This work categorizes quadruped robot skills into three types: rhythmic motions, expressive motions, and high-dynamic motions and generates reference trajectories for each category using central pattern generators, animation design, and motion capture, respectively, and designs an asymmetric neural network architecture and employs an imitation–reinforcement learning algorithm to train policies for generating these three types of motions.
Abstract
The appeal of quadruped robots lies not only in their ability to mimic the diverse and agile locomotion of animals but also in their potential to integrate with human artistic expression to achieve complex multi-skill movements. Continuous multi-skill motion in quadruped robots requires the realization of diverse, continuous, and long-horizon behaviors, involving a broader state space and more complex motion generation and transitions. This presents significant challenges, including sparse rewards, incomplete data, long-horizon motion planning, and the design of fine-grained motion transitions. In this work, we categorize quadruped robot skills into three types: rhythmic motions, expressive motions, and high-dynamic motions and generate reference trajectories for each category using central pattern generators, animation design, and motion capture, respectively. We then design an asymmetric neural network architecture and employ an imitation–reinforcement learning algorithm to train policies for generating these three types of motions. By composing multiple motion skill trajectories, we avoid long-horizon motion planning; by leveraging reinforcement learning, we enable smooth and continuous skill transitions; and by introducing a two-stage reference state initialization curriculum, the robot is able to switch from arbitrary states to the target motion skill. Moreover, during training, the policy imitates only key characteristics of the reference motions rather than strictly tracking fixed trajectories, making it more robust. Finally, we achieve robust motion skill generation and seamless transitions on a quadruped robot equipped with a 6-DoF manipulator, validating the effectiveness and feasibility of the proposed multi-skill generation and transition method.
Although legged animals are capable of performing explosive motions while traversing confined spaces, replicating this behavior in quadrupedal robots has been a longstanding challenge. Here, we propose a hierarchical reinforcement learning pipeline that empowers the robots to perform aggressive locomotion through constrained obstacles--a narrow gate. The imitation learning technique is used to train the low-level policy, which mimics the behaviors of real animals and forms a set of diverse skills. The high-level controller, having an awareness of the capability of low-level skills and acquiring the gate information via vision-based detection, determines the suitable maneuvers with collision-free trajectories to traverse it dynamically. Notably, we also verify that this framework can be extended to other highly dynamic tasks. This is one of the first works that perform autonomous and agile aerial gate traversal tasks on ground-walking robots, extending the lifelike agility of legged robots to match that of their biological counterparts.
Zeren Luo, Jiahui Zhang, Yimin Han et al.· 1 citation
Brachiation is a form of locomotion in which primates move primarily using their arms, enabling traversal in environments without footholds. However, this motion requires highly coordinated whole-body movement and precise timing control for bar grasping and release. As a result, achieving robust behavior on life-sized robotic platforms remains challenging. In this study, we present a reinforcement learning-based method to realize brachiation on a life-sized dual-arm robot. The core of the proposed approach is Waypoint-Guided Reinforcement Learning (WGRL), a learning framework for inducing non-linear and complex motions. For high-difficulty tasks where imitation learning data are unavailable, WGRL guides behavior acquisition by sparsely specifying waypoints for the end-effector trajectory, while whole-body motion is generated through reinforcement learning. In addition, by integrating the waypoint-following guidance with rewards based on task success and mechanical energy, and training in an environment designed for Sim-to-Real transfer, the proposed method achieves both forward progression and motion stability. The acquired behavior is evaluated through Sim-to-Sim experiments under monkey-bar environments with geometric variations and hardware experiments, confirming robust brachiation including failure recovery behavior. This study provides effective learning design guidelines for realizing arm-based locomotion on life-sized robotic hardware and expanding the traversable workspace of robots.
Ayumu Iwata, Kento Kawaharazuka, Keita Yoneda et al.· 0 citations
Enabling quadrupedal robots to traverse complex terrains, from rugged outdoor environments to urban landscapes, requires seamless integration of multiple motor skills, smooth transitions between gaits, and high-speed perceptive locomotion using only onboard sensors. We present APT-RL (action pretrained transformer-based reinforcement learning), a unified framework that enables multiskill locomotion to achieve high-speed traversal in complex environments through autonomous skill transitions using only onboard perception and computation. Our approach generates large-scale, feature-rich two-dimensional (2D) motion datasets through trajectory optimization with simplified dynamics. These datasets enable training of diverse, reusable locomotion skills that transfer effectively to a real quadruped robot operating on complex uneven terrains. The resulting high-quality skills serve as strong priors for efficient learning of complex downstream tasks and extend naturally to 3D environments, enabling smooth, high-speed multiskill locomotion in deployed policy. Real-world experiments demonstrate the framework's capabilities: The robot performed agile maneuvers through complex indoor obstacles and outdoor wild environments, including dynamic drop-down maneuvers that reached instantaneous peak speeds of up to 6 meters per second. A single onboard policy enabled robust traversal of diverse obstacles, including stairs, hurdles, stepping stones, gaps, and fallen branches, demonstrating the versatility and effectiveness of our approach.
Jun-Gill Kang, Jaehyun Park, Tae-Gyu Song et al.· Science Robotics· 1 citation
Quadruped robots have gained significant attention due to their superior mobility on uneven and unstructured terrains, offering potential applications in inspection, search and rescue, and field exploration. However, achieving robust locomotion on low-cost platforms remains challenging because of constraints in stability, adaptability, sensing quality, and onboard computation. In this work, we present an integrated motion-control framework that combines biologically inspired Central Pattern Generators (CPGs), a multi-agent reinforcement learning coordination layer, and low-cost hardware adaptation to enable reliable and efficient quadruped locomotion. The proposed framework uses CPGs as structured gait priors for rhythmic leg motion, models each leg as a coordinated agent with a shared-parameter residual policy, and incorporates actuator abstraction and safety-aware command projection. The low-cost merit specifically concerns online deployment: the four legs share a single 39,560-parameter actor (approximately 155 KiB in 32-bit precision), evaluated at 50 Hz from compact proprioceptive observations, while the centralized critic, simulation infrastructure, external motion capture, vision-based terrain perception, direct torque sensing, and online dynamics optimization are not required on the robot. We validate the approach in both simulation and on a physical low-cost quadruped robot across obstacles, ramps, stairs, and uneven terrain. Experimental results demonstrate that the integrated system improves locomotion stability, energy efficiency, and terrain adaptability compared with baseline controllers, highlighting the effectiveness of combining a structured gait prior, lightweight residual coordination, and hardware-aware deployment for practical quadruped locomotion.
The motion controller is one of the most fundamental modules in embodied intelligence systems. Driven by large-scale human motion-capture data and the motion-tracking paradigm, humanoid control has achieved remarkable progress in recent years. However, migrating this recipe to the quadrupedal setting is far less straightforward: animal motion data is scarcer and harder to capture at scale than human data, and cross-embodiment retargeting remains fragile. We present ABot-C0, a generalist motion-control system for quadruped robots that establishes three complementary behavior foundations: a scalable multi-source motion-data pipeline, robust policy learning across motion tracking, locomotion, and scene interaction, and a unified deployment stack for reliable real-world operation. Fundamentally, we construct a data pyramid through conditional video-generation synthesis, annotated motion capture, teleoperation, and human design, producing 16,074 physically feasible motion clips as the data foundation for diverse motion-learning demands. With large-scale motion data, a Flow-Matching generalist policy demonstrates, for the first time, a scaling law for quadruped motion tracking: performance improves consistently as training scales up, with zero-shot capability to track unseen motions. We then go a step further toward robust all-terrain locomotion by adopting a three-stage privileged-to-perceptive framework with temporal LiDAR memory and terrain-predictive supervision. Collectively, these components form a motion generalist that coordinates multi-policy execution, smooth behavior transitions, energy-efficient control, and safety mechanisms for real-world deployment. Extensive experiments on urban-terrain autonomous navigation and companion-style multimodal interaction demonstrate that quadruped robots can move beyond functional demos toward product-level behavioral intelligence.
Xufeng Zhao, Fuzhi Yang, Jianhui Chen et al.· 0 citations
Non-prehensile manipulation of freely moving objects on a mobile base represents a significant challenge in underactuated robotics. This paper presents a sim-to-real reinforcement learning pipeline for a Unitree Go2 robot tasked with balancing a free-rolling ping-pong ball on a board mounted on its trunk while maintaining stable posture or tracking commanded velocities. Built on Legged Gym and the Genesis simulation, the proposed framework augments standard quadrupedal locomotion with ball-aware observations, task-specific reward design, and curriculum learning for progressively harder balancing and locomotion regimes. To improve transfer, the method incorporates domain randomization, camera-rate-compatible ball observations that mimic asynchronous visual feedback, and deployment-oriented safeguards such as smooth startup action blending. The learned policies are evaluated through a three-stage pipeline: large-scale training in Genesis, sim-to-sim validation in MuJoCo, and deployment on a physical Unitree Go2 using vision-estimated board-frame ball states. Experimental results show that the proposed framework can achieve both standing ball balance and ball-balancing locomotion on hardware, while additional comparisons between PPO and SAC highlight a trade-off between nominal task performance and disturbance robustness. These results suggest that reinforcement learning, when combined with transfer-aware observation design and deployment mechanisms, provides a practical approach for dynamic ball-balancing control on quadruped robots.