Daqi Jiang
Papers
5
Total Citations
94
H-Index
5
About
Daqi Jiang is a robotics researcher whose work bridges deep reinforcement learning, brain–computer interfaces, and intelligent industrial automation. His most cited paper, "Mastering the Complex Assembly Task With a Dual-Arm Robot: A Novel Reinforcement Learning Method" (2023, 32 citations), tackles the challenge of acquiring large-scale motion data from physical robots by proposing a neural network training algorithm that enables complex dual-arm assembly without extensive real-world data collection. In parallel, Jiang has pioneered human–robot interaction through single-channel EEG signals, developing an end-to-end CNN with residual blocks for online mobile robot control (2022, 31 citations). His contributions extend to construction automation, where he introduced attention-enhanced machine vision for precise concrete vibration timing (2023, 20 citations) and a continuous vibration method integrating spatial features (2024). Early work on an industrial intelligent grasping system based on CNNs (2022, 5 citations) achieved a high gripping success rate while minimizing dataset preparation time, making it practical for factory deployment. Across these projects, Jiang consistently addresses the core robotics challenge of transferring learning from simulation or limited data to reliable real-world performance. His work demonstrates a rare versatility, applying advanced AI methods to domains as diverse as assembly, brain-controlled navigation, and concrete construction, with each contribution targeting a specific industrial bottleneck.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5