Giacomo Golluccio
Papers
6
Total Citations
51
H-Index
3
About
Giacomo Golluccio is a robotics researcher whose work centers on robot dynamics identification, task and motion planning, and control in cluttered environments. His most-cited paper, "Robot Dynamics Identification: A Reproducible Comparison With Experiments on the Kinova Jaco" (2020, 32 citations), provides a benchmark for identifying dynamic parameters critical for high-performance model-based control in applications like surgical and legged robotics. Golluccio has made significant contributions to object relocation in clutter, developing tree-based Q-learning algorithms that combine task and motion planning to retrieve target objects efficiently (2021–2022, 5–6 citations each). He also explores null-space control for redundant robots, investigating when local optimization fails and how to learn which secondary objectives to maximize (2023, 3 citations). His work addresses practical challenges in autonomous manipulation, offering reproducible methods and novel learning approaches. With a focus on bridging theory and experiment, Golluccio’s research impacts fields from warehouse automation to assistive robotics, demonstrating a clear trajectory toward more intelligent and adaptable robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6