Papers
8
Total Citations
218
H-Index
7
About
Mark Ollis is a leading researcher in autonomous mobile robotics, with a focus on terrain perception, navigation, and machine learning for field robots. His work addresses the fundamental challenge of enabling robots to operate safely and efficiently in unstructured, natural outdoor environments. A major contribution is his development of a hybrid approach to terrain classification, which combines unsupervised learning of color models with supervised learning of geometric features to predict traversability—a method detailed in his highly cited 2006 paper (76 citations). He also pioneered the use of panoramic stereo vision for wide-field-of-view perception (52 citations) and introduced a Bayesian framework for imitation learning in robot navigation (31 citations). Notably, his research extends to practical industrial applications, including position measurement systems for automated mining machinery. Ollis has also advanced path planning by proposing image-space planning, which avoids the distortions of traditional Cartesian costmaps. With over 200 total citations, his work has significantly influenced the fields of off-road navigation, autonomous driving, and mining automation.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3A Bayesian approach to imitation learning for robot navigation31 citations · 2007
- 4Position Measurement for Automated Mining Machinery16 citations · 1999
- 5Image-based path planning for outdoor mobile robots14 citations · 2008
- 6
- 7Image‐based path planning for outdoor mobile robots12 citations · 2009
- 8Using Learned Features from 3D Data for Robot Navigation4 citations · 2007