Peng Zeng
Papers
1
Total Citations
7
H-Index
1
About
Peng Zeng is a leading researcher in robotics and artificial intelligence, with a primary focus on continual learning and its application to autonomous systems. His work addresses one of the most pressing challenges in modern robotics: catastrophic forgetting, where robots lose previously acquired knowledge when learning new tasks. In his highly influential 2024 paper, "Mitigating Catastrophic Forgetting in Robot Continual Learning: A Guided Policy Search Approach Enhanced With Memory-Aware Synapses," Zeng introduced a novel framework that combines guided policy search with memory-aware synaptic consolidation. This approach enables industrial robots to sequentially solve multiple interrelated problems without degrading prior performance—a critical capability for complex, real-world operational scenarios. Although early in its trajectory, the paper has already garnered 7 citations, signaling strong interest from the robotics and machine learning communities. Zeng's contributions are particularly notable for bridging theoretical continual learning methods with practical robotic systems, paving the way for more adaptive and resilient autonomous agents. His work holds significant promise for advancing intelligent manufacturing and long-term robotic deployment.
Research Focus
Key Achievements
Top Papers
- 1