David Mulvaney
Papers
14
Total Citations
155
H-Index
7
About
David Mulvaney is a leading figure in mobile robotics, whose career has been defined by pioneering work in autonomous navigation and path planning. His research focuses on enabling robots to intelligently traverse complex, dynamic environments, bridging the gap between reactive behavior and deliberative planning. Mulvaney’s most significant contributions include the development of a genetic algorithm (GA) planner that rapidly determines optimal paths by restricting its search to obstacle vertices—a method introduced in his highly cited 2007 paper (28 citations). He also advanced the field with his novel waypoint-based navigation system, which allows robots to learn from reactive exploration for future deliberative movement (16 citations). A consistent theme in his work is the application of incremental machine learning, particularly decision trees, to create robots that can adapt to unexpected events in real-time. His 2006 paper on a fast, memory-efficient incremental decision tree algorithm (11 citations) exemplifies this focus. With a body of work spanning over two decades, Mulvaney’s research has provided foundational techniques for efficient, adaptive robot control, earning him over 150 total citations and solidifying his reputation as a key innovator in intelligent robotic navigation.
Research Focus
Key Achievements
Top Papers
- 1Robot Navigation by Waypoints31 citations · 2008
- 2Mobile Robot Path Planning in Dynamic Environments28 citations · 2007
- 3Genetic-based Mobile Robot Path Planning using Vertex Heuristics21 citations · 2006
- 4Waypoint-based Mobile Robot Navigation16 citations · 2006
- 5On-line learning of fuzzy decision trees for global path planning11 citations · 1999
- 6
- 7
- 8Robot Navigation Using Decision Trees7 citations · 2003
- 9
- 10Efflcient incremental decision tree generation for embedded applications5 citations · 2005