Alessandro Pozzi
Papers
2
Total Citations
6
H-Index
2
About
Alessandro Pozzi is a robotics researcher whose work focuses on the intersection of model predictive control, reinforcement learning, and physical human-robot interaction. His primary research areas include force control, interaction control, and learning-based methods for robotic manipulation in constrained environments. Pozzi has made significant contributions to the development of intelligent controllers that enable robots to safely and accurately interact with their surroundings. Notably, his work on "Optimized Residual Action for Interaction Control with Learned Environments" (2023, 4 citations) introduces a novel framework that combines learned environment models with optimized residual actions to improve force tracking and compliance. His paper "Experimental Validation of an Actor-Critic Model Predictive Force Controller for Robot-Environment Interaction Tasks" (2023, 2 citations) further demonstrates the practical application of these methods, validating their effectiveness in real-world industrial settings. Through his research, Pozzi addresses the critical challenge of enabling robots to perform precise force-controlled tasks—such as assembly, polishing, or grinding—without requiring extensive manual tuning, thereby advancing the deployment of adaptive and safe robotic systems in industry.
Research Focus
Key Achievements
Top Papers
- 1
- 2