Bianca Sangiovanni
Papers
10
Total Citations
289
H-Index
6
About
Bianca Sangiovanni is a robotics and control systems researcher whose work sits at the intersection of deep reinforcement learning, motion planning, and robot manipulator control. She is best known for pioneering hybrid control methodologies that integrate Deep Reinforcement Learning (DRL) with classical control techniques to enable safe, autonomous collision avoidance in robotic manipulators — a critical challenge for human-robot coexistence in shared workspaces. Her 2020 paper on self-configuring robot path planning has garnered 111 citations, while her foundational 2018 work on DRL-based collision avoidance has accumulated 92 citations, underscoring the broad influence of her contributions across the robotics community. Beyond collision avoidance, Sangiovanni has made meaningful contributions to robust control design, particularly through Integral Sliding Mode control schemes and switched-structure controllers for robot manipulators. Her more recent research extends into teleoperation and shared control, exploring how DRL can support human operators commanding remote robotic agents. She has also demonstrated a strong commitment to experimental validation, grounding theoretical advances in practical, real-world assessments using Linear Parameter Varying frameworks. Across her body of work, Sangiovanni consistently bridges the gap between intelligent learning-based methods and rigorous control engineering, making her research highly relevant to both academic robotics researchers and industrial practitioners.
Research Focus
Key Achievements
Top Papers
- 1
- 2Deep Reinforcement Learning for Collision Avoidance of Robotic Manipulators92 citations · 2018
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10