Bipedal robot achieves Guinness World Record

Cassie was produced by Oregon State University spinout Agility Robotics. Developed under the direction of Oregon State robotics professor Jonathan Hurst with a 16-month, $1 million grant from the Defence Advanced Research Projects Agency (DARPA), Cassie is the first bipedal robot to use machine learning to control a running gait on outdoor terrain.

Starting from a standing position and returning to that position after the sprint, with no falls, Cassie clocked a time of 24.73 seconds at OSU’s Whyte Track and Field Centre.

This isn’t the first record for the robot – in 2021, Cassie traversed five kilometres in just over 53 minutes. This was untethered and on a single battery charge.

“We have been building the understanding to achieve this world record over the past several years, running a 5K and also going up and down stairs,” said graduate student Devin Crowley, who led the Guinness effort. “Machine learning approaches have long been used for pattern recognition, such as image recognition, but generating control behaviours for robots is new and different.

“Completing a 5K was about reliability and endurance, which left open the question of, how fast can Cassie run? That led the research team to shift its focus to speed.”

The robot has knees that bend like an ostrich and operates with no cameras or external sensors. It has been put through a range of training experiences, including a full year of training in a simulated environment. A computing technique called parallelisation was also used – this is where multiple processes and calculations happen at the same time.

“Cassie can perform a spectrum of different gaits but as we specialised it for speed we began to wonder, which gaits are most efficient at each speed?” Crowley said. “This led to Cassie’s first optimised running gait and resulted in behaviour that was strikingly similar to human biomechanics.”

The challenge remains to get Cassie to reliably start from a free-standing position, run, and then return to the free-standing position without falling. “Starting and stopping in a standing position are more difficult than the running part, similar to how taking off and landing are harder than actually flying a plane,” artificial intelligence professor Alan Fern said. “This 100-metre result was achieved by a deep collaboration between mechanical hardware design and advanced artificial intelligence for the control of that hardware.”

Hurst, Chief Technology Officer at Agility Robotics, and a robotics professor at Oregon State, called the Guinness-recognised accomplishment “a big watershed moment.”

“This may be the first bipedal robot to learn to run, but it won’t be the last,” he said. “I believe control approaches like this are going to be a huge part of the future of robotics. The exciting part of this race is the potential. Using learned policies for robot control is a very new field, and this 100-meter dash is showing better performance than other control methods. I think progress is going to accelerate from here.”