Papers
7
Total Citations
276
H-Index
7
About
Leonardo Trujillo is a leading figure in evolutionary robotics and computational intelligence, whose work has fundamentally reshaped how autonomous systems learn and adapt. His research centers on the intersection of evolutionary computation, robot path planning, and machine learning, with a particular emphasis on developing algorithms that can discover multiple, distinct behaviors without human intervention. Trujillo’s most influential contribution, his 2006 paper on *Multiple Objective Genetic Algorithms for Path-planning Optimization in Autonomous Mobile Robots*, has garnered over 162 citations, establishing a cornerstone for multi-objective optimization in robotics. He is also widely recognized for pioneering the concept of *speciation in behavioral space*, a paradigm that allows evolutionary processes to generate diverse robot strategies from a single run—a breakthrough detailed in his highly cited 2008 and 2011 works. Beyond robotics, Trujillo has advanced genetic programming by introducing *novelty search* for regression and classification, as seen in his 2013 and 2016 papers, which challenge traditional fitness-driven optimization. His innovative approach to evolving classifiers and discovering novel solutions has made him a key thinker in open-ended evolution, inspiring a generation of researchers to move beyond rigid objective functions.
Research Focus
Key Achievements
Top Papers
- 1
- 2Speciation in Behavioral Space for Evolutionary Robotics31 citations · 2011
- 3Discovering Several Robot Behaviors through Speciation24 citations · 2008
- 4Searching for novel regression functions22 citations · 2013
- 5Searching for Novel Classifiers17 citations · 2013
- 6Evolving genetic programming classifiers with novelty search12 citations · 2016
- 7Behavior-based speciation for evolutionary robotics8 citations · 2008