The mission of our research group at CPSquare is centered around the development of theoretical and experimental methods for robotics, automation, and cyber-physical systems (CPS), including autonomous vehicles, unmanned aerial vehicles, and robot manipulators. Our work is focused on three key research directions, detailed below.

We are consistently seeking ambitious graduate and undergraduate students interested in cyber-physical systems and robotics. If you're motivated by addressing fundamental challenges for autonomous systems and are considering theoretical/experimental research collaborations, feel free to contact sfarzan@calpoly.edu.

This research investigates robust motion planning and control strategies for cyber-physical systems, emphasizing safety and resilience in complex, uncertain environments. We explore how autonomous agents (e.g., vehicles, drones) can operate reliably and safely, whether individually or in coordinated groups. Integrating advanced techniques from control theory, artificial intelligence, and machine learning, we address key challenges such as ensuring robustness to sensor noise, environmental disturbances, and unpredictable agent dynamics for individual agents, to design decentralized control strategies for safe and efficient multi-agent coordination, and to create fault-tolerant systems capable of handling component failures or communication disruptions in both single-agent and multi-agent scenarios. The goal is to enable reliable and safe operation of autonomous systems in diverse and dynamic scenarios, and enhance their performance in critical applications such as autonomous transportation, surveillance, and disaster response.

This research investigates advanced vision-guided techniques to enhance robotic capabilities in industrial automation and material handling. We combine robotic vision with motion planning to enable robots to perceive and interact with their environment more effectively. We focus on designing control strategies that use visual feedback (visual servoing) to guide robot motion with high precision and robustness, and to enable accurate manipulation even in dynamic environments. We also develop efficient motion planning algorithms that integrate visual information to enable robots to perform complex manipulation tasks such as assembly, inspection, and packaging. This research aims to revolutionize automation in manufacturing and logistics, leading to increased productivity, reduced operational costs, and improved flexibility in handling diverse tasks.

This research focuses on developing and deploying robotic systems to address key challenges in modern agriculture, to promote sustainable and efficient farming practices. By integrating advanced sensing, actuation, and autonomous decision-making, we aim to optimize crop management, reduce labor demands, and minimize environmental impact. Our research encompasses the development of robust navigation and localization algorithms for robots operating in unstructured agricultural environments to enable autonomous traversal of fields and orchards. We also focus on integrating advanced sensors (e.g., multispectral imaging, LiDAR) and data analytics to enable precise crop monitoring, targeted treatment application, and optimized resource utilization. Furthermore, we design and implement specialized robotic systems for tasks such as planting, harvesting, weeding, and pruning, improving efficiency and reducing reliance on manual labor.