Using an evolutionary Process to Design robots for exploring other planets

It’s been suggested that an advance party of robots will be needed if humans are ever to settle on other planets. Sent ahead to create conditions favorable for humankind, these robots will need to be tough, adaptable and recyclable if they’re to survive within the inhospitable cosmic climates that await them.

Collaborating with roboticists and computer scientists, have been working on just such a set of robots. Produced via 3D printer and assembled autonomously, the robots continually evolve in order to rapidly optimize for the conditions they find themselves in.

Robots have come a long way since the first clumsy forays into artificial movement many decades ago. Today, companies such as Boston Dynamics produce ultra-efficient robots which are capable and mobile enough to load up trucks, build pallets, and move boxes around factories, undertaking tasks you might think only humans could perform.

Despite these advances, designing robots to work in unknown or inhospitable environments, like exoplanets or deep ocean trenches, still poses a considerable challenge for scientists and engineers.

An impossible brainteaser for humans, nature has already solved this problem. Evolution has resulted in millions of species that are perfectly adapted to their environment. Although biological evolution takes millions of years, artificial evolution, modeling evolutionary processes inside a computer, can take place in hours, or even minutes. Computer scientists have been harnessing its power for decades, resulting in gas nozzles to satellite antennas that are ideally suited to their function, for instance.

Any evolved robots will need to be capable of sensing their environment and have diverse means of moving, for example using wheels, jointed legs, or even mixtures of the two. And to address the inevitable reality gap that occurs when transferring a design from software to hardware, it is also desirable for at least some evolution to take place in hardware, within an ecosystem of robots that evolve in real time and real space.

The Autonomous Robot Evolution project addresses exactly this, bringing together scientists and engineers from four universities in an ambitious four-year project to develop this radical new technology.

As depicted above, robots will be born through the use of 3D manufacturing. A new kind of hybrid hardware-software evolutionary architecture for design. That means that every physical robot has a digital clone. Physical robots are performance-tested in real-world environments, while their digital clones enter a software program, where they undergo rapid simulated evolution. This hybrid system introduces a novel type of evolution: new generations can be produced from a union of the most successful traits from a virtual mother and a physical father.

As well as being rendered in our simulator, child robots produced via our hybrid evolution are also 3D printed and introduced into a real-world, creche-like environment.

Two years into the project, significant advances have been made. From a scientific perspective, we have designed new artificial evolutionary algorithms that have produced a diverse set of robots that drive or crawl, and can learn to navigate through complex mazes.

The first major use case plans to address is deploying this technology to design robots to undertake clean-up of legacy waste in a nuclear reactor. Using humans for this task is both dangerous and expensive, and necessary robotic solutions remain to be developed.

Looking forward, the long-term vision is to develop the technology sufficiently to enable the evolution of entire autonomous robotic ecosystems that live and work for long periods in challenging and dynamic environments without the need for direct human oversight.