X-Loco: Towards Generalist Humanoid Locomotion Control via Synergetic Policy Distillation

• URL: http://arxiv.org/abs/2603.03733v1
• Date: Wed, 04 Mar 2026 05:07:05 GMT
• Title: X-Loco: Towards Generalist Humanoid Locomotion Control via Synergetic Policy Distillation
• Abstract summary: We introduce X-Loco, a framework for training a vision-based generalist humanoid locomotion policy.<n>X-Loco trains multiple oracle specialist policies and adopts a synergetic policy distillation with a case-adaptive specialist selection mechanism.<n>This design enables the student to acquire a broad spectrum of locomotion skills.
• Score: 50.0220259870317
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: While recent advances have demonstrated strong performance in individual humanoid skills such as upright locomotion, fall recovery and whole-body coordination, learning a single policy that masters all these skills remains challenging due to the diverse dynamics and conflicting control objectives involved. To address this, we introduce X-Loco, a framework for training a vision-based generalist humanoid locomotion policy. X-Loco trains multiple oracle specialist policies and adopts a synergetic policy distillation with a case-adaptive specialist selection mechanism, which dynamically leverages multiple specialist policies to guide a vision-based student policy. This design enables the student to acquire a broad spectrum of locomotion skills, ranging from fall recovery to terrain traversal and whole-body coordination skills. To the best of our knowledge, X-Loco is the first framework to demonstrate vision-based humanoid locomotion that jointly integrates upright locomotion, whole-body coordination and fall recovery, while operating solely under velocity commands without relying on reference motions. Experimental results show that X-Loco achieves superior performance, demonstrated by tasks such as fall recovery and terrain traversal. Ablation studies further highlight that our framework effectively leverages specialist expertise and enhances learning efficiency.

Related papers

• TeamHOI: Learning a Unified Policy for Cooperative Human-Object Interactions with Any Team Size [54.0714652192002]
  Physics-based humanoid control has achieved remarkable progress in enabling realistic and high-performing single-agent behaviors.<n>We present TeamHOI, a framework that enables a single decentralized policy to handle cooperative HOIs across any number of cooperating agents.
  arXiv  Detail & Related papers  (2026-03-09T05:52:13Z)
• 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)
• HUSKY: Humanoid Skateboarding System via Physics-Aware Whole-Body Control [67.58927286226925]
  We propose a learning-based framework that integrates humanoid-skateboard system modeling and physics-aware whole-body control.<n>Experiments on the Unitree G1 humanoid platform demonstrate that our framework enables stable and agile maneuvering on skateboards in real-world scenarios.
  arXiv  Detail & Related papers  (2026-02-03T07:18:01Z)
• Locomotion Beyond Feet [35.148387990120014]
  Locomotion Beyond Feet is a comprehensive system for whole-body humanoid locomotion across challenging terrains.<n>Our approach addresses two key challenges: contact-rich motion planning and generalization across diverse terrains.<n>Keyframes encode human knowledge of motor skills, are embodiment-specific, and can be readily validated in simulation or on hardware.
  arXiv  Detail & Related papers  (2026-01-07T05:36:39Z)
• Learning coordinated badminton skills for legged manipulators [12.514822343998908]
  We introduce an approach for enabling legged mobile manipulators to play badminton.<n>We propose a unified reinforcement learning-based control policy for whole-body visuomotor skills.<n>Our method includes a shuttlecock prediction model, constrained reinforcement learning for robust motion control, and integrated system identification techniques.
  arXiv  Detail & Related papers  (2025-05-29T01:26:30Z)
• Teacher Motion Priors: Enhancing Robot Locomotion over Challenging Terrain [6.7297018009524]
  This paper introduces a teacher prior framework based on the teacher student paradigm.<n>It integrates imitation and auxiliary task learning to improve learning efficiency and generalization.<n>The framework is validated on a humanoid robot, showing a great improvement in locomotion stability on dynamic terrains.
  arXiv  Detail & Related papers  (2025-04-14T16:36:56Z)
• StyleLoco: Generative Adversarial Distillation for Natural Humanoid Robot Locomotion [31.30409161905949]
  StyleLoco is a novel framework for learning humanoid locomotion.<n>It combines the agility of reinforcement learning with the natural fluidity of human-like movements.<n>We demonstrate that StyleLoco enables humanoid robots to perform diverse locomotion tasks.
  arXiv  Detail & Related papers  (2025-03-19T10:27:44Z)
• 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)
• An Adaptable Approach to Learn Realistic Legged Locomotion without Examples [38.81854337592694]
  This work proposes a generic approach for ensuring realism in locomotion by guiding the learning process with the spring-loaded inverted pendulum model as a reference. We present experimental results showing that even in a model-free setup, the learned policies can generate realistic and energy-efficient locomotion gaits for a bipedal and a quadrupedal robot.
  arXiv  Detail & Related papers  (2021-10-28T10:14:47Z)
• UniCon: Universal Neural Controller For Physics-based Character Motion [70.45421551688332]
  We propose a physics-based universal neural controller (UniCon) that learns to master thousands of motions with different styles by learning on large-scale motion datasets. UniCon can support keyboard-driven control, compose motion sequences drawn from a large pool of locomotion and acrobatics skills and teleport a person captured on video to a physics-based virtual avatar.
  arXiv  Detail & Related papers  (2020-11-30T18:51:16Z)

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.