Project Detail
Multi-Agent Robotics Coverage
Distributed control, ROS integration, and experimental coverage efficiency
UCSD Multi-Agent Robotics LabUndergraduate Researcher10/2025 – Present
Research project in UCSD Multi-Agent Robotics Lab focusing on distributed robotic coverage using Voronoi-based algorithms. The work connects theory, control, localization, and experimental performance on real robotic platforms.
Domain
Distributed robotics
Core Method
Voronoi coverage + centroid control
Stack
Python, ROS, data logging
Tools Used
PythonROSMulti-agent AlgorithmsExperimental Robotics Platforms
Research Sponsors
- National Science Foundation
- AFOSR
- Naval Research Laboratory
- Northrop Grumman
Engineering Challenges
- Making distributed coverage logic converge reliably when localization, mapping quality, and communication imperfections affect robot behavior.
- Integrating control laws with ROS feedback loops so theoretical updates remain stable on physical hardware.
- Measuring coverage efficiency and convergence with enough experimental discipline to support real research conclusions.
Design Approach
- Developed Voronoi-based coverage and centroid control algorithms for distributed workspace allocation.
- Integrated localization, mapping, and ROS feedback control to support repeatable robot operation.
- Implemented multi-agent coordination logic and evaluated convergence behavior and coverage efficiency.
Validation / Testing
- Performed system identification and controller tuning using experimental data logging.
- Observed closed-loop behavior on multi-agent robotic platforms rather than relying only on simulation.
- Tracked convergence quality and controller response to refine gains and coordination behavior.
Results / Impact
- Built a stronger bridge between distributed robotics theory and experimentally validated system behavior.
- Improved controller tuning and measurement discipline for multi-agent coverage experiments.
- Contributed research infrastructure relevant to autonomy, control, and robotics experimentation.
Next Steps
- Expand testing across larger workspaces and more diverse multi-robot scenarios.
- Refine robustness against localization error and dynamic disturbances.
- Compare coverage performance across alternative coordination and feedback strategies.
Project Media
Replace with test footage, CAD renders, GitHub links, or experiment media when available.