Tony Carrick

About

Tony Carrick’s research sits at the intersection of embedded systems, machine learning, and precision agriculture, with a focus on deploying deep neural networks (DNNs) at the edge. His most influential work, “Low-Power and High-Speed Deep FPGA Inference Engines for Weed Classification at the Edge” (2019, 98 citations), addresses a critical challenge: bringing the power of DNNs—typically reliant on energy-hungry GPUs—to resource-constrained, real-world environments. Carrick pioneered FPGA-based inference engines that achieve high-speed, low-power classification, enabling real-time weed detection directly in the field. This contribution is foundational for sustainable, autonomous agricultural robotics, demonstrating that complex AI can operate efficiently without cloud connectivity. By optimizing hardware-software co-design, his work has opened pathways for practical edge AI in farming, reducing chemical use and improving crop yields. Carrick’s research is widely cited for its practical impact, bridging the gap between theoretical deep learning and deployable, energy-efficient solutions. His achievements highlight a commitment to making AI accessible and actionable in critical, real-world domains, inspiring students and researchers to explore the frontiers of embedded intelligence.

Research Focus

Key Achievements

Top Papers

1. 1
   Low-Power and High-Speed Deep FPGA Inference Engines for Weed Classification at the Edge

   98 citations · 2019

Key Collaborators

Contact & Links