Dongping Wu
Papers
2
Total Citations
9
H-Index
2
About
Dongping Wu is a robotics researcher specializing in locomotion control for quadruped robots, with a particular focus on enabling stable movement in complex, unknown environments. His work bridges classical control theory and modern machine learning, addressing fundamental challenges in legged robotics. Wu's most cited paper, "Quadruped Robot Locomotion in Unknown Terrain Using Deep Reinforcement Learning" (2020, 5 citations), demonstrates how deep deterministic policy gradient (DDPG) algorithms can generate adaptive gait policies without explicit terrain modeling. This contribution is significant for advancing autonomous navigation in unstructured settings. In related work, "SLIP Model-Based Foot-to-Ground Contact Sensation via Kalman Filter for Miniaturized Quadruped Robots" (2019, 4 citations), Wu developed a sensor fusion approach using the Spring-Loaded Inverted Pendulum (SLIP) model and Kalman filtering to estimate foot contact forces—a critical capability for small-scale robots lacking expensive tactile sensors. Though his citation counts are modest, Wu's research represents foundational steps toward more robust, perceptive quadruped locomotion, combining reinforcement learning with classical state estimation techniques. His work is particularly relevant for students and researchers exploring practical implementations of learning-based control in resource-constrained robotic platforms.
Research Focus
Key Achievements
Top Papers
- 1
- 2