Like humans, robots often need to learn things the hard way. For super complex automatons, like Boston Dynamics' Atlas, that can mean understanding the complexities of human bullying. But in the case of this bumbling bot named MARLO, it's just something as simple as trying — and failing — to walk across a hilly field.
MARLO is being designed by an engineering team at the University of Michigan. Although its walking capabilities look like MARLO is on the rough end of a day-long bender, MARLO's ability to traverse such uneven terrain would be a big step forward for robotics. According to the University of Michigan, the team will be working on MARLO's gait algorithms over the winter before it tries out the impromptu course, an art installation called the Wave Field, a second time.
To test outside, the team had to develop a human-operated gantry that could prevent MARLO from being severely damaged after a fall. The 60-90cm mounds, which the team describes as "merely very difficult", are a much bigger challenge than the small, man-made terrain MARLO successfully traversed inside the roboticists' own lab this past May.
The MARLO team is developing its robotic walking algorithm to be specific enough for its own machine, but also broad enough so that future robots can take advantage of everything they're building. Researchers are already using the algorithm to improve advanced prosthetics.
Keep trying, buddy.