Kangkang Duan

University of British Columbia

Papers

6

Total Citations

59

H-Index

4

About

Kangkang Duan is an emerging researcher at the intersection of robotics, artificial intelligence, and construction automation, with a focus on developing intelligent robotic systems capable of operating in complex, unstructured environments. His work spans reinforcement learning, imitation learning, and human-robot collaboration, addressing some of the most pressing challenges in deploying autonomous robots on construction sites. Duan's most-cited contribution explores robot morphology evolution for HVAC inspection tasks, combining graph heuristic search with reinforcement learning to enable adaptive robot design — a paper that has already garnered 17 citations since 2023. His research into safety-constrained deep reinforcement learning for human-robot collaboration (13 citations) tackles the critical challenge of keeping human workers safe alongside increasingly autonomous machines. He has also pioneered intuitive training pipelines for construction robots through imitation learning and virtual reality environments, reducing dependence on costly expert demonstrations. More recently, Duan has expanded into multiagent reinforcement learning, enabling coordinated robot teams to handle complex, multi-step construction workflows. Collectively accumulating nearly 60 citations across a compact publication window, his work is rapidly shaping the future of intelligent, collaborative construction robotics.

Research Focus

Key Achievements

4
H-Index
6
Papers
59
Total Citations
10
Avg Citations/Paper
🏆 Most Cited Paper
Robot morphology evolution for automated HVAC system inspections using graph heuristic search and reinforcement learning
17 citations · 2023
📈 Most Prolific Year: 2023 (2 Papers)
🤝 Key Collaborators: 3
🏛 Institutions: University of British Columbia

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4
  5. 5
  6. 6

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 16 days ago