VentureBeat is reporting that U.K.-based startup Wayve has raised $20 million in Series A funding to improve AI for autonomous vehicles.
Wayve takes a different approach to autonomous vehicles than many other companies. Rather than hand-coded rules, or throwing more sensors at the problem, Wayve is trying to improve the AI behind autonomous vehicles to better emulate human-style adaptability and decision-making.
“The company said that it trains its autonomous driving system using simulated environments and then transfers that knowledge into the real world, where it emulates how humans adapt to conditions in real time. Wayve’s systems learn from each safety driver intervention to understand why the driver had to intervene, bypassing HD maps, lidar, and other sensors that have become synonymous with the burgeoning autonomous vehicle movement.”
Wayve’s machine learning algorithms are hardware and sensor-agnostic, meaning they can be used with any hardware or sensors, provided the manufacturer wants to. However, the real strength of Wayve’s approach is that their algorithms can learn and adapt to new situations.
Alex Kendall, Wayve confounder and CTO told VentureBeat: “Our algorithms are learning to become super-human drivers. We learn from attentive human driving, which already eliminates the 98.3% of human road errors due to inattention / ineffective driving. We then further improve beyond what humans are capable of with reinforcement learning, by providing feedback to our system.”
If Wayve can deliver on its premise, it’s a safe bet their tech will soon make its way into self-driving vehicles.