Papers
3
Total Citations
34
H-Index
3
About
Dongkun Zhang is a researcher advancing the frontiers of autonomous driving and multi-robot systems. His work centers on hierarchical imitation learning, certifiably safe multi-agent navigation, and robust global localization. In his highly cited 2021 paper, Zhang tackles the gap between machine and human driving by proposing a hierarchical driving model that learns continuous intentions and trajectories from demonstrations, addressing the coupled complexity of environments and dynamics (21 citations). He further addresses safety in decentralized multi-robot navigation with a 2022 study introducing a control barrier function (CBF)-based optimizer that ensures high-probability safety using only sensor measurements, enabling flexible and reliable policy execution (10 citations). Most recently, Zhang’s 2025 work on RING# introduces roto-translation equivariant Gram learning for PR-by-PE global localization, a critical capability for autonomous systems operating without GPS. By integrating perception, safety guarantees, and equivariant learning, Zhang’s contributions are shaping more capable and trustworthy autonomous agents, with his research already influencing the fields of robotics and intelligent transportation.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3