Fengkang Ying
Papers
7
Total Citations
72
H-Index
4
About
Fengkang Ying is an emerging robotics researcher whose work sits at the intersection of deep reinforcement learning (DRL) and intelligent robotic motion planning. His research primarily addresses trajectory generation, obstacle avoidance, and policy learning for redundant manipulators — domains where traditional methods often fall short due to their reliance on manual configuration or task-specific inverse kinematics solutions. Ying's most influential contributions include the development of a nested dual-memory deep deterministic policy gradient framework for sequential multiprocess robotic tasks (23 citations) and an actor-critic architecture incorporating expert-guided policy learning and fuzzy feedback rewards for IK-free trajectory generation (20 citations). His 2024 obstacle-avoidable motion planning framework, which has already garnered 17 citations, demonstrates a universal DRL-based approach capable of operating in complex, cluttered environments. More recently, his work on bio-inspired grasping — drawing from the logarithmic spiraling behavior of elephant trunks and octopus arms — reflects a broadening research vision that integrates rigid-soft robot synergy. Across his growing publication record, Ying has accumulated over 70 citations, signaling meaningful early-career impact. His work collectively advances the goal of generalizable, autonomous robotic systems capable of operating safely and efficiently in real-world industrial settings.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7