John A. Goldsmith,et al.  Unsupervised Learning of the Morphology of a Natural Language , 2001, CL.

[2]  Nicholas Roy,et al.  Where to go: Interpreting natural directions using global inference , 2009, 2009 IEEE International Conference on Robotics and Automation.

[3]  David Whitney,et al.  Interpreting multimodal referring expressions in real time , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[4]  Hirotaka Osawa,et al.  Improving voice interaction for older people using an attachable gesture robot , 2010, 19th International Symposium in Robot and Human Interactive Communication.

[5]  Adam Kendon,et al.  Spacing and Orientation in Co-present Interaction , 2009, COST 2102 Training School.

[6]  Siddhartha S. Srinivasa,et al.  Spatial references and perspective in natural language instructions for collaborative manipulation , 2016, 2016 25th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN).

[7]  David R Traum,et al.  Towards a Computational Theory of Grounding in Natural Language Conversation , 1991 .

[8]  Manuela M. Veloso,et al.  Language-Based Sensing Descriptors for Robot Object Grounding , 2015, RoboCup.

[9]  Sotiris Makris,et al.  Human–robot interaction review and challenges on task planning and programming , 2016, Int. J. Comput. Integr. Manuf..

[10]  Ryo Kurazume,et al.  Service robot system with an informationally structured environment , 2015, Robotics Auton. Syst..

[11]  Honghai Liu,et al.  Grounding spatial relations in natural language by fuzzy representation for human-robot interaction , 2014, 2014 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).

[12]  Leopoldina Fortunati Moving Robots from Industrial Sectors to Domestic Spheres: A Foreword , 2016, Toward Robotic Socially Believable Behaving Systems.

[13]  P.H.D. Arjuna S. Srimal,et al.  A multi-modal approach for enhancing object placement , 2017, 2017 6th National Conference on Technology and Management (NCTM).

[14]  Kevin Lee,et al.  Tell me Dave: Context-sensitive grounding of natural language to manipulation instructions , 2014, Int. J. Robotics Res..

[15]  Stefanie Tellex,et al.  Toward understanding natural language directions , 2010, HRI 2010.

[16]  M. A. Viraj J. Muthugala,et al.  Enhancing human-robot interaction by interpreting uncertain information in navigational commands based on experience and environment , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[17]  Uwe Reyle,et al.  From Discourse to Logic - Introduction to Modeltheoretic Semantics of Natural Language, Formal Logic and Discourse Representation Theory , 1993, Studies in linguistics and philosophy.

[18]  Michael Beetz,et al.  Grounding the Interaction: Anchoring Situated Discourse in Everyday Human-Robot Interaction , 2012, Int. J. Soc. Robotics.

[19]  Francesco Timpone,et al.  Advances in Robot Design and Intelligent Control - Proceedings of the 25th Conference on Robotics in Alpe-Adria-Danube Region, RAAD 2016, Belgrade, Serbia, 30 June - 2 July 2016 , 2017, RAAD.

[20]  Simon Kirby,et al.  Natural Language From Artificial Life , 2002, Artificial Life.

[21]  M. A. Viraj J. Muthugala,et al.  Deictic gesture enhanced fuzzy spatial relation grounding in natural language , 2017, 2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).

[22]  Matthew R. Walter,et al.  Understanding Natural Language Commands for Robotic Navigation and Mobile Manipulation , 2011, AAAI.