Residual-learning-based landing control with gravity estimation for quadruped robot in low-gravity scenarios

Integrated attitude and landing control for quadruped robots in asteroid landing mission scenarios using reinforcement learning

Quadruped robots walking in discrete environments conventionally control leg swinging using either simple potentiometer-based feedback or feed forward. We think accurate positioning control for a safe landing using visual servoing is required. Conventional visual servoing, however, has problems such as requiring complex nonlinear calculation with exact camera and joint angles. To solve these problems, we propose Linear Visual Servoing (LVS) for positioning the quadruped robot leg in a gait. We show that the robot can make minor adjustments despite error between planned and safe landing points.

In surface exploration missions, wheeled planetary vehicles have difficulty traveling on asteroids due to their weak gravitational fields. With the rapid development of hardware performance and control methods, quadruped robots have great potential to serve in asteroid exploration. When deploying or controlling the jumping motions of a quadruped robot on an asteroid, landing stability must be guaranteed. Under the weak and irregular gravitational fields of asteroids, the robot should be reoriented to an appropriate attitude for a smooth and stable landing. To achieve this objective, a model-free control method based on reinforcement learning (RL) was proposed. Sim-to-real transfer methods including domain randomization and transfer learning were proposed to address the sim-to-real problem. The original control model trained by RL was transferred to a new version that could be applied and tested on a real quadruped robot. An equivalent asteroid's weak gravitational environment experimental platform was for the first time designed and employed to test the performance of the proposed control scheme. Both the simulation and experimental results validated the effectiveness of the proposed controller training and sim-to-real transfer methods.

Aiming at the advantages of UAVs in field survey and search as well as their difficulties in taking off and landing in poor ground environment in the field, a simple self-balancing UAV take-off and landing control system based on a quadruped robot is proposed. Firstly, the simple physical model of the system is established and the mathematical analysis is carried out. Secondly, the inverse kinematics of the single leg model is derived. Thirdly, the attitude sensor is used to measure the attitude angle data of the system platform, and the Kalman filter is used in the software design to filter the attitude angle data, and the PID control algorithm is used to control each leg joint. Finally, The design is simulated by MATLAB and experimentally analyzed, and the test results meet the design requirements.

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.

Quadruped robots are machines intended for challenging and harsh environments. Despite the progress in locomotion strategy, safely recovering from unexpected falls or planned drops is still an open problem. It is further made more difficult when high horizontal velocities are involved. In this work, we propose an optimization-based reactive Landing Controller that uses only proprioceptive measures for torque-controlled quadruped robots that free-fall on a flat horizontal ground, knowing neither the distance to the landing surface nor the flight time. Based on an estimate of the Center of Mass horizontal velocity, the method uses the Variable Height Springy Inverted Pendulum model for continuously recomputing the feet position while the robot is falling. In this way, the quadruped is ready to attain a successful landing in all directions, even in the presence of significant horizontal velocities. The method is demonstrated to dramatically enlarge the region of horizontal velocities that can be dealt with by a naive approach that keeps the feet still during the airborne stage. To the best of our knowledge, this is the first time that a quadruped robot can successfully recover from falls with horizontal velocities up to 3 m/s in simulation. Experiments prove that the used platform, Go1, can successfully attain a stable standing configuration from falls with various horizontal velocities and different angular perturbations.

Lunar quadruped robots face landing challenges including weak gravity, large mass variations, uncertain sloped terrain, and strict payload acceleration limits, requiring effective impact mitigation and rapid post-landing stabilization. This paper presents a novel end-to-end reinforcement learning-based landing controller with three key novelties: (i) a phase-structured yet implicitly encoded formulation that distinguishes contact preparation, energy dissipation, and stabilization without explicit phase switching; (ii) a terrain-agnostic state and control representation using equivalent support direction construction and contact-gated modulation to decouple normal–tangential dynamics; and (iii) an extremum oriented learning strategy that directly captures peak impact suppression and buffering sufficiency, addressing limitations of cumulative rewards in hybrid, peak-dominated tasks. A hybrid control model for lunar quadruped landing dynamics is established, incorporating variable mass, low impact, and full stroke as key constraints during training. Simulation and full-scale experimental prototypes are built to validate the controller. Simulation results demonstrate robust landing buffering and stability control under varying mass, landing velocity, and slope conditions, with favorable robustness against parameter variations. Experimental verification is conducted under diverse conditions including different masses (200 kg, 250 kg), vertical/horizontal landing velocities (0.8 m/s, 0.2 m/s), and slopes (0°, 8°). The deviation between simulation and experimental results does not exceed 30%, confirming the effectiveness and transferability of the proposed approach.