It is suggested that an advance party of robots would be needed if humans ever wanted to settle on other planets. These robots, sent forward to create favorable conditions for mankind, will have to be tough, adaptable and recyclable to survive within the inhospitable cosmic climate that awaits them.
My team and I work with robotics and computer scientists and work on just such a set of robots. The robots we create are manufactured using a 3D printer and compiled autonomously to quickly optimize for the conditions in which they operate.
Our work represents the latest advances towards the kind of autonomous robotic ecosystems that can help build the future homes of mankind, far away from the earth and far away from human supervision.
Robot ugly
Robots have come a long way since our first clumsy invasion of artificial motion many decades ago. Currently, companies like Boston Dynamics manufacture ultra-efficient robots that load trucks, build pallets, and move boxes in factories and perform tasks that you think only humans can perform.
Despite this progress, designing robots to work in unfamiliar or inhospitable environments – such as exoplanets or deep ocean trenches – remains a major challenge for scientists and engineers. What shape and size should the ideal robot be outside the cosmos? Should it crawl or walk? What tools does he need to manipulate his environment – and how will it survive extreme pressure, temperature and chemical corrosion?
[Read: How much does it cost to buy, own, and run an EV? It’s not as much as you think]
Nature is an impossible brain-breaker for man and has already solved the problem. Darwinist evolution has led to millions of species that are perfectly adapted to their environment. Although biological evolution takes millions of years, artificial evolution – the modeling of evolutionary processes within a computer – can take place within hours, or even minutes. Computer scientists have been using its power for decades, leading to gas nozzles to satellite antennas that are ideal for their function, for example.
But the current artificial evolution of moving, physical objects still requires a great deal of human supervision, requiring a close feedback loop between robot and human. If artificial evolution is to design a useful robot for exoplanetary exploration, we must remove man from the loop. In essence, evolving robotic designs have to manufacture, assemble and test themselves autonomously – independent of human supervision.
Unnatural selection
Any developed robot should be able to sense their environment and have different ways of moving – for example using wheels, joint legs or even mixtures of the two. And to address the inevitable reality gap that occurs when a software design is transferred to hardware, it is also desirable that at least some evolution in hardware takes place – within an ecosystem of robots operating in real-time and real-time space developed.
The Autonomous Robot Evolution (ARE) project addresses exactly this and brings 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” using 3D manufacturing. We use a new kind of hybrid hardware software evolutionary architecture for design. This means that every physical robot has a digital clone. Physical robots are tested for performance in real-world environments, while their digital clones enter a software program, where they quickly undergo a simulated evolution. This hybrid system introduces a new type of evolution: new generations can be produced from a union of the most successful traits of a virtual ‘mother’ and a physical ‘father’.
In addition to being rendered in our simulator, ‘child robots’ produced by our hybrid evolution are also 3D-printed and introduced in a real, crèche-like environment. The most successful individuals within this physical training center make their ‘genetic code’ available for reproduction and for the betterment of future generations, while less “suitable” robots can simply be hoisted away and recycled into new ones as part of an ongoing evolutionary cycle.
Two years after the project, significant progress has been made. From a scientific perspective, we have designed new artificial evolutionary algorithms that produce a variety of robots that drive or crawl and can learn to navigate through complex mazes. These algorithms develop both the body plan and the brain of the robot.
The brain contains a controller that determines how the robot moves, interprets sensory information from the environment and translates it into motor controls. Once the robot is built, a learning algorithm quickly refines the child brain to take into account the possible mismatch between the new body and the hereditary brain.
From an engineering perspective, we designed the ‘RoboFab’ to fully automate manufacturing. This robot arm attaches wires, sensors and other ‘organs’ selected by evolution to the 3D chassis of the robot. We designed these components to facilitate quick assembly, giving the RoboFab access to a large toolbox with robotic limbs and organs.
Litter removal
The first major use case we plan to address is the use of this technology to design robots to clean up the waste in a nuclear reactor – as seen in the TV miniseries Chernobyl. The use of humans for this task is dangerous and expensive, and the necessary robot solutions have yet to be developed.
Looking ahead, the long-term vision is to develop the technology sufficiently to enable the evolution of entire autonomous robotic ecosystems that live and work in challenging and dynamic environments for long periods of time without the need for direct human oversight.
In this radical new paradigm, robots are conceived and born, rather than designed and manufactured. Such robots will fundamentally change the concept of machines and introduce a new breed that can change their shape and behavior over time – just like us.
This article by Emma Hart, Chair of Natural Computation, Napier University of Edinburgh, is published from The Conversation under a Creative Commons license. Read the original article.
Read the following:
Secure all your online data with this highly rated VPN for sale today