Papers
5
Total Citations
25
H-Index
3
About
Luke E. Richards is a researcher at the forefront of grounded language learning for human-robot interaction, specializing in bridging the gap between natural language and robotic perception. His work focuses on enabling robots to understand non-categorical physical language—how humans describe objects, attributes, and actions in real-world contexts—without relying on predefined categories. Richards’ major contributions include developing novel learning systems that ground language in visual and acoustic percepts, using deep featurization and cross-modal manifold alignment to create consistent, multi-modal embeddings. His 2021 paper, “Learning to Understand Non-Categorical Physical Language for Human Robot Interactions,” has garnered 10 citations, highlighting its impact on shared autonomy interfaces. He has also pioneered practical approaches like triplet loss-based alignment (2020, 2021) and extended grounded learning to raw speech inputs (2022), moving beyond text-based methods. With a total of 25 citations across his top works, Richards is recognized for advancing category-free, real-world language acquisition, making human-robot communication more intuitive and adaptable. His research is essential for students and engineers aiming to build robots that truly understand human language in dynamic environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5Practical Cross-modal Manifold Alignment for Grounded Language2 citations · 2020