Papers
7
Total Citations
214
H-Index
5
About
Nachuan Ma is a robotics researcher whose work bridges learning-based motion planning and autonomous perception, with a particular focus on enabling robots to navigate complex, unstructured environments. His most impactful contribution is a comprehensive survey on learning-based robot motion planning (93 citations), which has become a key reference for researchers exploring how deep learning can overcome the limitations of traditional sampling-based algorithms in high-dimensional spaces. Ma has advanced this field through innovative approaches such as conditional generative adversarial networks for optimal path planning (56 citations) and deep neural network-enhanced sampling-based methods for 3D space (46 citations), both demonstrating significant improvements in path quality and convergence speed. Beyond motion planning, he has made notable contributions to robotic perception for elevator button recognition, creating large-scale datasets for benchmarking segmentation and character recognition—critical for enabling autonomous inter-floor navigation. His recent work extends to infrastructure inspection, with a collaborative dual-branch learning approach for real-time road crack detection on robotic platforms. With over 200 total citations and publications spanning from foundational surveys to applied perception systems, Ma’s research is shaping the next generation of autonomous robots capable of operating safely and efficiently in human environments.
Research Focus
Key Achievements
Top Papers
- 1A survey of learning‐based robot motion planning93 citations · 2021
- 2Conditional Generative Adversarial Networks for Optimal Path Planning56 citations · 2021
- 3Deep Neural Network Enhanced Sampling-Based Path Planning in 3D Space46 citations · 2021
- 4
- 5
- 6
- 7