“Robots working in human environments need to adapt to the fact that humans are unique and that we can all solve the same task in a different way. An important area in robotics development. , therefore, is to teach robots how to work alongside Maximilian Diehl, a PhD student in the Department of Electrical Engineering at Chalmers University of Technology and the lead researcher behind the project, which says humans in the environment dynamic.
New Artificial Intelligence (AI) can explain
even though Robots require precise programming work in a continuous process of the same model, moreover need a flexible way of working for them to successfully interact with people in areas such as healthcare or customer-facing roles.
To design a human-like approach to solving tasks between robots, the team developed a ‘AI can explain’ (the type of artificial intelligence where a human can understand how it comes to a particular decision or outcome) can plan a flexible and adaptive path towards long-term goals.
“With our AI, the robot made plans with a 92% success rate after just one human demonstration. When the information from all twelve performances was used, the success rate increased. up to 100%.” It is likely to take several years until we see truly versatile and autonomous robots, mainly because many individual challenges still need to be solved, such as computer vision, controllability and Safe interactions with people. However, we believe that our approach will contribute to accelerating the learning process of robotics, allowing the robot to connect all these aspects and apply them in new situations,” said Maximilian Diehl. .
Source: Medindia
