Giovanni Paolo Canuti
Papers
1
Total Citations
1
H-Index
1
About
Giovanni Paolo Canuti is a researcher at the forefront of embodied AI and robotics, specializing in affordance segmentation, neural architecture search (NAS), and efficient deep learning for embedded systems. His work bridges the gap between high-performance computer vision and the stringent constraints of wearable and mobile devices. Canuti’s major contribution is pioneering hardware-aware NAS methods that optimize neural networks for real-time, on-device inference using RGB-D cameras. His 2025 paper, "Filling the Pareto-Optimal Front for Affordance Segmentation on Embedded Devices Using RGB-D Cameras," introduces a reformulated NAS approach with a novel search space, enabling wearable robots to understand object interaction possibilities directly from depth data—a critical step toward autonomous assistive technologies. While still early in his career, his work has already garnered attention for its practical impact on low-power robotics. Canuti’s research promises to make intelligent, context-aware robots more accessible, pushing the boundaries of what is possible in human-robot interaction and assistive devices.
Research Focus
Key Achievements
Top Papers
- 1