David Do

Google (United States)

Papers

2

Total Citations

17

H-Index

2

About

David Do is a pioneering researcher at the intersection of robotics and artificial intelligence, with a primary focus on scaling deep reinforcement learning (RL) for real-world, autonomous systems. His most notable contribution is the development of a groundbreaking system that applies deep RL to robotic manipulation at an unprecedented scale: sorting recyclables and trash using a fleet of mobile manipulators in office buildings. This work, detailed in his highly cited 2023 paper, demonstrates how to bridge the gap between simulated training and practical deployment, addressing critical challenges in bootstrapping real-world policies. By integrating scalable algorithms with physical robot fleets, Do has shown that deep RL can move beyond controlled labs into messy, dynamic environments—a major leap for sustainable automation. His research has garnered significant attention, with his flagship paper accumulating 15 citations shortly after publication, reflecting its impact on both academia and industry. Do’s achievements highlight his role as a key figure in making autonomous waste sorting economically viable, paving the way for smarter, greener cities and inspiring future work in large-scale robotic learning.

Research Focus

Key Achievements

2
H-Index
2
Papers
17
Total Citations
9
Avg Citations/Paper
🏆 Most Cited Paper
Deep RL at Scale: Sorting Waste in Office Buildings with a Fleet of Mobile Manipulators
15 citations · 2023
📈 Most Prolific Year: 2023 (2 Papers)
🤝 Key Collaborators: 43
🏛 Institutions: Google (United States)

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago