Minimizing Energy Consumption Leads to the Emergence of Gaits in Legged Robots
This addresses the limitation of pre-programmed gaits for legged robots, enabling more general and adaptive locomotion across varied terrains, though it is incremental as it builds on energy minimization principles from animal studies.
The study tackled the problem of generating locomotion gaits in legged robots by minimizing mechanical energy, demonstrating that this approach leads to the emergence of natural gaits like those of horses and sheep in ideal terrains and unstructured patterns in rough terrains, validated in simulation and real hardware.
Legged locomotion is commonly studied and expressed as a discrete set of gait patterns, like walk, trot, gallop, which are usually treated as given and pre-programmed in legged robots for efficient locomotion at different speeds. However, fixing a set of pre-programmed gaits limits the generality of locomotion. Recent animal motor studies show that these conventional gaits are only prevalent in ideal flat terrain conditions while real-world locomotion is unstructured and more like bouts of intermittent steps. What principles could lead to both structured and unstructured patterns across mammals and how to synthesize them in robots? In this work, we take an analysis-by-synthesis approach and learn to move by minimizing mechanical energy. We demonstrate that learning to minimize energy consumption plays a key role in the emergence of natural locomotion gaits at different speeds in real quadruped robots. The emergent gaits are structured in ideal terrains and look similar to that of horses and sheep. The same approach leads to unstructured gaits in rough terrains which is consistent with the findings in animal motor control. We validate our hypothesis in both simulation and real hardware across natural terrains. Videos at https://energy-locomotion.github.io