Zizhao Wang

Papers

Total Citations

H-Index

About

Zizhao Wang is a robotics researcher whose work sits at the intersection of human-robot interaction, reinforcement learning, and computer vision. His primary research focuses on making robot learning more efficient and accessible by leveraging human feedback and multi-modal sensory inputs. Wang’s most cited work, “Maximizing BCI Human Feedback using Active Learning” (2020, 8 citations), addresses a critical bottleneck in Learning from Human Feedback (LfHF): the need for constant human attention. By integrating active learning strategies, his approach intelligently queries human evaluators only when necessary, dramatically reducing the cognitive burden on non-expert users while maintaining training efficacy. In “CLAMGen: Closed-Loop Arm Motion Generation via Multi-view Vision-Based RL” (2021, 2 citations), Wang tackles the fundamental challenge of safe, collision-free arm trajectory generation. He proposes a vision-based reinforcement learning framework that uses multiple camera views to enable closed-loop control, allowing robots to adapt their motion in real-time based on visual feedback. This work bridges the gap between perception and action, a key challenge in deploying robots in unstructured environments. Wang’s contributions are particularly notable for their focus on practical, real-world deployment, seeking to democratize robotics by enabling non-experts to train and interact with autonomous systems.