Wenhao Ding

Papers

Total Citations

H-Index

About

Wenhao Ding is an emerging researcher at the intersection of robotics, reinforcement learning, and artificial intelligence, with a focus on advancing the capabilities and safety of autonomous systems. His work spans active perception, sim-to-real transfer, and privacy in embodied AI — areas that collectively address some of the most pressing challenges in deploying intelligent robots in real-world environments. Among his notable contributions, Ding's 2023 paper "Learning to View: Decision Transformers for Active Object Detection" (16 citations) demonstrates how coupling planning with perception through transformer-based architectures can significantly enhance a robot's ability to gather environmental information dynamically. His work on differentiable causal discovery offers a principled approach to diagnosing and closing the simulation-to-reality gap — a persistent bottleneck in robot learning pipelines. More recently, his investigation into privacy risks within household robotics AI highlights a growing and underexplored concern as embodied systems become increasingly integrated into personal spaces. Ding's research reflects a broad and forward-thinking vision: not only making robots more capable, but also more trustworthy and deployable. Students interested in the future of safe, intelligent robotics will find his work both technically rigorous and practically motivated.