Papers
2
Total Citations
56
H-Index
2
About
Hui Gong is a researcher specializing in autonomous robotics and deep reinforcement learning, with a particular focus on intelligent path planning for mobile robots. His work addresses fundamental challenges in applying reinforcement learning algorithms to real-world robotic navigation, where limited environmental observability and slow convergence have historically constrained practical deployment. Gong's most significant contributions center on enhancing the Deep Deterministic Policy Gradient (DDPG) algorithm, a powerful deep reinforcement learning approach designed to handle continuous action spaces in robotic systems. Recognizing that standard DDPG implementations struggle with low training efficiency and sluggish convergence in mobile robot contexts, Gong has pioneered the integration of Long Short-Term Memory (LSTM) networks to improve temporal reasoning and environmental awareness during training. His 2022 paper on this approach has garnered 46 citations, reflecting its strong resonance within the robotics and AI research communities. A companion publication exploring intelligent DDPG-based path planning has accumulated an additional 10 citations. Through the Actor-Critic framework, Gong's research ensures smoother, more continuous robot motion trajectories, bridging the gap between theoretical reinforcement learning models and practical robotic applications. His work is an important reference for researchers seeking to deploy adaptive, learning-based navigation systems in dynamic, partially observable environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2