Zhihui Zhu

About

Zhihui Zhu is a rising researcher at the intersection of robotics, artificial intelligence, and quantum computing, whose work addresses fundamental challenges in autonomous navigation under uncertainty. Their most-cited paper, "Quantum Exploration-based Reinforcement Learning for Efficient Robot Path Planning in Sparse-Reward Environment" (2024, 3 citations), introduces a novel framework that leverages quantum-inspired exploration strategies to overcome the notoriously difficult sparse-reward problem in reinforcement learning. This work is particularly significant for real-world deployment, where robots must adapt quickly in unstructured environments—such as disaster sites—despite limited onboard computing and dynamic disruptions. By integrating quantum principles with classical reinforcement learning, Zhu’s approach promises faster convergence and more efficient path planning than traditional methods. Though early in their career, this contribution signals a forward-looking research agenda that bridges quantum computing and embodied AI. Their work holds practical implications for search-and-rescue, autonomous inspection, and other mission-critical applications where computational efficiency and rapid adaptation are paramount. As the field moves toward more resilient and intelligent robotic systems, Zhihui Zhu’s research offers a compelling glimpse into how quantum-enhanced algorithms can unlock new capabilities for real-world autonomy.

Research Focus

Key Achievements

Top Papers

1. 1
   Quantum Exploration-based Reinforcement Learning for Efficient Robot Path Planning in Sparse-Reward Environment

   3 citations · 2024

Key Collaborators

Contact & Links