ASER Seminar -- December 4th, 2009


Research Challenges on Human-Robot Interaction and Robotic Human Science

by Jorge SOLIS-ALFARO, Assistant Professor, Waseda University, Japan

Abstract:

The research on human-robot interaction (HRI) and robotic human science (RHS) have been an emerging topic of interest for both basic research and customer application. The studies specially focus on behavioral and cognitive aspects of the interaction and the social contexts surrounding it. One of the most challenging problems is giving the robots an understanding of how to interact with human beings at the same logical level so that they may function not as passive tools, but rather as active agents that can drive the human interaction, instead of merely reproducing a sequence of movements. Hence, these robots must have higher level cognitive functions that include knowing how to reason, when to perceive and what to look for, how to integrate perception and action under changing conditions, etc. These functions will enable robots to perform more complex tasks which require tight human interaction; consequently, the robots can perform high level interactions (i.e. teaching motor skills to unskilled people, etc.). In this talk, an overview of the current research on humanoid robots, medical robotics and systems and education robotics will be introduced.

  1. Humanoid Robots: Nowadays several researchers have been developing anthropomorphic robots as a research approach related to RHS to roughly replicate some of the human motor skills such as walking, dancing, etc. However, such robots are still far away from understanding and processing emotional states as the human does. In order to overcome this limitation, the research on music still seems particularly promising; since it is a universal communication medium. Furthermore, the research on music can also provide expressive tools that traditionally have been hidden in musicians' skills. For that reason, at Waseda University, the research on the Waseda Flutist Robot and Saxophonist Robot have been carried out as an approach to understand the human motor control from an engineering point of view as well as introducing novel ways of musical teaching.
  2. Medical Robotics and Systems: Certainly, in order to conduct effective learning experiments, the robotic system must actively interact with humans at the same logical/perceptual level through all the stages of the learning process. This means that robots should analyze the exchanged information between human and robot to evaluate learner’s performance and furthermore, to provide some kind of feedback (aural, haptic, visual, etc.) which may promote the creation of the internal models by the active training of learner on the task so that subjects can reconstruct accurately the motor skill by reinforcing the kinaesthetic memory. On the other hand, there is the possibility of studying which parameters of the learning process may lead or break down the acquisition of the motor skill by modifying the conditions of the experiments. These parameters may include: which feedback modality is provided (one modality or multimodal), complexity of the skill, learning procedure, number of repetitions of the task, etc.
  3. Education Robotics: Developed countries, as leading nations in scientific research and production of innovative technological products, hold very large shares in high technology industries. However, the continuous falling of the birthrate in developed countries is resulting in a reduction in the number of students where most of them are going away from scientific fields. This situation may tremendously affect the industry by losing competitive power in the future due to the shortage of talented engineers. For this purpose, we have focused our research in developing more advanced educational mechatronic tools to motivate their creativity at different educational levels. For this purpose, we have proposed the development of a two-wheeled inverted pendulum type mobile robot designed to provide educational issues related to electronics, mechanics, control theory and programming.