New Framework Allows Four-Legged Robots to Move Efficiently and at High Speeds

Stress response of a biped robot after skidding on terrain. Credit: Jin et al

Researchers at Zhejiang University and the ZJU-Hangzhou Global Scientific and Technological Center have developed a new framework that could allow four-legged robots to move efficiently and at high speeds. This framework, which was introduced in Nature Machine Intelligence, is based on a training method known as imitation-relaxation reinforcement learning (IRRL).

Background: The Challenges of Legged Robot Locomotion

For legged robots to effectively explore their surroundings and complete missions, they need to be able to move both rapidly and reliably. However, the effective locomotion of legged robots entails solving several different problems. These include ensuring that the robots maintain their balance, that they move most efficiently, that they periodically alternate their leg movements to produce a particular gait, and that they can follow commands.

While some approaches for legged robot locomotion have achieved promising results, many are unable to consistently tackle all these problems. When they do, they sometimes struggle to achieve high speeds, thus only allowing robots to move slowly.

The Imitation-Relaxation Reinforcement Learning Framework

Statistics of the maximum speed and body mass of mammals and quadrupedal robots in logarithmic scales. Credit: Jin et al

In contrast with conventional reinforcement learning methods, the approach proposed by the researchers optimizes the different objectives of legged robot locomotion in stages. In addition, when assessing the robustness of their system, the researchers introduced the notion of "stochastic stability," a measure that they hoped would better reflect how a robot would perform in real-world environments (i.e., as opposed to in simulations).

The researchers found that the framework allowed the four-legged robot, which resembles the renowned Mini-Cheetah robot created by MIT, to run at a speed of 5.0 m/s-1, without losing its balance.

Future Applications and Implications

The framework introduced by this team of researchers could soon be implemented and evaluated in different real-world settings, using various physical legged robots. Ultimately, it could help to improve the locomotion of both existing and newly created legged robots, allowing them to move faster, complete missions in a smaller amount of time, and reach target locations more efficiently.

According to researcher Jin Yongbin, "In the future, we will directly introduce stability indicators in the process of controller learning and strive to catch up with the agility of natural creatures."

Journal Information: Yongbin Jin et al, High-speed quadrupedal locomotion by imitation-relaxation reinforcement learning, Nature Machine Intelligence (2022). DOI: 10.1038/s42256-022-00576-3.