Papers
44
Total Citations
995
H-Index
19
About
Paolo Valigi is a distinguished researcher whose work spans robotics, computer vision, and autonomous systems, with particular expertise in depth estimation, visual navigation, and robot control. Over three decades of scholarly contribution, his research has accumulated significant influence across both classical and modern machine learning paradigms. Valigi's early foundational work in the 1990s addressed robust stabilization of MIMO dynamical systems and state estimation for industrial robots, establishing his credentials in control theory. His more recent contributions reflect a decisive pivot toward deep learning applications in robotics. His 2016 paper on fast monocular depth estimation using fully convolutional networks (105 citations) became a benchmark in obstacle detection research, while his follow-up work on domain-independent depth estimation further extended its impact (69 citations). His 2020 paper on target-driven visual navigation using deep reinforcement learning (102 citations) demonstrates his ability to tackle complex embodied AI challenges. Beyond perception, Valigi has advanced perception-aware path planning, loop closure detection, agricultural fruit counting via domain adaptation, and natural language interfaces for service robots — reflecting a remarkably broad research portfolio. Collectively, his top papers have garnered over 600 citations, cementing his reputation as a versatile and enduring voice in intelligent autonomous systems research.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4Toward Domain Independence for Learning-Based Monocular Depth Estimation69 citations · 2017
- 5Experimental results in state estimation of industrial robots53 citations · 1990
- 6Evaluation of non-geometric methods for visual odometry49 citations · 2014
- 7
- 8
- 9Perception-aware Path Planning37 citations · 2016
- 10