Jiwei Zhu
Papers
5
Total Citations
23
H-Index
4
About
Jiwei Zhu is a robotics researcher advancing the frontier of learning from demonstrations (LfD) and autonomous navigation. His work centers on enabling robots to generalize skills across unfamiliar environments with minimal data—a critical challenge for real-world deployment. Zhu’s key contributions include developing domain-adaptive meta-learning frameworks that allow robots to transfer knowledge from visual demonstrations to new tasks and settings, as demonstrated in his highly cited 2022 paper on random domain-adaptive meta-learning (8 citations). He has also pioneered the UP3 framework, an unsupervised predictive path planner that lets mobile robots navigate unknown environments without expert demonstrations or frequent environment interactions. In multi-robot systems, Zhu has tackled decentralized collision avoidance using deep reinforcement learning combined with trajectory optimization. His research consistently bridges meta-learning, domain adaptation, and robot control, with multiple papers from 2022 accumulating over 20 citations. By reducing the need for extensive retraining or human intervention, Zhu’s work is paving the way toward more adaptable, autonomous robots capable of operating safely and efficiently in dynamic, unstructured spaces.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5