-
FR202503.
Assessing Security of Mobile Robots in Public Spaces.
by Roel Deimann and Tom Broumels.
#Security #Technology
We present an initial version of an attackand
defense matrix for mobile robots in public spaces.
These matrices are the result of modeling threats and
performing security tests on robots by teams of student researchers.
Although we found considerable overlap with existing
Mitre matrices, some of the identified attack tactics
and techniques are specific to mobile robots in public places:
physical tampering, reconnaissance by visual inspection, targeting
ROS. Given the possible consequences on the physical
security of everything in close proximity to the robot, we
recommend the addition of views for mobile robots in public
places to the MITRE matrices.
-
FR202502.
A feasibility study into alternative pressure air matrass detection through machine learning.
by Joris Geurts.
#AI #Health #Technology
Alternating pressure air mattresses play an essential role in the prevention of decubitus. Their presence and smoothless operation
reduces the risk of developing decubitus. Nursing homes in the Netherlands have residents with varying physical conditions, and
have therefore varying types of mattresses. The beds can be equipped with a sensor board that measures pressure and vibrations
continuously. This report presents the investigation in machine learning models that predict the presence of alternative pressure air
mattresses based on the sensor information. Working with a data set of a single nursing home, good accuracy results have been
obtained. Future investigations on explainability of the trained models, as well as testing on larger data sets is needed to improve
the robustness of the model.
-
FR202501.
AI-based Autonomous Driving - How we won the RDW Self Driving Challenge 2024
by Edwin van den Oetelaar, Sieuwe Elferink and Teade Punter.
#AI #Autonomous-driving #Technology
-
FR202402.
On the Suitability of the INTERSECT Open Architecture and SiLA 2 for the Implementation of Self-Driving Laboratories
by Dirk van Zon.
#case-study #architecture #master #fontys-project
Self-driving laboratories (SDLs) enable autonomous discovery through the integration of big data, artificial intelligence, and robotics. The RobotLab project applies this concept to develop a platform for autonomously conducting experiments on complex molecular systems. This research evaluates the applicability of the INTERSECT Open Architecture and SiLA 2 laboratory automation standard with the RobotLab project by designing and implementing an independent SDL. The experimental use case used for this research aims to determine the optimal concentration of sodium dodecyl sulphate (SDS) in water to achieve a target interfacial surface tension, a process that is currently performed manually. Applying viewpoints from the INTERSECT Open Architecture, architectures are designed on multiple levels of abstraction. The microservices architecture is implemented in a demonstrator using the SiLA 2 standard and simulates the surface tension use case. The INTERSECT Open Architecture and the SiLA 2 standard offer a generic way to set up and run an independent SDL. SiLA 2 does limit the microservices orchestration patterns to the orchestration method, which can create a bottleneck with a complex experimental use case, such as experiments with multiple experiments that may depend on each other.
