Physical AI refers to using AI techniques to solve problems that involve direct interaction with the physical world, e.g., by observing the world through sensors or by modifying the world through actuators. The data is generated from various sources, including physical sensors and ”human sources,” such as social networks or smartphones. Actuation may range from support to human decisions to managing automated devices(e.g., traffic lights, gates) and actively directing autonomous cars, drones, etc.
One intrinsic feature of Physical AI is the uncertainty associated with the acquired information, its incompleteness, and the uncertainty about the effects of actions over (physical) systems that share the environment with humans. In other words, Physical AI deals with unreliable, heterogeneous, and high-dimensional sources of data/information and a significant set of actuation variables/actions to learn models, detect events, or classify situations, to name just a few cases. In some cases, a decision-making loop is closed over physical systems with their dynamics, often complicated and challenging to model (e.g., weather dynamics, human crowd behavior).
To tackle such large physical problems, existing techniques for data processing and decision-making are not tractable. Thus, one should develop and improve methods that exploit redundancy, combine/infer partial/missing data, transfer knowledge (e.g., through learning) and exploit low-rank characteristics of data to reduce the several relevant dimensions of the problems (in terms of observation, state and action spaces).
YoloV5 model released by Ultralytics for object detection. The component takes one image as input and outputs the coordinates of the bounding boxes of all objects detected in the image.
The Machine Learning (ML) models used to predict both energy needs and future environmental parameters of the some retail stores in Italy
An AI resource to track "group-leader" social interactions within videos
GRIDouble is a comprehensive energy management tool that completely automates the finding of optimal patterns in energy consumption and production in the case of facilities with renewable energy sources.
A toolkit for processing geospatial data, featuring an array of functions and workflows crucial for managing and analyzing information related to geospatial and terrain features. Developed by AMIGO s.r.l. for the ARIA project, part of the I-NERGY 2nd Ope...
This dataset contains hyperspectral images of denim fabric over 224 reflectance bands. It was used to test automated composition analysis in the DIH4AI Open Call 2 FABCOD project (Fabric Composition Detector).
The problem of finding faults in oscillating data in the form of 3-phase current and voltage values is considered. While these kind of data have high resolutions, we give a solution to multivariate changing point detection, framed as an anomaly detection...
Classification of a video segment into a single human action (action recognition)