Papers
54
Total Citations
1,203
H-Index
17
About
Lionel Ott is a robotics researcher whose work spans autonomous exploration, environmental mapping, and robot perception — areas that sit at the intersection of probabilistic methods, machine learning, and real-world robot deployment. He is perhaps best known for his contributions to continuous occupancy mapping, most notably the Hilbert Maps framework, which introduced scalable, stochastic gradient descent-based techniques for representing robot environments beyond the limitations of traditional grid maps — work that has collectively attracted nearly 250 citations. His 2020 paper on sampling-based informative path planning, now cited nearly 300 times, has become a key reference for researchers tackling online autonomous navigation in unknown environments. Ott has also advanced multi-robot exploration in challenging subterranean settings using legged and aerial platforms, contributed to 6-DOF grasp detection for cluttered scenes, and developed novel state estimation approaches including a Stein Particle Filter for nonlinear, non-Gaussian systems. His applied work extends to contact-based aerial inspection and autonomous road infrastructure maintenance through the HERON project. Across these diverse contributions, Ott consistently bridges rigorous theoretical foundations with practical robotic systems, making his research highly relevant to both the academic community and real-world deployments.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5Volumetric Grasping Network: Real-time 6 DOF Grasp Detection in Clutter44 citations · 2021
- 6
- 7
- 8Robotic Maintenance of Road Infrastructures: The HERON Project27 citations · 2022
- 9Continuous Occupancy Map Fusion with Fast Bayesian Hilbert Maps26 citations · 2019
- 10Stein Particle Filter for Nonlinear, Non-Gaussian State Estimation26 citations · 2022