MIT’s newest robot, the Cheetah 3, is unlike any of its predecessors, as it can now easily leap, gallop across rough terrain, and even climb a staircase littered with debris. When suddenly yanked or shoved, it can quickly recover its balance, all the while essentially blind, thanks to new vision-free algorithms.



Its innovative contact detection algorithm helps the robot determine the best time to transition between a leg between swing and step by constantly calculating for each leg three probabilities: the probability of a leg making contact with the ground, the force generated once the leg hits the ground, and that the leg will be in mid-swing. The algorithm calculates this data based on data from gyroscopes, accelerometers, and joint positions of the legs, which record the leg’s angle and height with respect to the ground.

Petoi Robot Dog Bittle Robotics Kit (Pre-Assembled) | App Control Quadruped Smart Robot | Open Source...
  • Coding robot dog: create new behaviors with block-based coding/Python/C++ and visually design new robot skills. Code Bittle Robotics Kit to perceive...
  • Fun remote-control: offers 1-hour playtime with 35+ built-in lifelike movements & remote control or app-operated tricks powered by high performance...
  • Engaging robotics education: inspire students of ages 10+ & adults to explore robotics & coding. Ideal for K12 schools, colleges, robotics camps,...


Author

A technology, gadget and video game enthusiast that loves covering the latest industry news. Favorite trade show? Mobile World Congress in Barcelona.