New research finds that robots will need to comprehend why they’re doing a particular task, if they are to safely work alongside humans in future.
The research team at the National Centre for Nuclear Robotics at Birmingham University, believes that this could result in significant changes in the robotics space.
Lead researcher, Dr. Valerio Ortenzi, claims that the change in ideas will be essential as industries adopt automation, connectivity and digitisation (‘Industry 4.0 ‘) and human-robot engagement rates, whether in warehouses or households, significantly rise.
“Imagine asking a robot to pass you a screwdriver in a workshop. Based on current conventions the best way for a robot to pick up the tool is by the handle. Unfortunately, that could mean that a hugely powerful machine then thrusts a potentially lethal blade towards you, at speed,” he said.
“Instead, the robot needs to know what the end goal is, i.e.,to pass the screwdriver safely to its human colleague, in order to rethink its actions.”
The paper, published in Nature Machine Intelligence, cites example of robots working alongside people and examines the issue of the use of objects by robots. It highlights a basic problem: what has typically been considered a ‘successful’ grasp for a robot could be a real-world failure because the machine does not take into account what the aim is and why the object is picked up.
The team recommends that traditional metrics used by researchers, over the past twenty years, to assess robotic manipulation, are not sufficient.
“In the most practical sense, robots need a new philosophy to get a grip,” Dr. Ortenzi said.
The research was conducted in collaboration with the Center of Excellence for Robotic Vision at Queensland Technology University, Australia, Scuola Superiore Sant’Anna, Italy, the German Aerospace Center (DLR), Germany, and Pisa University, Italy.
Stay up to date by getting stories like this delivered to your mailbox.
Sign up to receive our free weekly Spatial Source newsletter.