Papers
12
Total Citations
190
H-Index
9
About
Jane Mulligan is a prominent robotics and computer vision researcher whose work has significantly advanced the field of autonomous robot navigation in unstructured outdoor environments. Her research sits at the intersection of machine learning, computer vision, and mobile robotics, with a particular focus on enabling robots to reliably identify traversable terrain and plan safe paths through complex, real-world settings. Mulligan's most influential contribution, "Learning Terrain Segmentation with Classifier Ensembles for Autonomous Robot Navigation in Unstructured Environments" (2009, 64 citations), established foundational techniques for using ensemble learning methods to solve the challenging problem of terrain classification using stereo vision. Her broader body of work explores complementary themes including image-space path planning, long-term concept drift adaptation, online learning with multiple perceptual models, and strategies for handling imbalanced training data—all critical challenges when deploying robots in dynamic, unpredictable environments. Her early work on topological mapping with visual manifolds (2005) demonstrates a sustained commitment to vision-based robot localization and mapping. Mulligan also served as a guest editor for the Journal of Field Robotics' special issue on machine learning-based robotics, reflecting her recognized leadership in the community. Collectively, her publications have garnered over 175 citations, cementing her as a key contributor to intelligent autonomous systems research.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5An experimental analysis of classifier ensembles for learning drifting concepts over time in autonomous outdoor robot navigation13 citations · 2007
- 6
- 7Topological Mapping with Multiple Visual Manifolds12 citations · 2005
- 8
- 9
- 10