Max Robotics — Global Service Robot Directory + US Certification

About

Shichao Yang is a robotics and computer vision researcher whose work centers on 3D scene understanding, semantic mapping, and autonomous robot navigation. He is perhaps best known for his contributions to semantic 3D occupancy mapping, where his 2017 paper employing efficient high-order Conditional Random Fields (CRFs) garnered over 86 citations, demonstrating how geometric mapping and semantic segmentation can be effectively unified for large-scale environments. This line of work has direct implications for robot navigation and augmented reality applications. Yang has also made significant strides in single-image scene understanding, developing a real-time Convolutional Neural Network approach for recovering 3D indoor layouts — earning 42 citations — and advancing monocular obstacle avoidance through deep intermediate perception networks, cited 34 times. His 2019 research on learning-based ego-motion estimation introduced homomorphism-based losses and drift correction strategies to improve visual odometry robustness without demanding precise sensor calibration. Early in his career, Yang explored biologically inspired locomotion, proposing an optimized central pattern generator network for humanoid robot walking. Across his body of work, Yang's research consistently bridges deep learning and robotics perception, helping autonomous systems better interpret and navigate complex real-world environments.