Max Robotics — Global Service Robot Directory + US Certification

About

Shilang Chen is a leading researcher in simultaneous localization and mapping (SLAM) for autonomous robotics, with a particular focus on cloud-edge collaborative systems and visual SLAM (VSLAM). His work bridges the gap between explicit and implicit representations in VSLAM, introducing innovative methods for cross-data association that enhance both real-time performance and geometric precision. Chen’s most impactful contributions include the development of BiCR-SLAM, a multi-source fusion system tailored for biped climbing robots in complex truss environments, and a comprehensive review of cloud-edge SLAM that has garnered significant attention for its vision of asynchronous collaboration and implicit representation transmission. His research on multi-scale convolutional features for semantic segmentation in indoor scenes has also advanced scene understanding for service robots. With over 40 citations across his top papers, Chen’s work on cloud-edge collaborative VSLAM, including the use of Variable-Order Chebyshev-KAN for optimizing transmission, addresses critical challenges in communication-limited environments. Notably, his cross-scene loop-closure detection with continual learning mimics human memory retention, pushing the boundaries of autonomous navigation. Chen’s achievements position him as a key innovator in making SLAM systems more efficient, scalable, and adaptable for real-world robotic applications.