Researchers used an AI technique called reinforcement learning to help a two-legged robot nicknamed Cassie to run 400 meters, over varying terrains, and execute standing long jumps and high jumps, without being trained explicitly on each movement. Reinforcement learning works by rewarding or penalizing an AI as it tries to carry out an objective. In this case, the approach taught the robot to generalize and respond in new scenarios, instead of freezing like its predecessors may have done. "We wanted to push the limits of robot agility," says Zhongyu Li, a PhD student at University of California, Berkeley, who worked on the project, which has not yet been peer-reviewed. "The high-level goal was to teach the robot to learn how to do all kinds of dynamic motions the way a human does."

A two-legged robot that can chase you down in the street may sound like something dreamed up for the latest episode of Black Mirror. But it may not be far from reality, after a two-legged robot known as'Cassie' set a new Guinness World Record for the fastest 100 metres by a bipedal robot. Cassie clocked the historic time of 24.73 seconds, starting from a standing position and returning to that position after the sprint, with no falls. While that's more than 15 seconds slower than the world record for a 100-metre sprint by a human, held by Usain Bolt at 9.58 seconds, it is faster than most humans would take to jog the same distance. Oregon State robotics professor Jonathan Hurst, who led the development of the robot, described it as'a big watershed moment'.

Biped human walking and running is a complicated activity involving the coordination of complex motor, sensory and neural systems, [Holmes et al., 2006]. The description of all these processes and their coordination is an enormous task demanding detailed knowledge of many biological processes, eventually some of them unknown. The ability of humans to walk requires a long process of learning by trial and error, ultimately associated with the adaptation of several neural mechanisms during human development. Although the complexity of human walking, engineers, biologists, physicists, and mathematicians have joined efforts to build machines reproducing human movements and walking. Models describing the basic features of walking and running inspired the industry to create robots to perform some human activities [Adams et al., 2000].

DHL is using robotics to support numerous warehousing and logistics tasks. DHL innovates its logistics workflow and the tools and technologies deployed in DHL distribution centers around the world, as the company continually improves its efficiency. Sally Miller, DHL Supply Chain's chief information officer for North America, recently spoke to The Robot Report about the types of robots the company uses and the innovation cycle it employs to find the most effective solutions. Sally Miller will also be a keynote speaker at RoboBusiness, which takes place in Santa Clara on Oct 19-20, 2022. The full interview with Sally was featured on a recent episode of The Robot Report Podcast, which you can listen to here.

Cassie has made history as the first bipedal robot to complete a five-kilometer (5K) run, having done so in just over 53 minutes. Developed by Oregon State University, the two-legged machine with knees that bend like those of an ostrich, taught itself how to run through a deep reinforcement learning algorithm. Yesh Godse, an undergraduate in the lab, said in a statement: 'Deep reinforcement learning is a powerful method in AI that opens up skills like running, skipping and walking up and down stairs.' Cassie's total time of 53 minutes, three seconds, included about six and a half minutes of resets following two falls. Cassie first stumbled when its computer overheated and the other came after it took a turn at too high of a speed. The robot's makers foresee it eventually delivering packages, managing warehouse tasks and helping people in their homes.

Ford has announced that it is purchasing a new two-legged, two-armed robot produced by Agility Robotics, which the car-maker hopes will soon be walking around neighborhoods carrying parcels from the delivery vehicle right up to your door. Going by the name of Digit, the five-feet tall humanoid can navigate its way across urban settings ranging from sidewalks to flowerbeds in a surprisingly human-like manner, due to the mobile limbs attached to its upper torso. The uncanny valley effect is fortunately avoided thanks to the robot's lack of a head. Digit has only just gone on sale, and the reason that Agility can boast Ford as the very first buyer is that the robot provides a solution to the so-called "last 50 feet problem". In the home delivery industry 2.0, those 50 feet are the final steps between the autonomous vehicle carrying a customer's order, and that customer's doorstep.

Self-driving delivery vehicles may be getting closer to becoming a reality, but Ford believes there's one leg of the process that could be further solved by robots. The auto giant has partnered with startup Agility Robotics to create a two-legged robot called'Digit' that can ferry packages to your doorstep. It solves a problem generated by self-driving delivery vehicles, which is that if there's no humans in the driver's seat that can drop off a package, autonomous robots can pick up the slack. 'It's not always convenient for people to leave their homes to retrieve deliveries or for businesses to run their own delivery services,' Ken Washington, chief technology officer at Ford, wrote in a blog post. 'If we can free people up to focus less on the logistics of making deliveries, they can turn their time and effort to things that really need their attention.