Flexible Landing Control of a Quadruped Robot’s 2-DOF Leg Using DDPG During Free Fall at Varying Heights

This paper presents a deep reinforcement learning-based method for two-degree-of-freedom (2-DOF) flexible landing leg for quadruped robots, which aims to mitigate the problem of high impact forces during free-fall landings at uncertain heights. First, a virtual model controller (VMC) for the 2-DOF leg is created in Cartesian space. Then, the hybrid control method is used, which utilizes a control policy during falling and fixed impedance parameters during buffering. In addition, a Deep Deterministic Policy Gradient (DDPG) based control policy for the falling stage is developed, which aims to learn an impedance parameter adjustment policy specific to the free fall of the leg within a certain height range. Finally, the proposed method was validated by simulation experiments. This showed that it reduces the impact forces during landing more and more effectively with increasing height. At the same time, the reasons for the reduction in impact forces were elucidated by an analysis based on the relationship between impulse and momentum.