In medical settings, IV infusions deliver intravenous fluids or medications by allowing fluid to flow from an IV bag through tubing and a drip chamber, known as an administration set. In this talk, we will show how SAFEflow uses embedded vision and machine learning to observe fluid behavior directly and turn this process into a continuously monitored, closed-loop system. We will focus on how the product works: the imaging approach, the vision pipeline, the algorithms used to estimate flow rate and infused volume and the control methods that enable accurate real-time adjustment. We will also discuss the engineering challenges involved in making the system robust in clinical settings, including the need for high accuracy and reliability.
Embedded Vision for Real-Time Gravity Infusion Monitoring and Control
Session Speakers
-
Dirk van der Merwe
Autonomous Robotics Lead, DEKA Research & Development
Dirk van der Merwe, currently the Autonomous Robotics Lead at DEKA Research & Development, has over 20 years of experience at the intersection of robotics, medical devices and space exploration. With degrees in Electrical and Electronics Engineering and Mechanical Engineering, he began his career as an aerospace engineer, contributing to projects such as South Africa’s SUNSAT microsatellite and NASA’s CatSat under the STEDI program. At DEKA, Dirk has focused on developing control algorithms for various mobility and medical devices, including the iBOT wheelchair and the LUKE arm. He has also led teams for projects such as the DARPA Prosthetic Arm Project and the Roxo delivery robots. Dirk’s expertise encompasses perception systems; localization and path planning; integrating advanced technologies like deep learning algorithms; and LiDAR sensors. Today, he oversees all autonomous robot development at DEKA.
