Videos & Demos
Here are selected demonstrations of my work in robotics and UAV autonomy, mapping, and mobile robot navigation.
UAV Mapping with RGBD Camera (Depth → Map)
Problem: GPS-denied mapping using onboard depth sensing.
What I built: ROS pipeline from depth → point cloud → mapping + tuning for stability.
Why it matters: Enables reliable autonomy and inspection without external infrastructure.
Multi-agent obstacle-avoidance simulation framework
Problem: How can multiple robots maintain safe, coordinated motion in dynamic and crowded environments without relying too heavily on a single leader?
What I built: A ROS1/Gazebo/C++ multi-agent simulation framework inspired by reciprocal collision avoidance for cooperative robot navigation.
Why it matters: It built my foundation in swarm robotics, decentralized avoidance, and scalable multi-agent system design.
AMR Navigation + Task Planning with Behavior Trees
Problem: In warehouse environments, task execution can become hard to debug and maintain as the number of states, exceptions, and recovery behaviors grows.
What I built: A behavior-tree-based task planner in C++ to make execution logic modular (clear node responsibilities) and easy to extend with recovery/fallback behaviors.
How I validated it: Used Groot for real-time visualization and monitoring of task status, and integrated navigation with move_base_flex to support flexible planners/controllers and safer motion execution.
Impact: More transparent task status, faster debugging, and a more maintainable autonomy stack for real deployments.
Multi Robots Navigation ROS Noetic and Gazebo
Problem: What happens when one robot is no longer enough? The jump from single-robot navigation to multi-agent systems is where robotics becomes far more realistic—and far more challenging. Managing multiple robots in ROS1 means handling separate topics, namespaces, and control flows without interference.
What I built: I built a dual-TurtleBot3 navigation project in ROS1 using C++, Gazebo 11, and Ubuntu Focal, where two different robots operate in the same simulated environment. The core focus was creating a clean multi-agent structure by properly separating each robot’s topics and navigation stack.
Why it matters: This project gave me the hands-on foundation for future multi-agent robotics systems. It was an early but essential step toward scalable robot coordination, where the real challenge is not just motion—but architecture, communication, and system reliability.