Papers
7
Total Citations
151
H-Index
6
About
Mathias Perrollaz is a robotics and computer vision researcher whose work has made significant contributions to autonomous vehicle perception and environment representation. His research focuses primarily on occupancy grid computation, stereo-vision processing, and multi-sensor fusion — core challenges in enabling robots and intelligent vehicles to understand their surroundings reliably. Perrollaz is perhaps best known for his innovative work on computing occupancy grids from stereo-vision using the disparity space, a less conventional but powerful approach that has drawn considerable attention, with his 2012 papers accumulating 42 and 46 citations respectively. By moving occupancy computation directly into disparity space rather than 3D Euclidean space, his methods offered improved efficiency and accuracy for real-world autonomous driving scenarios. His 2012 paper on fusing lidar and stereo-vision data through Linear Opinion Pools further demonstrated his ability to combine complementary sensing modalities for richer environmental understanding. Beyond autonomous vehicles, Perrollaz extended his vision expertise to industrial robotics, exploring teachless teach-repeat paradigms that could automate robot programming through visual feedback. With a consistent publication record spanning obstacle detection, sensor fusion, and robotic manipulation, his cumulative impact — over 150 citations — reflects the broad relevance of his contributions across mobile robotics and intelligent systems communities.
Research Focus
Key Achievements
Top Papers
- 1Computing occupancy grids from multiple sensors using linear opinion pools46 citations · 2012
- 2
- 3Using the disparity space to compute occupancy grids from stereo-vision24 citations · 2010
- 4
- 5Obstacle Detection Based on Fusion Between Stereovision and 2D Laser Scanner11 citations · 2007
- 6Teachless teach-repeat: Toward vision-based programming of industrial robots10 citations · 2012
- 7