Understanding the gap between simulation and reality is critical for reinforcement learning
with legged robots, which are largely trained in simulation. However, recent work has …

Some quadruped robots developed recently show better dynamic performance and
environmental adaptability than ever, and have been preliminarily applied in the field of …

Abstract Model-free reinforcement learning (RL) for legged locomotion commonly relies on a
physics simulator that can accurately predict the behaviors of every degree of freedom of the …

Recently reinforcement learning (RL) has emerged as a promising approach for
quadrupedal locomotion, which can save the manual effort in conventional approaches such …

Low-dimensional models are ubiquitous in the bipedal robotics literature. On the one hand
is the community of researchers that bases feedback control design on pendulum models …

Robots are designed to achieve muscle contraction, body curling, stress response, and
other complex movements. Inspired by the arm configuration and compression–torsion cubic …

In this letter, we aim to improve the robustness of dynamic quadrupedal locomotion through
two aspects: 1) fast model predictive foothold planning, and 2) applying LQR to projected …

Recently developed quadruped robots have more efficient dynamic performance and
adaptation to environments than before. They have already been used in the building of …

Locomotion stability is essential for controlling quadruped robots and adapting them to
unstructured terrain. We propose a control strategy with center-of-mass (CoM) dynamic …

We introduce a reaction wheel system that enhances the balancing capabilities and stability
of quadrupedal robots during challenging locomotion tasks. Inspired by both the standard …