Robots rising<\/h2>\n
Robots have come a long way since our first clumsy forays into artificial movement many decades ago. Today, companies such as Boston Dynamics produce ultra-efficient robots<\/a> that load trucks, build pallets, and move boxes around factories, undertaking tasks you might think only humans could perform.<\/p>\n Despite these advances, designing robots to work in unknown or inhospitable environments \u2013 like exoplanets or deep ocean trenches \u2013 still poses a considerable challenge for scientists and engineers. Out in the cosmos, what shape and size should the ideal robot be? Should it crawl or walk? What tools will it need to manipulate its environment \u2013 and how will it survive extremes of pressure, temperature, and chemical corrosion?<\/p>\n [Read: How much does it cost to buy, own, and run an EV? It\u2019s not as much as you think<\/span><\/a>]<\/em><\/p>\n An impossible brainteaser for humans, nature has already solved this problem. Darwinian evolution has resulted in millions of species that are perfectly adapted to their environment. Although biological evolution takes millions of years, artificial evolution<\/a> \u2013 modeling evolutionary processes inside a computer \u2013 can take place in hours, or even minutes. Computer scientists have been harnessing its power for decades, resulting in gas nozzles to satellite antennas<\/a> that are ideally suited to their function, for instance.<\/p>\n But current artificial evolution of moving, physical objects still requires a great deal of human oversight, requiring a tight feedback loop between robot and human. If artificial evolution is to design a useful robot for exoplanetary exploration, we\u2019ll need to remove the human from the loop. In essence, evolved robot designs must manufacture, assemble and test themselves autonomously \u2013 untethered from human oversight.<\/p>\n Any evolved robots will need to be capable of sensing their environment and have diverse means of moving \u2013 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 \u2013 within an ecosystem of robots that evolve in real-time<\/span> and real space.<\/p>\n The Autonomous Robot Evolution (ARE<\/a>) project addresses exactly this, bringing together scientists and engineers from four universities in an ambitious four-year project to develop this radical new technology.<\/p>\n As depicted above, robots will be \u201cborn\u201d through the use of 3D manufacturing. We use a new kind of hybrid hardware-software<\/span> evolutionary architecture for design. That means that every physical robot has a digital clone. Physical robots are performance-tested in real-world<\/span> 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 \u201cmother\u201d and a physical \u201cfather.\u201d<\/p>\n As well as being rendered in our simulator, \u201cchild\u201d robots produced via our hybrid evolution are also 3D-printed and introduced into a real-world<\/span>, creche-like environment. The most successful individuals within this physical training center make their \u201cgenetic code\u201d available for reproduction and for the improvement of future generations, while less \u201cfit\u201d robots can simply be hoisted away and recycled into new ones as part of an ongoing evolutionary cycle.<\/p>\n Two years into the project, significant advances have been made. From a scientific perspective, we have designed new artificial evolutionary algorithms<\/a> that have produced a diverse set of robots that drive or crawl and can learn to navigate through complex mazes. These algorithms evolve both the body-plan<\/a>, and brain of the robot.<\/p>\n The brain<\/a> contains a controller that determines how the robot moves, interpreting sensory information from the environment and translating this into motor controls. Once the robot is built, a learning algorithm<\/a> quickly refines the child brain to account for any potential mismatch between its new body and its inherited brain.<\/p>\n From an engineering perspective, we have designed the \u201cRoboFab<\/a>\u201d to fully automate manufacturing<\/a>. This robotic arm attaches wires, sensors, and other \u201corgans\u201d chosen by evolution to the robot\u2019s 3D-printed chassis. We designed these components to facilitate swift assembly, giving the RoboFab access to a big toolbox<\/a> of robot limbs and organs.<\/p>\n The first major use case we plan to address is deploying this technology to design robots to undertake clean-up of legacy waste in a nuclear reactor \u2013 like that seen in the TV miniseries Chernobyl. Using humans for this task is both dangerous and expensive, and necessary robotic solutions<\/a> remain to be developed.<\/p>\n Looking forward, the long-term vision is to develop the technology sufficiently to enable the evolution of entire autonomous robotic ecosystems<\/a> that live and work for long periods in challenging and dynamic environments without the need for direct human oversight.<\/p>\n In this radical new paradigm, robots are conceived and born, rather than designed and manufactured. Such robots will fundamentally change the concept of machines, showcasing a new breed that can change their form and behavior over time \u2013 just like us. This article by Emma Hart<\/a>, Chair in Natural Computation, Edinburgh Napier University<\/a> is republished from The Conversation<\/a> under a Creative Commons license. Read the original article<\/a>.<\/em><\/p>\nUnnatural selection<\/h2>\n
Waste disposal<\/h2>\n
![\"The](\"https:\/\/counter.theconversation.com\/content\/153159\/count.gif?distributor=republish-lightbox-basic\")
<\/p>\n