Laurent Malaterre
Centre National de la Recherche Scientifique, Université Clermont Auvergne
Papers
4
Total Citations
59
H-Index
3
About
Laurent Malaterre is a robotics researcher whose work bridges 3D perception and safe autonomous navigation. His most influential contribution, "CICP: Cluster Iterative Closest Point for sparse–dense point cloud registration" (2018, 38 citations), introduced a novel algorithm that robustly aligns data from different sensor types—a critical challenge for robots operating in real-world environments. This work directly addresses the practical need for fusing sparse LiDAR scans with dense camera depth maps. Earlier, Malaterre advanced object recognition by systematically evaluating 3D keypoint detectors for time-of-flight depth data (2016, 10 citations), providing a benchmark that helps practitioners select the most reliable features for tasks like tracking and mapping. More recently, he has focused on risk-aware path planning, developing a "Novel Occupancy Mapping Framework" (2021, 9 citations) and the "Lambda-Field" (2020, 2 citations)—a continuous alternative to traditional Bayesian occupancy grids. These frameworks enable robots to assess collision probabilities in complex, unstructured environments, moving beyond simple obstacle lists to continuous risk fields. Malaterre’s work is notable for its practical, algorithm-driven approach to making autonomous robots both more perceptive and safer.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4