<link>https://mr-tooth.github.io/</link></image><item><title>Started research internship at HKUST(GZ) Embodied Intelligence Research Institute</h1> <article> <h1>Started research internship at HKUST(GZ) Embodied Intelligence Research Institute</h1> <p>Thu, 14 May 2026 16:00:00 +0000</p> <p>I started a research internship at the Embodied Intelligence Research Institute, The Hong Kong University of Science and Technology (Guangzhou).</p> <p>The work focuses on cerebrum-cerebellum coordinated control for humanoid robots and data-driven dynamics representation for embodied intelligence.</p> </article> <article> <h1>BitRoboticsLab open-source organization now hosts robotics tools and tutorials</h1> <p>Tue, 05 May 2026 00:00:00 +0000</p> <p>BitRoboticsLab is my open-source organization for robotics tools, tutorials, and deployment-oriented research utilities.</p> <p>Current public repositories include <code>robot-motion-player</code>, <code>AStarFootstepPlanner</code>, <code>Heuclid</code>, <code>Coppeliasim-Tutorials-for-Beginners</code>, and <code>OpenClaw-Guide-for-Beginners</code>.</p> </article> <article> <h1>OpenClaw Guide for Beginners</h1> <p>Tue, 05 May 2026 00:00:00 +0000</p> <p><code>OpenClaw-Guide-for-Beginners</code> is a hands-on guide for deploying an OpenClaw AI assistant.</p> <p>It documents platform deployment, API configuration, and platform integration for users who want a 24-hour online assistant setup.</p> </article> <article> <h1>robot-motion-player</h1> <p>Sat, 18 Apr 2026 00:00:00 +0000</p> <p><code>robot-motion-player</code> is an open-source Python tool for visualizing and editing AMP motion datasets in legged locomotion and trajectory optimization workflows.</p> <p>It supports research iteration around motion data inspection, editing, and deployment-oriented locomotion tooling.</p> </article> <article> <h1>AStarFootstepPlanner</h1> <p>Thu, 09 Apr 2026 00:00:00 +0000</p> <p><code>AStarFootstepPlanner</code> is an open-source C++ planner for humanoid robot footsteps.</p> <p>It searches feasible footstep sequences on complex terrain while respecting kinematic constraints, making it a compact baseline for motion planning experiments and teaching.</p> </article> <article> <h1>Heuclid</h1> <p>Thu, 09 Apr 2026 00:00:00 +0000</p> <p><code>Heuclid</code> is a lightweight C++ geometry and vector math library for robotics codebases.</p> <p>It provides 2D/3D primitives, convex polygon tools, and spatial query utilities for planning and control projects that need a small, readable geometry layer.</p> </article> <article> <h1>CoppeliaSim Tutorials for Beginners</h1> <p>Fri, 20 Mar 2026 00:00:00 +0000</p> <p><code>Coppeliasim-Tutorials-for-Beginners</code> provides bilingual tutorials for robotics simulation with CoppeliaSim.</p> <p>The repository is intended for beginners who need presentations, code examples, and simulation models in one place.</p> </article> <article> <h1>Online Terrain-Aware Bipedal Gait Generation via Manifold Projection and Optimization-Guided Motion Libraries</h1> <p>Thu, 01 Jan 2026 00:00:00 +0000</p> <p>First-author manuscript under review. Update publication metadata after acceptance.</p> </article> <article> <h1>A Center-of-Mass State Estimation Method for Biped Robot Walking Based on Federated Kalman Filtering</h1> <p>Tue, 03 Jun 2025 00:00:00 +0000</p> <h2 id="patent-record">Patent record</h2> <table> <thead> <tr> <th>Field</th> <th>Official record</th> </tr> </thead> <tbody> <tr> <td>Chinese title</td> <td>基于联邦卡尔曼滤波的双足机器人行走质心状态估计方法</td> </tr> <tr> <td>Patent number</td> <td>ZL 2022 1 0904539.4</td> </tr> <tr> <td>Application date</td> <td>29 July 2022</td> </tr> <tr> <td>Grant date</td> <td>3 June 2025</td> </tr> <tr> <td>Grant announcement</td> <td>CN 115183779 B</td> </tr> <tr> <td>Certificate number</td> <td>7979388</td> </tr> <tr> <td>Patentee</td> <td>Beijing Institute of Technology</td> </tr> </tbody> </table> <p>Official inventors: 黄强、赖俊杭、陈学超、余张国、高峻峣、李庆庆、李超。</p> </article> <article> <h1>Multimodal Locomotion and Operation for Biomimetic Legged Robots</h1> <p>Tue, 01 Apr 2025 00:00:00 +0000</p> <p>This project studies heterogeneous reconfiguration and multimodal locomotion for biomimetic legged robots.</p> <p>My work focuses on multimodal control algorithm development. I expanded the command space for multimodal motion, designed implicit state estimation with a variational autoencoder, trained reinforcement-learning policies for multimodal locomotion, and supported sim-to-real deployment.</p> <p>The current capability targets complex-terrain walking, fall recovery, quadruped crawling, vehicle riding and separation, and other mode transitions on legged robot platforms.</p> </article> <article> <h1>Concept and strategies: Equivalent predictive control and handle point control for bipedal-vehicle transformable robots under various disturbances</h1> <p>Wed, 01 Jan 2025 00:00:00 +0000</p> <p>Co-authored paper. Add DOI, PDF, and final publication metadata when available.</p> </article> <article> <h1>Efficient hybrid environment expression for look-and-step behavior of bipedal walking</h1> <p>Wed, 01 Jan 2025 00:00:00 +0000</p> <p>Student third-author paper. Add DOI, PDF, and full author list when available.</p> </article> <article> <h1>First-author paper accepted by ISA Transactions</h1> <p>Wed, 01 Jan 2025 00:00:00 +0000</p> <p>My first-author paper, “Towards high mobility and adaptive mode transitions: Transformable wheel-biped humanoid locomotion strategy”, was published in ISA Transactions.</p> <p>The paper is part of my work on transformable humanoid locomotion, wheel-biped mode transition, and robot motion-control strategy design.</p> </article> <article> <h1>Towards high mobility and adaptive mode transitions: Transformable wheel-biped humanoid locomotion strategy</h1> <p>Wed, 01 Jan 2025 00:00:00 +0000</p> <p>First-author paper. The exact DOI, PDF, and full author list should be filled in after bibliography cleanup.</p> </article> <article> <h1>Completed key milestones for firefighting humanoid robot project</h1> <p>Sun, 01 Dec 2024 00:00:00 +0000</p> <p>I completed key research and project-delivery work for a Beijing science and technology project on humanoid robots for firefighting scenarios.</p> <p>My work covered milestone coordination, technical documentation, terrain-aware gait planning, mixed-terrain locomotion, and node acceptance material.</p> </article> <article> <h1>A Whole-Body Motion Planning Method for Low-Posture Crawling of Humanoid Robots Based on Key Mode Decomposition and CPG</h1> <p>Tue, 18 Jun 2024 00:00:00 +0000</p> <h2 id="patent-record">Patent record</h2> <table> <thead> <tr> <th>Field</th> <th>Official record</th> </tr> </thead> <tbody> <tr> <td>Chinese title</td> <td>基于关键模态分解和CPG的仿人机器人低姿匍匐全身运动规划方法</td> </tr> <tr> <td>Patent number</td> <td>ZL 2022 1 0890454.5</td> </tr> <tr> <td>Application date</td> <td>27 July 2022</td> </tr> <tr> <td>Grant date</td> <td>18 June 2024</td> </tr> <tr> <td>Grant announcement</td> <td>CN 115070775 B</td> </tr> <tr> <td>Certificate number</td> <td>7107745</td> </tr> <tr> <td>Patentee</td> <td>Beijing Institute of Technology</td> </tr> </tbody> </table> <p>Official inventors: 黄强、赖俊杭、陈学超、余张国、高峻峣、李庆庆。</p> </article> <article> <h1>A Linear Characterization Method for the Feasible Motion Range of a Three-DoF Electrically Driven Coupled Robot Joint</h1> <p>Tue, 28 May 2024 00:00:00 +0000</p> <h2 id="patent-record">Patent record</h2> <table> <thead> <tr> <th>Field</th> <th>Official record</th> </tr> </thead> <tbody> <tr> <td>Chinese title</td> <td>机器人三自由度电驱动耦合关节的运动可行范围线性界定方法</td> </tr> <tr> <td>Patent number</td> <td>ZL 2022 1 1034563.3</td> </tr> <tr> <td>Application date</td> <td>26 August 2022</td> </tr> <tr> <td>Grant date</td> <td>28 May 2024</td> </tr> <tr> <td>Grant announcement</td> <td>CN 115256400 B</td> </tr> <tr> <td>Certificate number</td> <td>7031385</td> </tr> <tr> <td>Patentee</td> <td>Beijing Institute of Technology</td> </tr> </tbody> </table> <p>Official inventors: 黄强、赖俊杭、陈学超、余张国、高峻峣、李庆庆、李超。</p> </article> <article> <h1>An Omnidirectional Center-of-Mass Trajectory Planning Method for Biped Robots Based on Bilevel Model Predictive Control</h1> <p>Tue, 28 May 2024 00:00:00 +0000</p> <h2 id="patent-record">Patent record</h2> <table> <thead> <tr> <th>Field</th> <th>Official record</th> </tr> </thead> <tbody> <tr> <td>Chinese title</td> <td>基于双层模型预测控制的双足机器人全向行走质心轨迹规划方法</td> </tr> <tr> <td>Patent number</td> <td>ZL 2022 1 1010867.6</td> </tr> <tr> <td>Application date</td> <td>23 August 2022</td> </tr> <tr> <td>Grant date</td> <td>28 May 2024</td> </tr> <tr> <td>Grant announcement</td> <td>CN 115256396 B</td> </tr> <tr> <td>Certificate number</td> <td>7042067</td> </tr> <tr> <td>Patentee</td> <td>Beijing Institute of Technology</td> </tr> </tbody> </table> <p>Official inventors: 黄强、赖俊杭、陈学超、余张国、高峻峣、李庆庆。</p> </article> <article> <h1>Experience</h1> <p>Tue, 24 Oct 2023 00:00:00 +0000</p> </article> <article> <h1>Humanoid Robot for Firefighting Scenarios</h1> <p>Sat, 01 Jul 2023 00:00:00 +0000</p> <p>This Beijing science and technology project focuses on humanoid robots for firefighting scenarios and mixed unstructured terrain.</p> <p>I served as the Ph.D. student lead, coordinating project milestones, personnel allocation, progress checks, and technical reports.</p> <p>On the algorithm side, I developed a layered mapping-optimization-reconstruction framework for complex foot-ground interaction. The method uses low-dimensional manifold motion modeling, safety trajectory optimization, efficient trajectory library construction, and fast trajectory reconstruction to support stable omnidirectional locomotion over stairs, slopes, and low obstacles.</p> <p>I also handled project documentation and acceptance material, including proposal material, milestone reports, annual reports, science and technology reports, technical summaries, and third-party test plans.</p> </article> <article> <h1>Humanoid Robot Demonstration and Field Delivery</h1> <p>Thu, 01 Jun 2023 00:00:00 +0000</p> <p>This industry-facing work was carried out during internships at Beijing BIT Huahui Intelligent Technology Co., Ltd.</p> <p>My role focused on motion-control algorithm development, on-site demonstration support, and project delivery. I supported the 2023 World Robot Conference demo filming and live demonstration, then contributed to a field delivery project that included one special humanoid robot platform and a motion-control software package.</p> <p>This page is an initial public summary. Confidential project details, customer information, and non-public acceptance material are intentionally omitted.</p> </article> <article> <h1>A Footstep Planning Method for Biped Robots Based on Variable-Parameter Velocity Mapping and Quadratic Programming</h1> <p>Tue, 14 Mar 2023 00:00:00 +0000</p> <h2 id="patent-record">Patent record</h2> <table> <thead> <tr> <th>Field</th> <th>Official record</th> </tr> </thead> <tbody> <tr> <td>Chinese title</td> <td>基于变参数速度映射和二次规划的双足机器人落脚点规划方法</td> </tr> <tr> <td>Patent number</td> <td>ZL 2022 1 0173869.0</td> </tr> <tr> <td>Application date</td> <td>24 February 2022</td> </tr> <tr> <td>Grant date</td> <td>14 March 2023</td> </tr> <tr> <td>Grant announcement</td> <td>CN 114527663 B</td> </tr> <tr> <td>Certificate number</td> <td>5781760</td> </tr> <tr> <td>Patentee</td> <td>Beijing Institute of Technology</td> </tr> </tbody> </table> <p>Official inventors: 黄强、赖俊杭、陈学超、余张国、李庆庆、石青、黄岩。</p> </article> <article> <h1>Optimization of Whole-Body Motion for Humanoid Robot Walking Down Stairs with Small Joint Range of Motion</h1> <p>Sun, 01 Jan 2023 00:00:00 +0000</p> <p>Imported from the Google Scholar-derived BibTeX seed. Add DOI, PDF, and full venue details when available.</p> </article> <article> <h1>Wheel-Biped Transformable Humanoid Robot</h1> <p>Thu, 01 Sep 2022 00:00:00 +0000</p> <p>This project developed a humanoid robot capable of autonomous mobility and dexterous operation, with a wheel-biped transformable subsystem for high-mobility locomotion.</p> <p>I built the biped robot system integration and software architecture. The real-time layer used RTOS and EtherCAT communication, with shared-memory multiprocessing and board-level device interface encapsulation for 0.25-1 kHz hybrid force-position control. The non-real-time layer integrated perception, planning, control, manipulation, and multithreading modules.</p> <p>I also designed the wheel-foot transformable subsystem, including a minimal active/passive wheel retrofit, motor selection and verification, prototype testing, and electromechanical-control joint debugging.</p> <p>For motion control, I proposed a key-phase decomposition guided particle-swarm trajectory optimization method and designed coordinated compliant control for the upper body, ankle, and foot, enabling adaptive mode switching and high-speed wheeled motion on unstructured terrain.</p> </article> <article> <h1>Low-centroid crawling motion for humanoid robot based on whole-body dynamics and trajectory optimization</h1> <p>Sat, 01 Jan 2022 00:00:00 +0000</p> <p>Imported from the Google Scholar-derived BibTeX seed. Add DOI, PDF, and full venue details when available.</p> </article> <article> <h1>Primate-Inspired High-Mobility Robot</h1> <p>Wed, 01 Sep 2021 00:00:00 +0000</p> <p>This national key R&D project studied primate-inspired high-mobility robot motion, including prone locomotion and omnidirectional walking.</p> <p>For biomimetic motion planning, I designed a central-pattern-generator based planning method to coordinate limbs during low-posture crawling, supporting stable crawling and slope climbing. This work led to one authorized invention patent and one EI paper.</p> <p>For bipedal walking, I proposed a multi-frequency decoupled planning architecture from command velocity to foot placement and gait generation. The controller combined quadratic-programming based footstep pose planning with model-predictive gait trajectory planning, enabling command-following omnidirectional walking and dynamic obstacle avoidance. This work led to two authorized invention patents.</p> </article> </main></body></html>