Dubbed Cassie, the running robot was developed under the direction of robotics professor Jonathan Hurst with a 16-month, $1m grant from the US Defence Advanced Research Projects Agency (DARPA).
Cassie, the first bipedal robot to use machine learning to control a running gait on outdoor terrain, completed the 5K on Oregon State’s campus untethered on a single battery charge.
“The Dynamic Robotics Laboratory students in the OSU College of Engineering combined expertise from biomechanics and existing robot control approaches with new machine learning tools,” said Hurst, who co-founded Agility in 2017. “This type of holistic approach will enable animal-like levels of performance. It’s incredibly exciting.”
Cassie, designed with knees that bend like an ostrich’s, taught itself to run using a deep reinforcement learning algorithm. Running requires dynamic balancing and Cassie is said to have learned to make infinite subtle adjustments to stay upright while moving.
“Cassie is a very efficient robot because of how it has been designed and built, and we were really able to reach the limits of the hardware and show what it can do,” said Jeremy Dao, a Ph.D. student in the Dynamic Robotics Laboratory.
“Deep reinforcement learning is a powerful method in AI that opens up skills like running, skipping and walking up and down stairs,” added Yesh Godse, an undergraduate in the lab.
In addition to logistics work like package delivery, bipedal robots eventually will have the intelligence and safety capabilities to help people in their own homes, Hurst said.
During the 5K, Cassie’s total time of 53 minutes, 3 seconds included about 6.5 minutes of resets following two falls: one because of an overheated computer, the other because the robot was asked to execute a turn at a high speed.