About

Mubbasir Kapadia is a leading researcher at the intersection of artificial intelligence, robotics, and computer graphics, whose work fundamentally advances how autonomous agents perceive, navigate, and interact within complex, dynamic environments. His primary research areas include social navigation, constraint-aware path planning, and multi-agent systems for emergency response. Kapadia's major contributions center on formalizing the often-unspoken social rules that govern human movement, enabling robots to navigate crowded spaces in a socially compliant manner—a critical step toward seamless human-robot coexistence. His seminal work on SEAN 2.0 (40 citations) provides an open-source framework for training and benchmarking socially-aware navigation policies, while his foundational papers on constraint-aware navigation (27 and 18 citations) pioneered the integration of spatial constraints into path planning algorithms. Kapadia has also made notable advances in GPU-accelerated search (15 citations) and automated landmark identification for indoor navigation (13 citations). His most recent work extends these principles to life-saving applications, using adversarial reinforcement learning to optimize evacuation guidance robots in intelligent fire scenarios. With a research portfolio spanning over a decade, Kapadia's work has garnered significant attention for its practical impact on autonomous systems operating in human-centered environments.

Research Focus

Key Achievements

5
H-Index
6
Papers
116
Total Citations
19
Avg Citations/Paper
🏆 Most Cited Paper
SEAN 2.0: Formalizing and Generating Social Situations for Robot Navigation
40 citations · 2022
📈 Most Prolific Year: 2013 (2 Papers)
🤝 Key Collaborators: 25
🏛 Institutions: Rutgers, The State University of New Jersey, California University of Pennsylvania, Rutgers Sexual and Reproductive Health and Rights

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4
    Dynamic search on the GPU
    15 citations · 2013
  5. 5
  6. 6

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 14 days ago