<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Research Project |</title><link>https://mr-tooth.github.io/tags/research-project/</link><atom:link href="https://mr-tooth.github.io/tags/research-project/index.xml" rel="self" type="application/rss+xml"/><description>Research Project</description><generator>HugoBlox Kit (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Tue, 01 Apr 2025 00:00:00 +0000</lastBuildDate><image><url>https://mr-tooth.github.io/media/icon_hu_1c0e9cb08cfb822a.png</url><title>Research Project</title><link>https://mr-tooth.github.io/tags/research-project/</link></image><item><title>Multimodal Locomotion and Operation for Biomimetic Legged Robots</title><link>https://mr-tooth.github.io/projects/multimodal-legged-robot/</link><pubDate>Tue, 01 Apr 2025 00:00:00 +0000</pubDate><guid>https://mr-tooth.github.io/projects/multimodal-legged-robot/</guid><description>&lt;p&gt;This project studies heterogeneous reconfiguration and multimodal locomotion for biomimetic legged robots.&lt;/p&gt;
&lt;p&gt;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.&lt;/p&gt;
&lt;p&gt;The current capability targets complex-terrain walking, fall recovery, quadruped crawling, vehicle riding and separation, and other mode transitions on legged robot platforms.&lt;/p&gt;</description></item><item><title>Humanoid Robot for Firefighting Scenarios</title><link>https://mr-tooth.github.io/projects/firefighting-humanoid/</link><pubDate>Sat, 01 Jul 2023 00:00:00 +0000</pubDate><guid>https://mr-tooth.github.io/projects/firefighting-humanoid/</guid><description>&lt;p&gt;This Beijing science and technology project focuses on humanoid robots for firefighting scenarios and mixed unstructured terrain.&lt;/p&gt;
&lt;p&gt;I served as the Ph.D. student lead, coordinating project milestones, personnel allocation, progress checks, and technical reports.&lt;/p&gt;
&lt;p&gt;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.&lt;/p&gt;
&lt;p&gt;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.&lt;/p&gt;</description></item><item><title>Wheel-Biped Transformable Humanoid Robot</title><link>https://mr-tooth.github.io/projects/wheel-biped-transformable-humanoid/</link><pubDate>Thu, 01 Sep 2022 00:00:00 +0000</pubDate><guid>https://mr-tooth.github.io/projects/wheel-biped-transformable-humanoid/</guid><description>&lt;p&gt;This project developed a humanoid robot capable of autonomous mobility and dexterous operation, with a wheel-biped transformable subsystem for high-mobility locomotion.&lt;/p&gt;
&lt;p&gt;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.&lt;/p&gt;
&lt;p&gt;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.&lt;/p&gt;
&lt;p&gt;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.&lt;/p&gt;</description></item><item><title>Primate-Inspired High-Mobility Robot</title><link>https://mr-tooth.github.io/projects/primate-inspired-mobile-robot/</link><pubDate>Wed, 01 Sep 2021 00:00:00 +0000</pubDate><guid>https://mr-tooth.github.io/projects/primate-inspired-mobile-robot/</guid><description>&lt;p&gt;This national key R&amp;amp;D project studied primate-inspired high-mobility robot motion, including prone locomotion and omnidirectional walking.&lt;/p&gt;
&lt;p&gt;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.&lt;/p&gt;
&lt;p&gt;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.&lt;/p&gt;</description></item></channel></rss>