S-Cheetah: A Novel Quadrupedal Robot with a 3-DOF Active Spine Learning Agile Locomotion

• URL: http://arxiv.org/abs/2605.27909v1
• Date: Wed, 27 May 2026 03:34:16 GMT
• Title: S-Cheetah: A Novel Quadrupedal Robot with a 3-DOF Active Spine Learning Agile Locomotion
• Abstract summary: We present S-Cheetah, a quadrupedal robot featuring a 3-DOF bio-inspired serial active spine capable of biomimetic tri-axial rotation.<n>S-Cheetah can achieve a peak speed of 6.9 m/s using the rotary G2 gallop gait and an in-place turning rate of 7.2 rad/s.<n>The system exhibits an emergent, feline-inspired aerial self-righting capability, allowing it to land stably on four feet from arbitrary orientations during free fall.
• Score: 1.9002598814341438
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The biological spine of quadrupeds enables sagittal flexion/extension, lateral bending, and axial rotation, playing a crucial role in highly agile and dexterous locomotion. While numerous studies have integrated active spinal joints into quadrupedal robots to enhance agility, most designs simplify control complexity by reducing spinal degrees of freedom (DOF), failing to achieve the spatial tri-axial rotation characteristic of biological spines. Consequently, replicating a multi-DOF biomimetic spine and effectively leveraging it to empower the agile locomotion of quadrupedal robots remains a significant research challenge. In this study, we present S-Cheetah, a quadrupedal robot featuring a 3-DOF bio-inspired serial active spine capable of biomimetic spatial tri-axial rotation. To empower the robot to fully utilize this active spine, we developed a specialized reinforcement learning framework to actively promote the engagement of the introduced spine and maximize the robot's locomotive capabilities by integrating an acceleration curriculum learning strategy with tailored reward functions, such as a gallop gait reward, a spine undulation reward, and a spine steering reward. Experimental results demonstrate that S-Cheetah can achieve a peak speed of 6.9 m/s using the rotary G2 gallop gait and an in-place turning rate of 7.2 rad/s. Besides, the system exhibits an emergent, feline-inspired aerial self-righting capability, allowing it to land stably on four feet from arbitrary orientations during free fall. Finally, through extensive evaluations across diverse locomotion tasks, we prove that the introduction of the proposed 3-DOF spine comprehensively enhances the locomotive agility of quadrupedal robots. Project website: himmy-robotics.github.io/scheetah

Related papers

• SPiralRoll: A Novel Adjustable-Stiffness Underactuated 3-DoF Joint with Torsion Springs for Rolling Robots [1.0604607292133101]
  SPiralRoll is a novel torsion-spring-based underactuated compliant mechanism for rolling robots and compliant robotic actuation.<n>The mechanism uses arc-distributed elastic members and two motor inputs to realize three physically observable output motions.<n>The full-arc design provides better structural support and smoother deformation, whereas the single-arc design yields larger deformation and stronger inertial excitation.
  arXiv  Detail & Related papers  (2026-06-21T11:27:50Z)
• Evaluation of an Actuated Spine in Agile Quadruped Locomotion [19.5524995782643]
  The spine plays a crucial role in the dynamic locomotion of quadrupedal animals.<n>This paper empirically investigates the benefits of an actuated spine for learning agile quadruped locomotion.
  arXiv  Detail & Related papers  (2026-05-08T16:45:28Z)
• X2-N: A Transformable Wheel-legged Humanoid Robot with Dual-mode Locomotion and Manipulation [12.614951789242896]
  We present X2-N, a high-DoF transformable robot with dual-mode locomotion and manipulation.<n>X2-N can operate in both humanoid and wheel-legged forms and transform seamlessly between them through joint reconfiguration.<n>We validate X2-N in a range of challenging locomotion and manipulation tasks, including dynamic skating-like motion, stair climbing and package delivery.
  arXiv  Detail & Related papers  (2026-04-23T11:10:11Z)
• Jumping Control for a Quadrupedal Wheeled-Legged Robot via NMPC and DE Optimization [14.88101223616473]
  Quadrupedal wheeled-legged robots combine the advantages of legged and wheeled locomotion to achieve superior mobility.<n> executing dynamic jumps remains a significant challenge due to the additional degrees of freedom introduced by wheeled legs.<n>This paper develops a mini-sized wheeled-legged robot for agile motion and presents a novel motion control framework.
  arXiv  Detail & Related papers  (2026-02-25T06:13:59Z)
• Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching [77.28042137892943]
  We present Perceptive Humanoid Parkour (PHP), a modular framework that enables humanoid robots to autonomously perform long-horizon, vision-based parkour.<n>We train motion-tracking reinforcement learning expert policies for these composed motions, and distill them into a single depth-based, multi-skill student policy.<n>We validate our framework with extensive real-world experiments on a Unitree G1 humanoid robot.
  arXiv  Detail & Related papers  (2026-02-17T18:59:11Z)
• Helical Tendon-Driven Continuum Robot with Programmable Follow-the-Leader Operation [0.11242503819703255]
  The ExoNav is a steerable robotic tool designed to facilitate precise navigation to the ventral and lateral epidural space.<n>Based on the helical shape of the ExoNav upon actuation, it is capable of performing follow-the-leader (FTL) motion.<n>The proposed simulation has the capability to calculate optimum tendon tensions to follow the desired FTL paths.
  arXiv  Detail & Related papers  (2026-01-19T16:03:56Z)
• RobotDancing: Residual-Action Reinforcement Learning Enables Robust Long-Horizon Humanoid Motion Tracking [50.200035833530876]
  RobotDancing is a simple, scalable framework that predicts residual joint targets to explicitly correct dynamics discrepancies.<n>It can track multi-minute, high-energy behaviors (jumps, spins, cartwheels) and deploys zero-shot to hardware with high motion tracking quality.
  arXiv  Detail & Related papers  (2025-09-25T03:30:34Z)
• Humanoid Whole-Body Locomotion on Narrow Terrain via Dynamic Balance and Reinforcement Learning [54.26816599309778]
  We propose a novel whole-body locomotion algorithm based on dynamic balance and Reinforcement Learning (RL)<n> Specifically, we introduce a dynamic balance mechanism by leveraging an extended measure of Zero-Moment Point (ZMP)-driven rewards and task-driven rewards in a whole-body actor-critic framework.<n> Experiments conducted on a full-sized Unitree H1-2 robot verify the ability of our method to maintain balance on extremely narrow terrains.
  arXiv  Detail & Related papers  (2025-02-24T14:53:45Z)
• Evolutionary Morphology Towards Overconstrained Locomotion via Large-Scale, Multi-Terrain Deep Reinforcement Learning [10.030349447312057]
  This paper investigates a novel class of overconstrained locomotion from a design and learning perspective inspired by evolutionary morphology. We propose a 3D-printable design of robotic limbs parametrically reconfigurable as a classical planar 4-bar linkage, an overconstrained Bennett linkage, and a spherical 4-bar linkage. Results show that the overconstrained limbs exhibit more efficient locomotion than planar limbs during forward and sideways walking over different terrains.
  arXiv  Detail & Related papers  (2024-07-01T07:57:01Z)
• Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control [106.32794844077534]
  This paper presents a study on using deep reinforcement learning to create dynamic locomotion controllers for bipedal robots. We develop a general control solution that can be used for a range of dynamic bipedal skills, from periodic walking and running to aperiodic jumping and standing. This work pushes the limits of agility for bipedal robots through extensive real-world experiments.
  arXiv  Detail & Related papers  (2024-01-30T10:48:43Z)
• Barkour: Benchmarking Animal-level Agility with Quadruped Robots [70.97471756305463]
  We introduce the Barkour benchmark, an obstacle course to quantify agility for legged robots. Inspired by dog agility competitions, it consists of diverse obstacles and a time based scoring mechanism. We present two methods for tackling the benchmark.
  arXiv  Detail & Related papers  (2023-05-24T02:49:43Z)
• VAE-Loco: Versatile Quadruped Locomotion by Learning a Disentangled Gait Representation [78.92147339883137]
  We show that it is pivotal in increasing controller robustness by learning a latent space capturing the key stance phases constituting a particular gait. We demonstrate that specific properties of the drive signal map directly to gait parameters such as cadence, footstep height and full stance duration. The use of a generative model facilitates the detection and mitigation of disturbances to provide a versatile and robust planning framework.
  arXiv  Detail & Related papers  (2022-05-02T19:49:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.