STRANDS’ companion robot featured on Gadget Man TV series
‘My final, personal, “pièce de résistance” is Linda, an intelligent robot programmed to autonomously patrol the house and make sure no one tries to jack my shiz,’ Ayoade explains as the robot enters the screen in his fictional, security gadget testing ‘crib’. Thanks to its laser scanner, Linda can move around while building up a map of her environment, identifying intruders and supporting security staff in their duties. She can run autonomously for weeks, gather data about her surroundings and adapt her behaviour accordingly. Last year, Linda was tested at the Natural History Museum of London where she was tasked with guiding visitors to exhibitions on the occasion of European Robotics Week. ‘We are trying to enable robots to learn from their long-term experience and their perception of how the environment unfolds in time. It will have many possible applications and taking Linda to the Natural History Museum is a fantastic opportunity for people to see how robots like this will, one day, be able to aid and assist humans in a variety of roles,’ Dr Marc Hanheide from the University of Lincoln had explained at the time. Linda is one of six robots developed by the STRANDS team that also includes Bob, Henry, Karl, Werner and Lucie. Where state-of-the-art robots would generally read spatio-temporal dynamics as anomalous readings, piling up errors that eventually prevent them from running more than a few hours, Linda and co. are expected to be able to run for at least 120 hours by the end of the project, while being capable of adapting to highly demanding, real-world security and care scenarios. While STRANDS is only due for completion in May 2017, its robots have already been tested in various situations. Bob, for instance, has been enrolled for three weeks by G4S – the leading global integrated security company – to patrol a working office environment. The latest project achievement was the publication of a research paper in March 2015. In the document, the team proposes a probabilistic sequential model of Human-Robot Spatial Interaction (HRSI) relying on a Qualitative Trajectory Calculus (QTC) embedding the concept of proxemics to facilitate richer models. ‘For mobile robots to be used in populated environments, they have to understand how humans behave and be able to move when encountering each other in a corridor for example. In such situations, the robot’s movement not only has to be safe but the robot has to be able to convey its intention on where and how to move, how to react to the human’s movements, and how the human will react to it. Current research mainly focuses on how the robot has to avoid a human, but not on how their movement might influence each other,’ lead author Christian Dondrup of Lincoln’s School of Computer Science explained. For further information, please visit: STRANDS http://strands.acin.tuwien.ac.at/
Countries
United Kingdom