Wayve Lingo-2 AI Model With Autonomous Driving Capabilities, Ability to Take Passenger Instructions Showcased

Wayve unveiled its artificial intelligence (AI)-based vision-language-action driving mannequin (VLAM) Lingo-2 on Wednesday. Lingo-2 comes because the successor of the Lingo-1 AI mannequin and has a number of new capabilities. The autonomous driving AI can now supply commentary of its actions whereas driving in addition to adapt its actions primarily based on the passenger’s directions. It will possibly additionally reply queries about its environment which isn’t immediately associated to its driving. The AI agency stated Lingo-2 was designed as the trail to construct a reliable autonomous driving know-how.

Showcasing the capabilities of Lingo-2 in a demo video on X (previously generally known as Twitter), the corporate launched the brand new Lingo-2 AI mannequin that’s able to navigating roads whereas taking directions from passengers. The submit on X additionally features a video of a Lingo-2 drive by Central London, the place the mannequin drives the automobile whereas concurrently producing real-time driving commentary.

The AI mannequin combines three completely different architectures — laptop imaginative and prescient, giant language mannequin (LLM), and motion fashions — to create a mixed VLAM mannequin that may carry out numerous complicated duties collectively in actual time. Based mostly on the demo, Lingo-2 can see what’s taking place on the highway, make choices on its foundation, and inform the passenger in regards to the resolution. Moreover, it could actually additionally adapt its behaviour primarily based on any directions given by the passenger, and reply non-driving associated queries corresponding to details about the climate.

Wayve says that performing these actions persistently and reliably is a vital step in direction of constructing autonomous driving know-how. “It opens up new potentialities for accelerating studying with pure language by incorporating an outline of driving actions and causal reasoning into the mannequin’s coaching.

Pure language interfaces may, even sooner or later, permit customers to have interaction in conversations with the driving mannequin, making it simpler for individuals to know these programs and construct belief,” the corporate stated on its website.

You will need to word that Lingo-2 does probably not drive a car as it’s simply an AI mannequin and isn’t built-in with {hardware} to manage a car. It’s educated and examined on Wayve’s in-house closed-loop simulation referred to as Ghost Gymnasium.

Being a closed-loop simulation, the corporate can check the sensible response of different autos and pedestrians primarily based on the management car’s behaviour. For the subsequent steps, the AI agency plans to begin restricted testing of the AI mannequin in a real-world atmosphere to analyse its decision-making in additional unpredictable conditions.