24 November 2020

Next generation of autonomy inspired by insects being developed by University of Sheffield spin out

Engineers from the University of Sheffield are developing the next generation of autonomy as part of a pioneering new spin out company.

A close up of the face of a bee against a black background
  • University of Sheffield researchers are developing the next generation of autonomy as part of a pioneering new spin out company
  • The start-up is developing lightweight, low cost silicon brains to enable robots and autonomous vehicles to see, sense, navigate and make decisions
  • Autonomy is based on the brains of insects capable of sophisticated decision making and navigation using optic flow to perceive depth and distance
  • Brain biomimicry is a far more efficient, robust and transparent way to achieve autonomy than current deep learning techniques and could be used to produce a wide variety of autonomous vehicles, drones, mining robots and even off-planet vehicles with real-time autonomous decision-making

Engineers from the University of Sheffield are developing the next generation of autonomy as part of a pioneering new spin out company.

Based on eight years of research led by Professor James Marshall and Dr Alex Cope from the University’s Department of Computer Science, Opteran is pioneering lightweight, low cost silicon brains to enable robots and autonomous vehicles to see, sense, navigate and make decisions.

Inspired by the brains of insects, the company believes its approach to autonomy called Natural Intelligence will significantly expand the potential addressable market for autonomy in machines and robotics.

Although insects have smaller brains than humans, they are capable of sophisticated decision making and navigation using optic flow to perceive depth and distance. This is a far more efficient, robust and transparent way to achieve autonomy than current deep learning techniques, which has inspired Opteran to reverse-engineer insect brains to produce algorithms requiring no data centre or extensive pre-training.

This means Opteran’s new solutions for autonomy can mimic tasks such as seeing, sensing objects, obstacle avoidance, navigation and decision making. In a recent trial, Opteran’s AI was able to control a sub-250g drone, with complete onboard autonomy, using fewer than 10,000 pixels from a single low-resolution panoramic camera.

This is the next exciting step in commercialising our bio-inspired solutions to autonomy; I am looking forward to working with our investors and partners to realise our ambition of redefining how autonomous systems are built.

Professor James Marshall

Professor of Theoretical and Computational Biology at the University of Sheffield

Weighing approximately 30g, and integrating Opteran technology drawing less than a watt of power, the Opteran Development Kit (ODK) will enable their solutions to be integrated into a wide variety of applications in the robotics market, which is expected to grow to $77 billion  by 2022.

Opteran’s technology could transform the use case for a wide variety of autonomous vehicles, drones, mining robots and even off-planet vehicles, as it will enable robust real-time autonomous decision-making.

Opteran has just secured £2.1 million in seed funding in a round-led by  IQ Capital with Episode1, Join and Seraphim Capital. In the next 18 months, Opteran will use this funding to build out functionality in the algorithms and chipsets, including launching Opteran Sense for obstacle avoidance and reactive navigation, Opteran Direct for SLAM, Opteran Decide for autonomous decision-making, and Opteran See - a 360 degree camera.

The spin out will also look to expand its engineering and commercial team, and has recently launched a Development Kit to enable partners to embed its technology in their applications.

James Marshall, Professor of Theoretical and Computational Biology at the University of Sheffield and Chief Scientific Officer at Opteran, said: “This is the next exciting step in commercialising our bio-inspired solutions to autonomy; I am looking forward to working with our investors and partners to realise our ambition of redefining how autonomous systems are built.”

David Rajan, Chief Executive Officer of Opteran, said: “2021 will be the year when Natural Intelligence will challenge deep learning in solving some of the most fundamental short-comings in autonomous applications and our latest funding round will set Opteran on a path to be at the forefront of this next wave.

“Already in a position to demonstrate the technology, we are confident that Natural Intelligence will become highly sought after as the way to deliver lightweight, low-cost and effective autonomy in a radically new way that will open up huge growth opportunities for robotics.”
Opteran

Computer Science at the University of Sheffield


Contact

For further information please contact: