We seek to fulfill the latent potential of the growing wave of robots and autonomous vehicles, which remain limited by their inability to instantly generate collision-free motion plans in response to fast-changing situations.
Realtime’s new special-purpose processor enables robots and vehicles to instantly react to their environments and compute how and where to move as their situation is changing. Realtime’s processor can be configured to plan at speeds as fast as 1kHz , overcoming the primary obstacle preventing robots and autonomous vehicles from achieving their potential. Realtime’s processor will enable robots with sophisticated arms to generate collision-free motion in unstructured and dynamic environments in real time, making them useful for tasks well beyond the precise, rigid, and repetitive industrial tasks where they are currently employed. Autonomous vehicles with Realtime’s processor will drive at normal speeds—like humans, but safer—instead of slowing to a crawl when there is uncertainty regarding other cars, bikes, and pedestrians.
Realtime Robotics was founded in March 2016 by Duke University professors Dan Sorin (Computer Architecture), George Konidaris (Robotics & Motion Planning), and a few of their top researchers, based on their groundbreaking DARPA-funded research. The Company is currently working with major multinational customers to create highly adaptable robotic systems for application to the vast majority of industrial tasks which are in dynamic environments, as well as to enable autonomous driving platforms to achieve superior safety at normal driving speeds, even in the complex urban driving environments that are the key challenge to the technology’s widespread adoption.