{"id":174014,"date":"2019-06-17T12:05:42","date_gmt":"2019-06-17T10:05:42","guid":{"rendered":"https:\/\/innovationorigins.com\/?p=174014"},"modified":"2019-06-17T12:05:42","modified_gmt":"2019-06-17T10:05:42","slug":"some-hypes-and-missed-opportunities-in-robotics","status":"publish","type":"post","link":"https:\/\/ioplus.nl\/archive\/en\/some-hypes-and-missed-opportunities-in-robotics\/","title":{"rendered":"Some hypes and missed opportunities in robotics"},"content":{"rendered":"

Prof. Herman Bruyninckx<\/a>\u00a0(<\/span>KU Leuven) presented a critical view on the robotics industry\u00a0during<\/span>\u00a0the seminar in High Tech Campus Eindhoven. Bruyninckx delivered a talk on the hypes and missed opportunities in\u00a0robotics<\/a> pointing\u00a0out the key issues that robotics should tackle nowadays.<\/p>\n

Herman Bruyninckx has a background in mathematics, physics, computer science and \u201cPhilips\u201d mechatronics. He has worked as a roboticist since 1988. <\/em>Now he is a professor of KU Leuven and TU\/e. <\/em>Herman Bruyninckx\u2019<\/em> research focus is robotics as the science of the integration of the systems-of-systems. \u00a0<\/em><\/p>\n

Does more computing power lead to better robot systems?<\/span><\/span><\/span><\/span><\/h3>\n

Context is everything<\/span><\/span><\/h3>\n

\u201cThere are different levels of perception, and we change them all the time automatically,\u201d says Bruyninckx. \u201cIf I\u2019m walking along the stage and I\u2019m not paying much attention to the edge, I\u2019m not going to drop off here. Even if I do, it\u2019s not so high. But I would move completely different if I hold a baby in my hands. Baby will have an impact on all of my control settings, on all of my perception settings. So the context of the task changes everything. But the robots haven\u2019t even started using that kind of context-dependency.\u201d<\/p>\n

Abstraction<\/span><\/span><\/h3>\n

\u201cWe don\u2019t memorize how many people we saw in the cafeteria \u2013 lots of background noise is erased. All that we use in our education is abstraction. Humans use abstractions so much and so long that they don\u2019t understand anymore how difficult it is. And we want the robots to learn how to use abstraction by showing them sensors\u2019 data. Then why don\u2019t we teach our kids maths by showing them 1000 million equations?\u201d<\/p>\n

Deep learning<\/em>, according to Bruyninckx is just a new buzz word. \u201cIt has nothing to do with deep<\/em> and nothing to do with learning<\/em>,\u201d argues Bruyninckx. \u201cIt\u2019s all about data reduction. Robots need hard human thinking, not ICT support.\u201d<\/p>\n

Robots and environment<\/span><\/span><\/h3>\n

\u201cNow robots are kept away from touching the environment, but it shouldn\u2019t be so,\u201d says Bruyninckx. \u201cIf I need to take something from the table without looking, I will take it by touching. Touch is really important for most of the tasks.\u201d Bruyninckx and his research group conducted tests on active sensing with people: a person was blindfolded, unable to hear and was wearing very thick clothes. It\u2019s the best possible approximation of a human to a robot.<\/p>\n

Herman Bruyninckx believes that what robots lack nowadays is the awareness of the users\u2019 intentions and the ability to use abstraction. \u201c50 years after the \u201cfirst robot\u201d Shakey<\/a> you can still you go to a robotics conference and understand everything there \u2013 because the context and the mathematics are exactly the same. Intention and abstraction of the robots are still very underdeveloped. We need higher-order logic to make the robot aware of why it should be doing something but there is no formal language to represent that. We cannot even formalize what we humans know about the intentional context,\u201d says Bruyninckx.<\/p>\n