Mohamed Khalid M Jaffar

University of Maryland, College Park

Papers

4

Total Citations

12

H-Index

2

About

Mohamed Khalid M Jaffar is a robotics researcher whose work sits at the intersection of autonomous navigation, vision-language models (VLMs), and legged locomotion. His key contributions include developing **BehAV**, a behavioral rule-guided autonomy framework that leverages VLMs to enable robots to interpret complex human instructions for outdoor navigation—a critical step toward more intuitive human-robot interaction. He also introduced **VLM-GroNav**, which physically grounds vision-language models to assess terrain traversability, allowing robots to make safer, context-aware decisions in unstructured environments. In quadrupedal locomotion, Jaffar proposed **CROSS-GAiT**, a cross-attention-based multimodal fusion approach that adapts gait parameters in real-time across complex terrains by integrating visual and proprioceptive data. His work on online motion replanning via invariant funnels (PiP-X) addresses the challenge of dynamic obstacle avoidance. Though early in his career, with his most-cited papers already garnering attention, Jaffar’s research is pioneering the integration of semantic understanding with physical reasoning—pushing toward robots that can navigate not just efficiently, but intelligently, in the wild.

Research Focus

Key Achievements

2
H-Index
4
Papers
12
Total Citations
3
Avg Citations/Paper
🏆 Most Cited Paper
Behav: Behavioral Rule Guided Autonomy Using VLMs for Robot Navigation in Outdoor Scenes
4 citations · 2025
📈 Most Prolific Year: 2025 (2 Papers)
🤝 Key Collaborators: 13
🏛 Institutions: University of Maryland, College Park

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 15 days ago