PSTO: Learning Energy-Efficient Locomotion for Quadruped Robots

Energy efficiency is critical for the locomotion of quadruped robots. However, energy values found in simulations do not transfer adequately to real world. To address this issue, we present a novel method, named Policy Search Transfer Optimization (PSTO), which combines deep reinforcement learning and optimization create energy-efficient robots The policy search process are performed by TD3 algorithm transferred open-loop control trajectory further optimized numerical methods, conducted on robot In order ensure high uniformity simulation results behavior hardware platform, introduce validate accurate model including consistent size fine-tuning parameters. We then those with real-world experiments Ant executing dynamic walking gaits different leg lengths numbers amplifications. analyze show that our methods can outperform method provided state-of-the-art sinusoid function both speed.