Max Robotics — Global Service Robot Directory + US Certification

About

Zarina Mohd Noh is a robotics researcher whose work focuses on making simultaneous localization and mapping (SLAM) more accessible and cost-effective. Her primary research areas include Rao-Blackwellized particle filters (RBPF), neural network sensor models, and low-cost robotic navigation systems. Noh’s major contribution lies in integrating artificial neural networks with RBPF algorithms to compensate for the noisy measurements produced by low-end sensors like laser distance sensors, enabling reliable SLAM performance without expensive hardware. Her most-cited paper (2023, 7 citations) introduces a Rao-Blackwellized particle filter algorithm integrated with a neural network sensor model, demonstrating how cost-efficient robots can achieve robust mapping and localization. She has also systematically compared sampling methods for RBPF with neural networks (2022, 3 citations) and investigated the effect of neural networks on reducing the number of particles needed for accurate SLAM (2023, 3 citations). Earlier in her career, Noh explored FPGA-based control for hexapod robots (2013, 3 citations), showcasing her versatility in hardware design. Her work is particularly valuable for researchers and students seeking to deploy autonomous robots in indoor environments using affordable sensors, bridging the gap between high-end performance and practical, low-cost solutions.