ICAV Cluster

Small vehicle Car

Wayve debuts multimodal driving model Lingo-2

Wayve has unveiled Lingo-2, a sophisticated closed-loop driving model designed to fuse vision, language, and action to elucidate and determine driving behavior.

This innovation marks Lingo-2 as the premier vision-language-action model (VLAM) to undergo real-world testing on public roads.

Expanding upon the groundwork laid by its predecessor, Lingo-1, which concentrated on open-loop driving commentary, Lingo-2 seamlessly integrates language with driving behavior, ushering in a new era of capabilities for autonomous driving and human-vehicle interaction, according to Wayve. These capabilities encompass the ability to adapt driving behaviors based on language cues, real-time interaction with the AI model, and dynamic capture of driving commentary as events unfold.

Wayve advocates for the utilization of AI driving models as a means of learning from data and practical experience, rather than relying solely on pre-programmed rules or high-definition maps. Lingo-2 merges Wayve’s vision model with an auto-regressive language model, conventionally employed for predicting subsequent words in sentences, to anticipate driving trajectories and provide commentary on driving decisions.

Following rigorous testing within Wayve’s neural simulator, Ghost Gym, and real-world driving scenarios, Lingo-2 exhibits promising indications of the potential achievable through the integration of linguistic explanations and decision-making processes, as stated by the company. This development is anticipated to instill greater confidence in autonomous driving technology.

Alex Kendall, CEO and co-founder at Wayve, said, “Lingo-2 is shaping the future of human-vehicle interaction. The Embodied AI we are building will not only automate driving but also create innovative experiences where the driver can interact with the vehicle to gain more confidence and trust in our assisted and autonomous driving systems.”

Jamie Shotton, Chief Scientist at Wayve, highlighted the significance of language as a tool for interaction with robots, comprehension of their decisions, accelerated training processes, and customization of outputs. He emphasized Wayve’s commitment to advancing the frontiers of science in the pursuit of building safe and reliable autonomous systems tailored to meet the diverse needs of individuals worldwide.

ICAV Cluster is CAV and Smart City news aggregator. To add your Smart City or CAV related news, please email our editorial team at info@icavcluster.com.