Perception for Autonomous Systems
Perception, the ability to detect the surroundings through sensing, is a task that animals and humans have evolved over millions of years. To us, it is second nature. Yet for machines, this task is extremely challenging. Understanding new situations, detecting dynamic environments and anticipating unpredictable elements (e.g. pedestrians) are tasks where machines regularly fail.
At Univrses, we solve challenging perception problems that arise when building autonomous systems to operate in the real world.
We have developed a set of software modules that can be integrated into robotic platforms and autonomous systems. We call these the 3DAI™ Engine. Each module in 3DAI™ Engine enables capability that contributes to increasing the perception capabilities and the autonomy of a system. 3DAI™ Engine comprises all the necessary components to enable autonomy: precise and reliable localisation of a vehicle, detection and tracking of nearby objects and semantic understanding of the environment and its evolution.