Max Robotics — Global Service Robot Directory + US Certification

About

Hyesoon Kim is a computer systems researcher whose work sits at the intersection of edge computing, deep neural networks (DNNs), and robotics. Her research addresses one of the most pressing challenges in modern AI deployment: how to efficiently execute computationally intensive neural network inference on resource-constrained edge devices and collaborative robots. Her 2019 paper characterizing DNN deployment on commercial edge devices has garnered 109 citations, reflecting its significance in benchmarking real-world AI performance beyond datacenter environments. Alongside this, her work on distributed perception by collaborative robots (88 citations) demonstrated how machine learning can empower multi-robot systems to process rich sensor streams in real time. Kim has further expanded her contributions to hardware-software co-design, exploring RISC-V FPGA platforms for ROS-based robotics and FPGA-accelerated sparse matrix computations at the edge. Her parallelization techniques for low-communication DNN inference underscore her commitment to practical, scalable AI solutions for IoT and autonomous systems. Across her portfolio, Kim consistently bridges the gap between theoretical deep learning advances and the demanding realities of edge deployment, making her research essential reading for anyone working on embedded AI or robotics systems.