Cambridge-based artificial intelligence start-up, PROWLER.io, has secured £10 million in series A funding, in a round led by Cambridge Innovation Capital with further investment from Atlantic Bridge Capital. Existing investors Passion Capital, Amadeus Capital Partners and SGInnovate reiterated their ongoing support for PROWLER.io by participating in the round.

With the funding, PROWLER.io aims to further develop the world’s first AI powered decision-making platform, that makes it possible to perceive and affect the ways in which vehicles, drones and even people interact in complex environments.

Specifically, the funding will be used to expand its world-leading team of researchers and continue development and commercialisation of its platform, says CEO Vishal Chatrath. The team current comprises experts in machine learning, probabilistic modelling, Gaussian processes, reinforcement learning, decision theory, multi agent systems and game theory—all of which goes into the company’s aim to build an AI decision making platform on a foundation of interpretable principles of mathematics and learning. “As a team, we are ready and eager to take the business to the next stage and continue solving some of the hardest machine learning problems to deliver the world’s first principled AI decision making platform,” Chatrath says.

PROWLER.io has the potential to transform complex systems design and implementation. With the advancements in self-driving technology, autonomous vehicles slowly inching to the mainstream. But it is impossible to programme autonomous vehicles for every eventuality they will face on the roads. PROWLER.io uses probabilistic modelling to help a self-driving car to “understand” itself and its environment, multiple principled learning approaches to teach it to drive and multi-agent systems to ensure that it operates safely alongside other road users.

In game development, PROWLER.io agents supersede the use of hand-crafted rules for decision making, which are time consuming, expensive and restrictive. The result is games that feel truly open and responsive and engage players in novel, freer, more personalised ways. Moreover, development costs and time to market decrease when testing is handled by teams of humans working with agents that can perform repetitive tasks thousands of times faster than manual testers.

In the context of smart cities, the platform optimises fleet planning and management. This ensures that real time demand for AVs matches supply, vehicles are close by when needed, routes are planned efficiently, congestion is reduced and negative environmental impacts are minimised.

Its core technology is founded on mathematical principles from three previously segregated fields: probabilistic modelling, machine learning and game theory. By merging these three fields, the platform allows for decision-making based on interpretable principles for the first time ever. The platform uses powerful statistical tools to generate flexible, dynamic probabilistic models which provide new insights about virtual or physical environments; machine learning and decision-making methodologies that are more visible and interpretable than those that take place within deep neural nets; and multi-agent systems that are much more flexible, adaptable and strategically interactive than traditional decision-tree based systems.