Description
As part of a multidisciplinary team project, I contributed to the design and development of an autonomous vehicle capable of navigating a randomly configured maze and collecting tennis balls under competition constraints. The robot combined mechanical design, electrical integration, and advanced computer vision, resulting in a highly customized system that demonstrated the ability to adapt to uncertain environments. This project allowed me to merge hardware and software expertise, work through real-world system integration challenges, and explore strategies for improving autonomous navigation in complex spaces.
- Designed and fabricated a custom tank chassis powered by a 20V battery system with voltage regulation for stable performance.
- Integrated Nvidia mini-PC, Intel RealSense camera, and LiDAR for depth sensing and spatial mapping.
- Implemented a YOLO-based object detection system to identify and collect tennis balls.
- Combined LiDAR and depth data for dynamic navigation and adaptive decision-making.
- Addressed maze navigation challenges, gaining experience in wall-following algorithms and system optimization.
Pictures
