用可微世界模型 + 想象 rollout(SuperMimic 范式)训练 wheelbipe 轮腿机器人。一个 6 维动作的策略同时做到前进 1.5 m/s、原地 10.21 rad/s 偏航、8 cm 变腿,训练过程不跑 PPO。
☆23Oct 28, 2026Updated 3 weeks ago
Alternatives and similar repositories for supermimic_wheelbipe
Users that are interested in supermimic_wheelbipe are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- This repository contains the simulation environment, training pipeline, and policies accompanying our paper "Self-Recovery of Quadrupedal…☆12Nov 1, 2025Updated last year
- 探索类开源:SuperMimic与MimicAgent联动用于四轮足机械臂的统一协同控制与分层控制的训练方案。欢迎交流与共同探索。☆22Updated this week
- Ghost-Exoskeleton: a Physical AI hackathon project development repository☆11Nov 2, 2026Updated 2 weeks ago
- ☆25Jul 16, 2024Updated 2 years ago
- AMP gait generator for quadruped robots (NMPC + WBC)☆73Jul 22, 2026Updated 3 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- 本项目是一个完整的轮腿机器人(Wheel-Legged Robot)控制和仿真系统,基于ROS2框架开发。项目包含两款机器人平台:cyclBot和 seriBot ,支持实时硬件控制、MuJoCo仿真、动力学建模和高级控制算法。☆23Apr 14, 2026Updated 7 months ago
- 原来会输出6个pt文件,后面整合成1个了,训练代码还需要再改改☆11Dec 18, 2025Updated 11 months ago
- Go2 robot mastering extreme terrain - leaping 80cm gaps, scaling 45cm parkour steps. Neural network ablation study on Isaac Lab with 7 br…☆41Jan 30, 2026Updated 9 months ago
- LainLab is a reinforcement-learning, simulation-validation, and deployment project for robots from multiple vendors, built on mjlab 1.6.0…☆19Sep 30, 2026Updated last month
- added height control command into official HIMLoco☆12Jul 15, 2025Updated last year
- An efficient WMP-based visual locomotion framework for Unitree Go1 with NVIDIA Warp depth rendering and Sim-to-Sim/Sim-to-Real deployment…☆44Oct 9, 2026Updated last month
- G1 perceptive SuperMimic prototype with a pretrained frozen heightmap autoencoder shared by policy, critic and world model.☆12Oct 24, 2026Updated 3 weeks ago
- Robot motion editor for GMR-format data☆18Oct 14, 2026Updated last month
- 在unitree_guide框架基础上编写的四足机器人深度强化学习Sim2Sim/Sim2Real框架☆11Jun 4, 2025Updated last year
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Attention-Based Map Encoding in mjlab☆17Oct 23, 2026Updated 3 weeks ago
- A simple PPO baseline for Unitree Go2 fall recovery, accompanying FR-Net (IEEE RA-L 2025).☆22Jul 23, 2026Updated 3 months ago
- ☆29Updated this week
- ☆19Jun 27, 2024Updated 2 years ago
- legbot四足/四轮足机器人Isaac lab训练框架,包含PPO、PPO+MoE+CTS、WF-CTS-MOE(四轮足训练:真机已验证多种地形的鲁棒运动),可实现多种地形下的鲁棒运动控制。☆64Nov 10, 2026Updated last week
- 简单修改的himloco框架☆33Nov 4, 2026Updated 2 weeks ago
- ☆27Jun 17, 2026Updated 5 months ago
- A deployment framework for reinforcement learning-based motion control of legged robots, covering bipedal, quadrupedal, wheeled-bipedal, …☆229Oct 9, 2026Updated last month
- 基于 Pinocchio + urdf 离线分析与最小二乘法拟合的六自由度串联型(PUMA)机械臂重力补偿☆50May 1, 2026Updated 6 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Training Go2W based on the HIMLoco framework☆110Nov 18, 2025Updated last year
- This repository provides the deployment and validation framework for **FEAP** (Feature-Enhanced Adversarial Priors), a unified learning f…☆13Jan 20, 2026Updated 10 months ago
- Source Code for MIRROR: Visual Motion Imitation via Real-time Retargeting and Teleoperation on Humanoid Robots with Parallel Differential…☆32Mar 26, 2026Updated 7 months ago
- ☆24May 3, 2026Updated 6 months ago
- ☆25Oct 15, 2026Updated last month
- Legged Incline Fall-recovery Technique for Enhanced Recovery☆12Dec 2, 2025Updated 11 months ago
- 四足机器人legbot跨楼层三维导航:集成 FAST-LIO 建图、PCT Planner多层全局规划、EGO/SCAN Planner局部避障与强化学习运动控制,并在 Gazebo 多层楼梯场景完成端到端验证。已接入巡检平台+真机已验证☆103Updated this week
- 六自由度串联型机械臂运动学动力学计算☆27May 1, 2026Updated 6 months ago
- 2026年度保研预推免通知合集(完整版)☆24Sep 23, 2026Updated last month
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- [Neurips 2026] SRL-MPC: Shape-Aware Reinforcement Learned Model Predictive Control☆12Nov 6, 2026Updated 2 weeks ago
- Agent-oriented USD scene generation for ROSClaw: online asset discovery, on-demand loading, Isaac Sim execution and evidence-driven valid…☆41Nov 9, 2026Updated last week
- A Go2W legged-wheel robot locomotion reinforcement learning project based on NVIDIA Isaac Gym.☆136May 12, 2026Updated 6 months ago
- quadruped reinforcement learning, includes train, sim2sim and sim2real☆25May 24, 2025Updated last year
- Reinforcement learning codebase built on MJLab for AMP-based Unitree G1 humanoid locomotion.☆13Aug 22, 2026Updated 2 months ago
- ☆12Nov 24, 2023Updated 2 years ago
- Matterport and Unreal Engine Data Generator For ViPanner☆10Oct 30, 2024Updated 2 years ago
Are these results useful?