jessygrizzle
Latest
U of M's Marlo robot uses algorithms to conquer uneven terrain
Robots walking unaided on flat ground is tough enough as it is -- just look at last year's class of DARPA Challenge failures -- so when one can handle uneven terrain in any direction (not just a straight line), we take notice. The latest example is Marlo, a joint project between University of Michigan's Jessy Grizzle and Oregon State University's Jonathan Hurst. The key difference here is how it achieves this feat: a bank of algorithms containing different instructions for different walking styles.
MABEL running robot snags bipedal speed title, cue 'Rocky' theme (video)
MABEL the running robot has been training hard, grabbing the title of "fastest bipedal robot with knees." Like any great sports star, it's been plagued by many dream-crushing obstacles and injuries, but this time it's done it: running at a speed of 6.8 miles per hour on a track. Jessy Grizzle, professor at the University of Michigan's Department of Electrical Engineering and Computer Science, attributes this bot's success to its human-like weight distribution -- a heavier torso and flexible legs with springs similar to tendons for movement "like a real runner." This bipedal technology, which can mimic a human's ability to run and climb over obstacles, may be used to help the disabled walk again, in rescue situations or as the basis of future vehicles that don't require roads or wheels to drive. If MABEL doesn't make the SWAT team this year, it can most certainly snag a spot as an extra in the next Transformers movie. Check out the PR and video of this modern day robo-Flo-Jo after the break.
