College - Author 1
College of Engineering
Department - Author 1
Electrical Engineering Department
Degree Name - Author 1
BS in Electrical Engineering
College - Author 2
College of Engineering
Department - Author 2
Electrical Engineering Department
Degree - Author 2
BS in Electrical Engineering
College - Author 3
College of Engineering
Department - Author 3
Electrical Engineering Department
Degree - Author 3
BS in Electrical Engineering
Date
6-2026
Primary Advisor
Siavash Farzan, College of Engineering, Electrical Engineering Department
Abstract/Summary
Modern robotic systems are often evaluated using static and highly controlled tasks, such as pick-and-place demonstrations, which do not fully represent the uncertainty and adaptability required in real-world environments. A major challenge in robotics research is enabling robotic systems to perceive, track, and respond to dynamic objects in real time while maintaining accurate and reliable motion control. This project addresses these challenges by developing an autonomous robotic platform in which an OpenMANIPULATOR-Y robotic arm detects, tracks, and attempts to catch a moving tennis ball using a vision-guided control system. The system integrates YOLO-based object detection with an Intel RealSense D455 depth camera to estimate the tennis ball's position during the early stages of motion and applies projectile-motion equations to predict an interception point for the robotic arm. OMPL was utilized to generate collision-free trajectories that positioned the robotic arm in a predefined ready-state configuration, after which MoveIt Servo provided low-latency real-time control to guide the arm toward the predicted interception point. Hardware experiments demonstrated that the system consistently predicted physically reachable interception points at the fixed interception plane of y = -0.45 m and guided the robotic arm to the predicted location, with the arm arriving approximately 150 ms after the ball crossed the catch plane. Experimental comparisons of multiple OMPL optimization methods further showed that planning time remained negligible compared to robotic motion execution time, while tuned planner configurations improved overall trajectory performance and smooth waypoint execution. The completed system provides a practical platform for studying real-time robotic perception, motion planning, and adaptive control under dynamic conditions. This work contributes to ongoing research in autonomous robotics and intelligent control systems within the field of Electrical Engineering.
URL: https://digitalcommons.calpoly.edu/eesp/729