Ananda L. Freire

Universidade Federal do Ceará, Bielefeld University

Papers

Total Citations

103

H-Index

About

Ananda L. Freire’s research lies at the intersection of robotics, neural computation, and cognitive modeling, with a particular focus on how biological principles—such as short-term memory and visuomotor coordination—can be harnessed to improve autonomous robot learning. Her most influential work, “Short-term memory mechanisms in neural network learning of robot navigation tasks: A case study” (2009, 89 citations), investigates how incorporating short-term memory into neural classifiers enhances performance in wall-following navigation, offering a foundational approach to more adaptive robotic systems. This study remains a key reference for researchers exploring memory-augmented learning in mobile robotics. Freire also made notable contributions to humanoid robotics through her work on the iCub platform. Her 2013 paper on kinesthetic teaching demonstrates how a robot can learn visuomotor coordination for pointing through direct physical guidance, while her 2012 study shows that pointing can be achieved without explicit depth calculation—by learning a direct mapping from pixel coordinates to joint angles. These contributions highlight her commitment to biologically inspired, computationally efficient learning strategies. Though her citation counts are modest, Freire’s work is valued for its conceptual clarity and practical relevance in developmental robotics and embodied cognition.