Latent Logic uses "imitation learning" to create simulations of human behavior that can be used in vehicle testing. Most AI training uses reinforcement learning, where an AI provides answers to problems that are either coded as right or wrong. Over time, a gain-based AI can learn the right answer faster.
However, this can be inefficient. In contrast, imitation learning mechanically mimics human behavior in order to learn some of people's implicit knowledge of the world. This enables the AI to model the optimal solution faster. Waymo could use this technique to train autonomous vehicles by AI simulating complex human behaviors such as car cutting or the appearance of a pedestrian in an unexpected location. Self-driving vehicle research. For example, there is Oxbotica, a group that has tested an autonomous grocery van, self-driving taxis, and driverless shuttles. In cooperation with researchers in Oxford, BAE Systems has developed a comprehensive autonomous off-world vehicle based on a Bowler Wildcat. There is also the University of Oxford, which also researches autonomous vehicles.
The acquisition of the company enabled Alphabet to gain a foothold in a key location in the UK and access to a hub of local talent. "We see an exciting opportunity in Europe not only to further expand our partnerships with major automakers, but also to benefit from the world-class technology and engineering capabilities in Oxford and beyond," said Drago Anguelov, Waymos chief scientist and research director The Guardian.
Waymo is not yet planning to launch self-driving car services in the UK, but the company has confirmed that it has plans to operate in Europe in the future.