Wayve, a UK-based autonomous vehicle startup, is pushing forward with a strategy that emphasizes affordability, adaptability, and broad application across the automotive and robotics sectors. CEO Alex Kendall outlined the company’s approach at Nvidia’s GTC conference, highlighting an end-to-end data-driven learning model that eliminates the need for high-definition maps or rule-based software.
The company, which has raised over $1.3 billion in the past two years, aims to license its self-driving software to automakers and fleet operators, including Uber. While no formal automotive partnerships have been announced, a Wayve spokesperson said the company is in “strong discussions” with multiple original equipment manufacturers (OEMs) to integrate its technology into a range of vehicles.
See also: UK’s Wayve to Open Self-Driving Tech Hub in Germany, Expands Testing Fleet
Kendall stressed that Wayve’s software can run on existing automotive hardware, allowing OEMs to adopt its advanced driver-assistance system (ADAS) without additional investments. “OEMs don’t need to invest anything into additional hardware because the technology can work with existing sensors, which usually consist of surround cameras and some radar,” he said. The software is also “silicon-agnostic,” capable of operating on various GPUs, though Wayve’s current development fleet utilizes Nvidia’s Orin system-on-a-chip.
Unlike many companies developing Level 4 autonomous driving technology, Wayve is focused on commercializing its system at an ADAS level first. This approach mirrors Tesla’s strategy of deploying AI-driven assistance to collect real-world driving data that could eventually enable full autonomy. However, Wayve diverges from Tesla’s camera-only system by remaining open to incorporating lidar for enhanced perception in specific conditions.
See also: Wayve Expands Autonomous Vehicle Testing to San Francisco with Self-Learning AI Software
“Do you want the car to drive faster through fog? Then maybe you want other sensors [like lidar]. But if you’re willing for the AI to understand the limitations of cameras and be defensive and conservative as a result? Our AI can learn that,” Kendall explained.
Wayve also introduced GAIA-2, its latest generative AI model designed to improve autonomous driving by processing video, text, and other data sources in an integrated manner. The model aims to make AI-driven vehicles more adaptive and capable of handling complex driving scenarios, including those they have not encountered during training.
See also: Wayve Plans US Expansion, Challenges Tesla and Waymo in Self-Driving Car Market
“What is really exciting to me is the human-like driving behavior that you see emerge,” Kendall said. “Of course, there’s no hand-coded behavior. We don’t tell the car how to behave. There’s no infrastructure or HD maps, but instead, the emergent behavior is data-driven and enables driving behavior that deals with very complex and diverse scenarios, including scenarios it may never have seen before during training.”
Wayve’s approach aligns with that of autonomous trucking startup Waabi, both of which prioritize scaling AI models that can generalize across diverse driving environments. The company’s focus on cost efficiency and hardware flexibility may prove pivotal in securing industry partnerships as automakers explore software-driven solutions for next-generation mobility.