Jeremy Soh

About

Jeremy Soh is a researcher focused on advancing real-time state estimation for autonomous systems, particularly through hardware-accelerated implementations of the Unscented Kalman Filter (UKF). His work addresses the growing demand for fast, accurate, and compact estimation solutions in mobile robotics, including unmanned aerial vehicles (UAVs) and other aerospace applications. Soh’s key contributions include pioneering FPGA-based UKF architectures that enable high-performance, low-latency state estimation within system-on-chip (SoC) platforms. His most cited paper, "An FPGA-Based Unscented Kalman Filter for System-On-Chip Applications" (2016, 27 citations), demonstrates how to meet the computational demands of embedded systems while maintaining a small form factor. He further refined this approach with a five-stage pipeline architecture (2017, 7 citations) to boost throughput, and a scalable, portable FPGA implementation (2017, 3 citations) designed for broader autonomous system integration. By bridging algorithmic efficiency with hardware design, Soh’s work has laid a foundation for more capable, real-time decision-making in next-generation autonomous vehicles and robotics.

Research Focus

Key Achievements

Top Papers

1. 1
   An FPGA-Based Unscented Kalman Filter for System-On-Chip Applications

   27 citations · 2016
2. 2
   A Five-Stage Pipeline Architecture of the Unscented Kalman Filter for System-on-Chip Applications

   7 citations · 2017
3. 3
   A scalable, portable, FPGA-based implementation of the Unscented Kalman Filter

   3 citations · 2017

Key Collaborators

Contact & Links