Chimp movements recreated with machine learning simulation
Image credit: Dreamstime
Researchers at the University of Manchester have used machine-learning techniques to create a virtual chimp. They hope that their work could help improving understanding of why primates move the way we do.
“Starting from an animal’s skeleton, computers using machine learning can now reconstruct how the animal could have moved. However, they don’t always do a good job,” said Professor Bill Sellers of Manchester’s School of Earth and Environmental Sciences.
“With some simple changes to the machine-learning goals we can now create much more accurate simulations. We’ve now used this process to generate chimpanzee locomotion to explore why they walk the way they do.”
Sellers and his colleagues hope that their computer simulation could help researchers understand the “curious way” that primates walk by studying how much energy it takes to walk in a stable fashion compared to other types of movement. In the field of evolutionary biomechanics, it is generally thought that the most energy-efficient gaits are most successful.
The Manchester researchers began with a full-body CT scan of an adult male chimpanzee, which they used to generate a skeletal model and skin outline.
This model was used to define the positions of joints, muscle paths and limb contact points. This could then be used to analyse the gait of a chimpanzee. This is similar to the pattern of movement that primates – including humans – follow as they walk.
Using this model, the researchers found that the gait of the chimpanzee may not be the most energy efficient, as may have been previously assumed. Instead, they found that energy efficiency may be traded off for lateral stability. Modelling for this trade-off with their machine-learning algorithm generated more realistic simulated movements.
“As technology has advanced and with musculoskeletal models becoming increasingly sophisticated, previous simulation models are becoming extremely unrealistic in relation to gait patterns, so we have to adapt the way we think and research,” said Sellers.
“The realism of the gait produced by the chimpanzee model is considerably enhanced by including a lateral stability and it is highly likely that this is an important evolutionary development. This enhanced lateral stability comes at a moderate energetic cost, however, and this cost would need to be outweighed by other adaptive advantages.”
This characteristic gait of chimpanzees and other primates has been suggested to be associated with retaining stability while moving through trees.
Beyond improving understanding of the unusual movement of primates, the research project demonstrated how very simple changes to machine-learning algorithms could produce far more accurate computer simulations of animal movement.