Papers
1
Total Citations
6
H-Index
1
About
Qiwei Du is an emerging researcher at the forefront of robot autonomy and neuro-symbolic artificial intelligence. His most notable work centers on bridging the gap between data-driven learning paradigms and principled reasoning systems, addressing a critical challenge in modern robotics: the inability of purely data-centric approaches to generalize across dynamic, real-world environments. His 2025 paper, "Imperative Learning: A Self-Supervised Neuro-Symbolic Learning Framework for Robot Autonomy," has already garnered 6 citations since publication — a promising indicator of early impact in a competitive field. In this work, Du and his collaborators tackle the practical limitations of reinforcement and imitation learning, particularly the high cost and impracticality of data labeling in robotic settings, by proposing a self-supervised framework that integrates neural and symbolic reasoning. This contribution positions him as a thoughtful innovator working to make robotic systems more robust, adaptable, and scalable without heavy reliance on labeled datasets. For students and researchers interested in autonomous systems, machine learning, and cognitive robotics, Du's work represents an exciting and timely direction that could meaningfully shape how next-generation robots learn and operate independently.
Research Focus
Key Achievements
Top Papers
- 1