Govind Thattai

Amazon (United States)

Papers

5

Total Citations

49

H-Index

3

About

Govind Thattai is a leading researcher at the intersection of embodied AI, multi-agent systems, and human-robot interaction. His work focuses on enabling robots to understand natural language instructions and collaborate effectively in complex, real-world environments. Thattai’s major contributions include the development of **Embodied BERT (EmBERT)** (30 citations), a pioneering transformer model that grounds language in visual observations for task completion, and **LEMMA** (8 citations), a benchmark for language-conditioned multi-robot manipulation that allows robots with complementary skills to collaborate. He also introduced **CH-MARL** (6 citations), a multimodal benchmark for cooperative, heterogeneous multi-agent reinforcement learning, and **Alexa Arena** (3 citations), a user-centric simulation platform for embodied AI research. Notably, Thattai played a key role in launching the **Alexa Prize SimBot Challenge**, a major initiative that empowers university students to build conversational agents for embodied tasks. His work has been instrumental in advancing how robots interpret language, collaborate with each other, and interact with humans in dynamic settings, with cumulative citations reflecting growing influence in the field.

Research Focus

Key Achievements

3
H-Index
5
Papers
49
Total Citations
10
Avg Citations/Paper
🏆 Most Cited Paper
Embodied BERT: A Transformer Model for Embodied, Language-guided Visual\n Task Completion
30 citations · 2021
📈 Most Prolific Year: 2023 (3 Papers)
🤝 Key Collaborators: 46
🏛 Institutions: Amazon (United States)

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4
  5. 5

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago