Elena Arcari

Papers

Total Citations

280

H-Index

About

Elena Arcari is a roboticist whose research lies at the intersection of model predictive control (MPC), machine learning, and autonomous manipulation. Her major contributions center on developing data-driven and learning-augmented control frameworks that enable compliant, cost-effective robots to achieve the high-precision trajectory tracking and versatile task execution typically reserved for expensive industrial hardware. In her highly cited 2019 work (235 citations), she pioneered a data-driven MPC approach for robotic arms, demonstrating that advanced control algorithms can compensate for mechanical compliance to deliver accurate trajectory tracking. More recently, her 2023 paper on Bayesian multi-task learning MPC (45 citations) tackles the fundamental challenge of mobile manipulation—enabling a single robot to perform diverse tasks like door opening and pick-and-place. By integrating Bayesian inference with model-based control, Arcari’s framework allows robots to leverage both first-principles models and task-specific data, improving sample efficiency and adaptability. Her work is notable for bridging the gap between theoretical control advances and practical robotic systems, making sophisticated manipulation capabilities more accessible. Arcari’s research continues to shape how robots learn and execute complex physical interactions in unstructured environments.