Cristian Consonni
Papers
1
Total Citations
7
H-Index
1
About
Cristian Consonni’s research bridges machine learning, path planning, and optimization, with a particular focus on the Markov–Dubins problem—a classic challenge in robotics and trajectory design. His most-cited work, “A new Markov–Dubins hybrid solver with learned decision trees” (2023, 7 citations), pioneers the integration of machine learning models into path planning, demonstrating how decision trees can efficiently approximate optimal solutions. This hybrid approach reduces computational overhead while maintaining accuracy, offering a scalable alternative to traditional solvers. Beyond this, Consonni’s broader contributions span computer vision, physics simulation, and user profiling, where he applies data-driven techniques to solve complex, real-world problems. His work stands out for its interdisciplinary reach, combining theoretical rigor with practical applicability. With a growing citation footprint, Consonni is establishing himself as a versatile researcher whose innovations in learned solvers are shaping the future of autonomous navigation and decision-making systems.
Research Focus
Key Achievements
Top Papers
- 1A new Markov–Dubins hybrid solver with learned decision trees7 citations · 2023