Papers
3
Total Citations
37
H-Index
3
About
Junxiao Xue is a robotics and artificial intelligence researcher whose work centers on deep reinforcement learning, autonomous navigation, and motion planning for mobile and humanoid robots. His research addresses some of the most pressing challenges in modern robotics: enabling machines to operate intelligently in complex, unpredictable real-world environments. Xue's most recognized contribution is the development of BOAE-DDPG (Bidirectional Obstacle Avoidance Enhancement–Deep Deterministic Policy Gradient), a novel algorithm that empowers mobile robots to plan paths in real time within unknown dynamic environments — a problem that has long resisted robust solutions. This work has garnered 19 citations since its 2024 publication, signaling rapid uptake within the robotics community. His earlier work on M-A3C, a lightweight mean-asynchronous advantage actor-critic method for biped robot gait planning, demonstrated his ability to translate reinforcement learning theory into practical locomotion solutions for humanoid platforms, earning 14 citations. His multi-agent path planning research, combining Model Predictive Control with DDPG, further illustrates his commitment to solving mixed static-dynamic obstacle avoidance at scale. Across his body of work, Xue consistently bridges theoretical reinforcement learning with deployable robotic systems, making him a notable emerging voice in intelligent autonomous robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Multi-Agent Path Planning based on MPC and DDPG4 citations · 2021