Nimble Atlas robot ups its game again to conquer tricky terrain



  • We take many of the things we do as humans for granted, such as balancing, but our bodies make thousands of adjustments every second just standing still and getting a robot to mimic what comes naturally to us isn’t as easy as you think


After showing off it’s impressive better-than-a-human balancing skills to the world earlier this year it looks like the worlds most advanced humanoid robot, Atlas, from Boston Dynamics has a new party trick thanks to a new algorithm created at the Florida Institute for Human & Machine Cognition (IHMC). And while you might be forgiven for thinking that walking across tricky terrain is nothing special, let me remind you that in order for you just to stand still your brain and your muscles are making thousands of adjustments and calculations every second.

Go on try it… see?

So trying to get a robot to do it – particularly a bi-pedal robot is an astonishing feat, and as they get better at it, yes, one day they’ll be able to sprint down the street or through woods after you when the robot rising eventually comes, or, alternatively, when they take over the police force.

Think about that… now get onto that running machine down the gym.


As marketing gets automated Revolve show off their AI generated billboards


The IHMC’s Atlas team says that the new control algorithm works by helping Atlas determine a solid foothold by letting it shift the weight of its outstretched foot to figure out what the optimum balance is, and once a steady footing is achieved it then does a quick step onto the next position, heaving its torso up and moving its other leg forward. And so on and so on. You get the picture.

Furthermore Atlas doesn’t need to know what sort of terrain is coming up next, and is capable of maintaining balance even when its foot is placed on thin contact points, such as building blocks set at an angle and, bearing in mind that one of Atlas’ possible applications is for it to be used in search and reduce missions this might be a handy skill to have but one day it’ll inevitably pose a problem for the team because once it becomes autonomous – which will simply be a matter of when not if, then it’ll be able to go off on its own with impunity.

The video below shows the robot’s steady progress across a brick-strewn divide.



About author

Matthew Griffin

Matthew Griffin, described as “The Adviser behind the Advisers” and a “Young Kurzweil,” is the founder and CEO of the World Futures Forum and the 311 Institute, a global Futures and Deep Futures consultancy working between the dates of 2020 to 2070, and is an award winning futurist, and author of “Codex of the Future” series. Regularly featured in the global media, including AP, BBC, Bloomberg, CNBC, Discovery, RT, Viacom, and WIRED, Matthew’s ability to identify, track, and explain the impacts of hundreds of revolutionary emerging technologies on global culture, industry and society, is unparalleled. Recognised for the past six years as one of the world’s foremost futurists, innovation and strategy experts Matthew is an international speaker who helps governments, investors, multi-nationals and regulators around the world envision, build and lead an inclusive, sustainable future. A rare talent Matthew’s recent work includes mentoring Lunar XPrize teams, re-envisioning global education and training with the G20, and helping the world’s largest organisations envision and ideate the future of their products and services, industries, and countries. Matthew's clients include three Prime Ministers and several governments, including the G7, Accenture, Aon, Bain & Co, BCG, Credit Suisse, Dell EMC, Dentons, Deloitte, E&Y, GEMS, Huawei, JPMorgan Chase, KPMG, Lego, McKinsey, PWC, Qualcomm, SAP, Samsung, Sopra Steria, T-Mobile, and many more.


Your email address will not be published. Required fields are marked *