Presentation is loading. Please wait.

Presentation is loading. Please wait.

A.G. Billard, Autonomous Robots Class Spring – EDPR/EDIC Doctoral School – Robotics Program Autonomous Robots Class Human-Robot Interaction.

Similar presentations


Presentation on theme: "A.G. Billard, Autonomous Robots Class Spring – EDPR/EDIC Doctoral School – Robotics Program Autonomous Robots Class Human-Robot Interaction."— Presentation transcript:

1 http://lasa.epfl.ch A.G. Billard, Autonomous Robots Class Spring – EDPR/EDIC Doctoral School – Robotics Program Autonomous Robots Class Human-Robot Interaction Methodologies in HRI Aude G Billard Learning Algorithms and Systems Laboratory - LASA EPFL, Swiss Federal Institute of Technology Lausanne, Switzerland aude.billard@epfl.ch

2 http://lasa.epfl.ch A.G. Billard, Autonomous Robots Class Spring – EDPR/EDIC HRI is a new field (about 15 years) Most studies cannot yet be reproduced (too different hardware) Methodologies in HRI

3 http://lasa.epfl.ch A.G. Billard, Autonomous Robots Class Spring – EDPR/EDIC Like in Psychology, it is difficult to agree on a methodology on how to carry out research. Should one apply quantitative, statistical methods requiring large-scale experiments, i.e. involving large sample sizes of participants, or pursue a qualitative approach focusing on case studies and in-depth analysis. Methodologies in HRI

4 http://lasa.epfl.ch A.G. Billard, Autonomous Robots Class Spring – EDPR/EDIC Wizard of Oz The WOZ method involves a human who is (unknown to the test subjects) controlling the behaviour of the system, ranging from full teleoperation to partial control of ‘higher level’ decision making processes. Methodologies in HRI In (Dahlback et al 93) a Wizard-of-Oz study was first conducted to explore how people would relate to a service robot, while the design of the robot’s dialogue capabilities was still ongoing. A general conclusion from the study was that users need explicit feedback at several levels to understand the state of the robot; in particular, to what degree it has perceived the instructions given, and where it is headed when moving around. N. Dahlbäck, A. Jönsson and L. Ahrenberg, Wizard of Oz studies—why and how. Knowledge-based Systems 6 4 (1993), pp. 256–258.

5 http://lasa.epfl.ch A.G. Billard, Autonomous Robots Class Spring – EDPR/EDIC The Theatrical Robot consists of a human instructed to behave and/or appear like a robot. The human is a professional such as a mime or person trained to perform pre- scripted behaviours, as needed for experimental protocols, reliably and with high precision. Robins, B., Dautenhahn, K. & Dubowski, J. (2006), Does appearance matter in the interaction of children with autism with a humanoid robot?, Interaction Studies 7(3), 509–542 In Robins et al 2006), the mime/theatrical robot mimicks the behavior of the doll robot, Robota, to test children with autism’s reaction prior to conducting the experiments Methodologies in HRI The response of children with autism towards the plain/robotic theatrical robot was notably more social and pro-active. The ordinary-human appearance resulted in avoidance behaviour or ‘aloofness’, a typical behaviour that autistic children show towards strangers.

6 http://lasa.epfl.ch A.G. Billard, Autonomous Robots Class Spring – EDPR/EDIC Sketch of a typical development time line of HRI robots. In an initial phase of planning and specification, mock-up models might be used before hardware and software development commences. Once a system’s main components have been implemented, a WoZ study is applicable, and/or video based methods can be applied. As soon as working prototypes exist that also conform with safety requirements, interaction studies can be conducted. The Theatrical Robot paradigm allows one to conduct interaction studies even from the early phase of planning and specification onwards throughout the whole development of the robot. K. Dautenhahn, Methodology & Themes of Human-Robot Interaction: A Growing Research Field, International Journal of Advanced Robotic Systems, Vol. 4, No. 1 (2007), pp. 103-108. Methodologies in HRI

7 http://lasa.epfl.ch A.G. Billard, Autonomous Robots Class Spring – EDPR/EDIC From the standpoint of human-robot interaction, how do we measure success? BENCHMARKS FOR HRI Kahn, P. H., Jr., Ishiguro, H., Friedman, B., & T. Kanda (2006). What is a human? - Toward psychological benchmarks in the field of human-robot interaction. Proceedings of the 15th International Symposium on Robot and Human Interactive Communication (RO-MAN '06). Hatfield, UK: Develop psychological benchmarks  Kahn et al 2006 have offered nine contenders: autonomy, imitation, intrinsic moral value, moral accountability, privacy, reciprocity, conventionality, creativity, and authenticity of relation. But, one may also consider benchmarks for emotion, attachment, cognition, and memory. One could also try to establish benchmarks on the level of group interaction, as opposed to individual human-robot interaction. Methodologies in HRI

8 http://lasa.epfl.ch A.G. Billard, Autonomous Robots Class Spring – EDPR/EDIC Robots are not people! It is a misconception that results from human-human interactions can be directly applied to human-robot interaction. Methodologies in HRI K. Dautenhahn, Methodology & Themes of Human-Robot Interaction: A Growing Research Field, International Journal of Advanced Robotic Systems, Vol. 4, No. 1 (2007), pp. 103-108. Even if it has been shown that people behave towards artifacts, i.e. computers, in many ways socially, e.g. attribute personality to them, reciprocate favours etc.,… … as long as robots and humans are distinguishable, and this will still be the case for many years to come, people are likely to not treat them identically to human beings.


Download ppt "A.G. Billard, Autonomous Robots Class Spring – EDPR/EDIC Doctoral School – Robotics Program Autonomous Robots Class Human-Robot Interaction."

Similar presentations


Ads by Google