Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – With the help of a form of machine lea rning called deep reinforcement learning (DRL), the EPFL robot notably learned t o transition from trotting to pronking - a leaping, arch-backed gait used by ani mals like springbok and gazelles - to navigate a challenging terrain with gaps r anging from 14-30cm. The study, led by the BioRobotics Laboratory in EPFL’s Scho ol of Engineering, offers new insights into why and how such gait transitions oc cur in animals. “Previous research has introduced energy efficiency and musculos keletal injury avoidance as the two main explanations for gait transitions. More recently, biologists have argued that stability on flat terrain could be more i mportant. But animal and robotic experiments have shown that these hypotheses ar e not always valid, especially on uneven ground,” says PhD student Milad Shafiee , first author on a paper published in Nature Communications.
NETL
NSTL