跳转至

ZHIWEI ZHANG / 张志威

Making robots
smarter.

Exploring embodied AI, robotics, artificial intelligence, and world models—toward robots that perceive their surroundings, understand tasks, learn skills, and act in the real world.

Embodied AIRoboticsArtificial intelligenceWorld models

BUILD & LEARN

GitHub activity

Recent work, collaboration, and coding habits. Charts are refreshed on a monthly schedule.

Code & community
GitHub profile, repository, and community statistics
Languages & code
Programming languages and recent code analysis
Achievements
Code and learning achievements generated by Metrics from GitHub activity
Recent activity
Recent branch, repository, and pull request activity
Coding habits
Recent coding activity by hour and day of the week
Contributions this year
GitHub contribution calendar for the past year
Contribution history & community
Contribution history
GitHub contribution calendars across the years
Issues & pull requests
Issue and pull request status across repositories
People & connections
GitHub followers and following
Animated snake following GitHub contributions
Recently starred projects Open-source repositories I recently starred on GitHub

EXPLORE

From curiosity to practice

Following a path through robotics and AI, grounded in programming and engineering.

01 / ROBOTICS

Robotics & ROS2

Building an understanding of robotic systems through modeling, transforms, simulation, and motion planning.

Explore ROS2 notes →

02 / LEARNING

Reinforcement learning

From states, actions, and rewards to value learning, policy learning, and Actor-Critic methods.

Read the series →

03 / ENGINEERING

Programming & engineering

Notes on C/C++, Python, Java, and the engineering problems worth revisiting.

Browse technical notes →

04 / WORLD MODELS

Embodied AI & world models

Exploring how robots represent their surroundings, anticipate change, and learn through interaction.

Explore my interests →

NOTES

A few notes to start with

Selected writing on robotics, learning, and everyday engineering.

How an agent learns

A starting point for understanding reinforcement learning: states, actions, policies, and rewards.

Read the note →

DWA local path planning

Understanding trajectory selection through differential-drive motion and velocity sampling.

Read the note →

Describing robots with URDF

Links, joints, and robot models: the foundations of visualization and simulation.

Read the note →

SSH port forwarding

Practical notes on tunneling network traffic through SSH and configuring development proxies.

Read the note →

Turn ideas into code. Keep a record of the journey.

All notes · Code & projects on GitHub ↗

Animated running character

Stay curious. Keep moving.