An insect-inspired “artificial brain” can guide a robot with little energy

British researchers drew inspiration from the brain function of certain insects (particularly bees and bumblebees) to design an autonomous navigation system that allows a robot to navigate its environment, including skillfully moving between obstacles, using less space and energy. The technology is currently being tested in delivery drones and mine inspection robots.

The system, which mimics the way bees and other insects navigate, was developed by the British company Opteran Technologies. It includes a specialized computer chip and two inexpensive CMOS cameras, providing a 360-degree view. It can be connected to various robots and drones.

The set weighs only 30 grams and consumes less than 3 watts of electricity in standard operation. That’s a fraction of what most robot control systems need, says David Rajan, CEO of Opteran. “Our algorithms are so light that we can run them on tiny chips and they are also incredibly fast,” he adds.

Imitate the best of nature …

“It extracts 600 million years of evolution in silicon”, we can read on the home page of the company’s website, or “Nature has solved the question of autonomy beyond Deep Learning”. Behind this potentially revolutionary technology is the work of James Marshall of the University of Sheffield (UK), who is also Opteran’s Chief Scientific Officer.

Combining behavioral studies and recordings of the insects’ neural activity, his team reconstructed the brain circuits they use for navigation. The software that runs on these circuits is similar to the neural networks used by artificial intelligence, explains Marshall. But instead of learning to solve tasks by training with a large amount of data, it is programmed to mimic the brain structures responsible for insects’ innate navigational abilities. Opteran simply calls it a “natural intelligence system.”

The researchers showed that a pair of their algorithms could guide a robot dog through a maze of cardboard boxes. The first algorithm gathers the data provided by the cameras to create a stabilized panoramic view. The second mimics the way insects analyze optical flow (that is, movement in a visual scene) to estimate speed and avoid collisions.

Opteran is also working on algorithms that allow robots to map their environment and make decisions by evaluating different targets. Several customers are currently testing the company’s technology, including delivery drones and mine inspection robots.

PHP Script, Elementor Pro Weadown, WordPress Theme, Fs Poster Plugin Nulled, Newspaper – News & WooCommerce WordPress Theme, Wordfence Premium Nulled, Dokan Pro Nulled, Plugins, Elementor Pro Weadown, Astra Pro Nulled, Premium Addons for Elementor, Yoast Nulled, Flatsome Nulled, Woocommerce Custom Product Ad, Wpml Nulled,Woodmart Theme Nulled, PW WooCommerce Gift Cards Pro Nulled, Avada 7.4 Nulled, Newspaper 11.2, Jannah Nulled, Jnews 8.1.0 Nulled, WP Reset Pro, Woodmart Theme Nulled, Business Consulting Nulled, Rank Math Seo Pro Weadown, Slider Revolution Nulled, Consulting 6.1.4 Nulled, WeaPlay, Nulledfire

Back to top button