Wayve pioneers new AI model for autonomous driving
Wayve, a self-driving technology company and a Virgin Group investment, has introduced a first-of-its-kind AI model for self-driving, called LINGO-1. The company is pioneering the use of natural language to help people more easily understand the reasoning and decision-making capabilities of its AI Driver technology.
The LINGO-1 model is an open-loop driving commentator that combines vision, language and action to enhance how Wayve can interpret, explain and train the foundation driving models. The model can comment on driving scenes and be prompted with questions to clarify and explain what factors in the driving environment affected its driving decisions. It will also help people to more easily understand the decision-making capabilities of the technology. As Wayve’s CEO, Alex Kendall, said: “We see it [LINGO] as a beachhead piece of research that opens up a wealth of new opportunities, particularly in AI safety and transparency, because we can now directly ask the system why it's doing what it’s doing.”
LINGO-1 can also respond to questions about a diverse range of driving scenes, and allows Wayve to make improvements through feedback. For example, the model can be asked: “Why did you slow down?” The answer then allows Wayve to evaluate LINGO-1’s scene comprehension and reasoning. It means Wayve can make more efficient improvements to the technology, and build more confidence in the system.
Wayve believes that natural language provides a powerful way to better understand and interact with robotics. In regards to autonomous driving, it provides potential for better and safer autonomous driving. Using LINGO-1, Wayve could incorporate natural language sources such as highway codes to retrain its AI models more easily. By improving the raw intelligence of its AI Driver, Wayve can accelerate the learning process, enhance accuracy, and increase the technology’s capacity to handle diverse driving tasks. As Kendall said:
“LINGO-1 marks a big step for embodied AI: aligning vision, language and action to deliver more intelligent and trusted autonomous vehicles. We are excited by the capabilities we observe from LINGO-1 today and we believe natural language will provide a powerful step change in how we understand and interact with robotics.”
“At Wayve, we’re investing in pushing the boundaries of cutting-edge science to deliver a safer, smarter and more sustainable future of transport, resulting in LINGO-1. LINGO-1 opens up many possibilities for self-driving, improving the intelligence of our end-to-end AI Driver as well as bridging the gap of public trust – and this is just the beginning of maximising its potential.”
Wayve is currently testing its self-driving technology daily on UK roads and is undertaking Europe’s largest last-mile autonomous grocery delivery trial with Asda. Wayve also aims to be the first company to deploy autonomous vehicles in 100 cities.