Home Electronics None are safe from MIT’s jumping robot cheetah

None are safe from MIT’s jumping robot cheetah

Who can escape a robot cheetah? Not you, that’s who. MIT’s robot cheetah could already run without tethers. Now, the bot can autonomously run and jump over obstacles. In the latest experiments, the machine was able to identify and clear objects as tall as 18 inches, or over half its height – all while maintaining an average speed of five miles per hour while running on a treadmill.

“A running jump is a truly dynamic behavior,” says Sangbae Kim, an assistant professor of mechanical engineering at MIT. “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.”

What sort of “dynamic behaviors?” Chasing someone down a debris-lined alleyway, or through their own tastefully appointed home, perhaps? The engineers are mum on the specifics.

The robot’s process for making the running jump is more or less identical to a human’s, though that the process takes place within a controlled mechanical system makes it all the more remarkable. The cheetah first identifies the obstacle, estimates its distance and height, times its stride and finally chooses the right amount of force to apply to the ground.

When MIT engineers enabled the robotic cheetah to run without guides or tethers last year, it was doing so “blind” – it had no on-board visual systems, and relied on the watchful eyes of its operators. The jumping breakthrough is made possible by the installation of a LIDAR system, which uses lasers to map the world ahead of it. The LIDAR, in conjunction with the algorithms designed by engineers, allow the robot cheetah to make adjustments in about 100 milliseconds, or half of a stride.

The researchers say that with everything involved, they aren’t attempting to create a “perfect” robot cheetah. Instead, they’re looking for something that’s just good enough.

“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 says. “In running, we don’t want to spend a lot of time to find a better solution. We just want one that’s feasible.”

When hunting the most dangerous game (man), feasibility, not optimization, is paramount.