Papers
6
Total Citations
77
H-Index
4
About
Dr. Chongben Tao is a leading researcher in robotics and artificial intelligence, specializing in the control and optimization of bipedal and humanoid robots. His work focuses on solving high-dimensional, nonlinear challenges in locomotion, including gait control, walking stability, and dynamic jumping. Dr. Tao’s major contributions include pioneering parallel deep reinforcement learning algorithms, such as a parallel Deep Deterministic Policy Gradient (DDPG) method for biped gait control, which significantly improves training speed and stability. He has also advanced multiobjective collaborative reinforcement learning for complex jumping tasks and developed a parallel comprehensive learning particle swarm optimizer for humanoid walking optimization. Beyond locomotion, Dr. Tao has made notable strides in 3D semantic robot VSLAM, enhancing indoor environmental mapping accuracy using Mask R-CNN. His most-cited works, including publications in 2020 and 2022, each with 21 citations, demonstrate the growing impact of his research on autonomous robotics. By integrating deep reinforcement learning with swarm intelligence and visual SLAM, Dr. Tao’s work is shaping the next generation of agile, perceptive robots capable of navigating and interacting with complex environments.
Research Focus
Key Achievements
Top Papers
- 1Parallel Deep Reinforcement Learning Method for Gait Control of Biped Robot21 citations · 2022
- 2
- 3
- 4
- 5
- 63D Visual SLAM Based on Multiple Iterative Closest Point2 citations · 2015