In case just being a headless cheetah robot wasn't scary enough, a group of researchers at the Massachusetts Institute of Technology (MIT) have now given their robot the ability to autonomously detect oncoming objects and jump over them.
This is no easy feat. The robot doesn't just hop, it relies on a visual system that maps terrain using reflections from a laser to spot an obstacle and calculate when and where it needs to take off, and then automatically adjusts its stride accordingly.
"A running jump is a truly dynamic behavior," Sangbae Kim, an assistant professor of mechanical engineering, told MIT News. "You have to manage balance and energy, and be able to handle impact after landing. Our robot is specifically designed for those highly dynamic behaviors."
But perhaps most impressive is that unlike how you might assume a robot works, the headless cheetah doesn't necessarily look for the optimal takeoff location, just one that will work.
"If you want to optimize for, say, energy efficiency, you would want the robot to barely clear the obstacle—but that’s dangerous, and finding a truly optimal solution would take a lot of computing time," Kim said. "In running, we don’t want to spend a lot of time to find a better solution. We just want one that’s feasible."
On a treadmill—with very little time to prepare itself—the robot cleared about 70 percent of the hurdles up to 18 inches (over half its height) tall. Out on a track, with room to really stretch its horrifying, sci-fi legs, it improved to clear about 90 percent.