Xiaojia Xiang
Papers
4
Total Citations
60
H-Index
4
About
Xiaojia Xiang is a leading researcher in multi-robot systems and bio-inspired robotics, with a focus on decentralized control, deep reinforcement learning, and autonomous navigation. Her most influential work introduces a novel Deep Reinforcement Learning framework using a Multicritic Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm for decentralized multi-robot path planning, which overcomes communication constraints and computational complexity—a paper that has already garnered 22 citations since 2024. She has also pioneered end-to-end formation control for robotic fish through deep reinforcement learning combined with non-expert imitation, achieving 21 citations. In the domain of robotic manipulation, Xiang developed a robust, task-oriented markerless extrinsic calibration method for pick-and-place scenarios, cited 9 times. Her earlier work on evaluating fin-ray trajectory tracking of bio-inspired robotic undulating fins, published in 2014, remains a foundational reference with 8 citations. Xiang’s contributions bridge theoretical advances in multi-agent reinforcement learning with practical applications in swarm robotics and autonomous systems, making her a key figure in the evolution of intelligent, cooperative robotic platforms.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4