The PAL Robotics team have just returned from yet another fantastically organised ICRA – the IEEE’s International Conference on Robotics and Automation. This year, it was held at the Marina Bay Sands Expo and Convention Center in Singapore. It’s hard to find an event that matches ICRA in terms of sheer size and scale. With 11 tracks, 900 paper presentations and over 40 exhibitors, it is a truly mammoth conference that mirrors the increasingly widespread interest in robotics. Hundreds of researchers from around the world gathered to discuss the latest developments, technologies and research that will enable robots to become a significant and functioning part of our everyday lives.
This year, one of our PhD students, Jeremie Deray, presented a paper outlining a new method for loop closure – a technique that enables robots to recognise places they’ve already been, in order to localise themselves in the environment and improve the quality of their map. Jeremie, along with fellow students from the Institut de Robotica, explained that their research focused on applying an approach typically used to recognise images in computer vision to robots’ 2D laser readings. They exploited the graph topology of the environment by enforcing neighbouring place constraints, which in turn increased performance and recognition rate. Jeremie and the team proved that their proposed method is comparable to or better than existing algorithms.
Noticia enviada por PAL Robotics
