Kai Ding

Papers

Total Citations

H-Index

About

Kai Ding is an emerging researcher specializing in robotic automation, deep reinforcement learning (DRL), and combinatorial optimization, with a particular focus on solving complex 3D bin packing problems for real-world logistics and manufacturing applications. His work sits at the intersection of artificial intelligence and robotics, addressing one of the most practically significant challenges in warehouse automation and supply chain efficiency. Ding's most notable contribution, "Towards reliable robot packing system based on deep reinforcement learning" (2023), has accumulated 37 citations, demonstrating rapid recognition within the robotics and AI communities. This work advances the reliability of autonomous packing systems, a critical requirement for industrial deployment. Building on this foundation, his 2024 paper introducing GOPT — a transformer-based DRL framework for generalizable online 3D bin packing — addresses a key limitation in existing approaches: the inability to perform robustly across diverse packing environments. By leveraging transformer architectures, GOPT represents a meaningful step toward scalable, adaptable packing solutions. Though early in his research career, Ding's growing citation record and consistent focus on bridging theoretical DRL methods with practical robotic systems mark him as a promising contributor to intelligent automation research.