Prowler.io is a Cambridge-based start-up, founded by Vishal Chatrath, Dr. Dongho Kim and Aleksi Tukianien. The company has a world-class team of leading experts in machine learning, probabilistic modelling, gaussian processes, reinforcement learning, principled decision making, multi agent systems and game theory. Prowler.io is using this expertise to build an AI decision-making platform on a foundation of interpretable principles of mathematics and learning.
Prowler.io's platform helps customers understand, guide and optimise the millions of micro-decisions that can occur in their dynamic systems. It can uncover hidden relations between events in complex environments and could transform fields such as game design, autonomous vehicles and smart city planning.
The platform is built on three core areas: probabilistic modelling, principled machine learning and game theory.
The combination of these approaches provides a decision-making platform which has:
- powerful statistical tools that can generate flexible probabilistic models of virtual or physical environments;
- principled learning and decision-making methodologies that are more visible and interpretable than those that take place within deep neural nets;
- truly autonomous agents that are much more flexible, adaptable and strategically interactive than traditional decision-tree based expert systems.
Prowler.io is initially focusing on game development, autonomous vehicles (AVs), drones, robotics and smart cities. Its models can simulate complex dynamic environments in which emerging technologies can safely be trained, tested and validated.
In game development, Prowler.io is seeking to supercede the use of hand-crafted rules for decision making, which are time consuming, expensive and restrictive. The result should be games that feel truly open and responsive and engage players in novel, freer, more personalised ways. Development costs and time to market should also fall when testing is handled by electronic agents that can do dull, repetitive jobs a thousand times faster than manual testers.
It is impossible to program autonomous vehicles for every eventuality they will face on the roads. Prowler.io’s technology should enable self-learning cars to cope with constantly changing road and traffic conditions. The platform will use probabilistic modelling to enable 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 smart cities, the platform will enable optimised fleet planning and management. This will ensure 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.
CIC led a £10 million series A funding round for Prowler.io in July 2017.