Giovanni Delnevo
Papers
2
Total Citations
5
H-Index
1
About
Giovanni Delnevo is a researcher at the forefront of human-robot interaction (HRI), specializing in the integration of Large Language Models (LLMs) and natural language processing to make robotic systems more intuitive and accessible. His work addresses a critical challenge: enabling robots to understand and execute complex commands without extensive pre-training. In his highly cited 2025 study, "Natural Language and LLMs in Human-Robot Interaction: Performance and Challenges in a Simulated Setting" (4 citations), Delnevo systematically evaluates how effectively users can command a robot using everyday language, identifying both the promise and the pitfalls of current LLM-based approaches. He further pushes the boundaries of the field in "Exploring the Capabilities and Limitations of Large Language Models for Zero-Shot Human-Robot Interaction" (1 citation), demonstrating how robots can learn to perform novel tasks on the fly—without any task-specific examples. This zero-shot capability is a game-changer for real-world deployment, where robots must adapt to unpredictable environments. Delnevo’s research is pivotal for students and engineers seeking to build the next generation of collaborative robots that can truly understand and respond to human intent.
Research Focus
Key Achievements
Top Papers
- 1
- 2