Abstract: This letter presents a control framework that combines model-based optimal control and reinforcement learning (RL) to achieve versatile and robust legged locomotion. Our approach enhances ...

Abstract: Recently, data analysis is used in model-free predictive control to mitigate the effects of parameter mismatches in parametric models. However, the finite-control-set (FCS) type cannot fully ...

Official implementation of Adding Conditional Control to Text-to-Image Diffusion Models. ControlNet is a neural network structure to control diffusion models by adding extra conditions. It copys the ...