Cambridge Prowler bags up £10m
- 著者:Ella Cai
- 公開::2017-09-06
Cambridge Innovation Capital (CIC) has led a £10 million Series A funding round for PROWLER.io which develops based on interpretable principles of mathematics and learning.
“This investment allows us to expand our world-leading team of academics and developers,” says PROWLER CEO Vishal Chatrath (pictured) “we will continue to solve some of the world’s hardest machine learning problems.”
PROWLER’s technology allows users to observe and predict the way agents – such as vehicles, drones, robots, characters in games and even people – interact in complex environments, thus providing users with an understanding of the millions of micro-decisions that can occur in dynamic systems
The platform combines three core mathematical areas: machine learning, probabilistic modelling and game theory to provide new insights into virtual and physical environments.
Its agent-based machine learning methodology is more interpretable than traditional deep neural nets and its multi-agent systems are more adaptable and strategically interactive than decision-tree based systems.
PROWLER.io’s platform has many potential uses but is initially focusing on game development, autonomous vehicles (AVs), drones, robotics and smart cities.
In game development, PROWLER.io’s platform replaces the use of hand-crafted rules, which are time consuming, expensive and restrictive for decision making. This produces games that feel open and responsive and engage players in novel, more personalised ways.
In addition, PROWLER.io’s agents can be designed to perform repetitive tasks thousands of times faster than manual testers, thus significantly reducing game development costs and time to market.
It is impossible to program AVs for every eventuality they will face on the roads.
PROWLER.io’s technology uses probabilistic modelling to enable a self-learning car to “understand” itself and its environment.
Multiple principled learning approaches are used to teach it to drive, together with multi-agent systems to ensure that it operates safely alongside other road users.
In 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.
“This investment allows us to expand our world-leading team of academics and developers,” says PROWLER CEO Vishal Chatrath (pictured) “we will continue to solve some of the world’s hardest machine learning problems.”
PROWLER’s technology allows users to observe and predict the way agents – such as vehicles, drones, robots, characters in games and even people – interact in complex environments, thus providing users with an understanding of the millions of micro-decisions that can occur in dynamic systems
The platform combines three core mathematical areas: machine learning, probabilistic modelling and game theory to provide new insights into virtual and physical environments.
Its agent-based machine learning methodology is more interpretable than traditional deep neural nets and its multi-agent systems are more adaptable and strategically interactive than decision-tree based systems.
PROWLER.io’s platform has many potential uses but is initially focusing on game development, autonomous vehicles (AVs), drones, robotics and smart cities.
In game development, PROWLER.io’s platform replaces the use of hand-crafted rules, which are time consuming, expensive and restrictive for decision making. This produces games that feel open and responsive and engage players in novel, more personalised ways.
In addition, PROWLER.io’s agents can be designed to perform repetitive tasks thousands of times faster than manual testers, thus significantly reducing game development costs and time to market.
It is impossible to program AVs for every eventuality they will face on the roads.
PROWLER.io’s technology uses probabilistic modelling to enable a self-learning car to “understand” itself and its environment.
Multiple principled learning approaches are used to teach it to drive, together with multi-agent systems to ensure that it operates safely alongside other road users.
In 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.