Neil Dhir
Papers
1
Total Citations
3
H-Index
1
About
Neil Dhir’s research lies at the intersection of robotics, machine learning, and human-robot interaction, with a particular focus on developing robust, unsupervised methods for understanding human behavior. His key contributions center on activity recognition and tracking, where he has pioneered the use of nonparametric Bayesian models to overcome the limitations of traditional supervised learning. In his most cited work, “Nonparametric Bayesian models for unsupervised activity recognition and tracking” (2016), Dhir addresses a critical challenge in robotics: enabling machines to safely navigate environments populated by humans without relying on noisy or unrealistic assumptions about training data. By leveraging Bayesian nonparametrics, his approach allows robots to autonomously discover and adapt to human locomotion patterns, significantly enhancing their ability to operate in dynamic, real-world settings. Though his citation count is modest, Dhir’s work is notable for its foundational impact on unsupervised learning in robotics, offering a principled alternative to data-hungry supervised methods. His research continues to influence the development of more adaptive and human-aware autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1