Zuohua Ding
Papers
15
Total Citations
427
H-Index
10
About
Zuohua Ding is a distinguished researcher whose work spans robotics, multi-robot systems, and intelligent motion planning — fields at the intersection of artificial intelligence, control theory, and autonomous systems. His most influential contribution, a deep Q-learning framework incorporating experience replay and heuristic knowledge for robot path planning (2019, 154 citations), demonstrated how reinforcement learning could be practically harnessed to tackle complex navigation and obstacle avoidance challenges. Building on this foundation, Ding has made significant strides in multi-robot coordination, developing distributed algorithms to address collision avoidance and deadlock prevention — problems that become exponentially complex as robot swarms scale in size. His 2017 papers on distributed motion planning and deadlock avoidance (73 and 49 citations respectively) established him as a leading voice in decentralized robotic control. More recently, Ding has pushed into the critical domain of adversarial robustness, exploring how GAN-based frameworks and causal deconfounding techniques can protect robot motion planning systems against localization and deception attacks — a timely contribution as autonomous systems face increasing cybersecurity threats. Spanning formal verification of fuzzy systems to cutting-edge reinforcement learning, his body of work reflects both theoretical rigor and practical relevance.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4A distributed approach to robust control of multi-robot systems41 citations · 2018
- 5A distributed method to avoid higher-order deadlocks in multi-robot systems32 citations · 2019
- 6
- 7
- 8
- 9
- 10Stability Analysis of Switched Fuzzy Systems Via Model Checking11 citations · 2014