

AI4IoT/PhysicalAI pollution dataset
Trondheim data for pollutants PM10,PM2.5,NO2 from 4 urban stations Jan 2014-June 2019
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).
Trondheim data for pollutants PM10,PM2.5,NO2 from 4 urban stations Jan 2014-June 2019
Set of libraries and ROS nodes to detect and track people using 2D lidar
3D orientation estimation algorithm integrated in a full 6D pose estimation pipeline.
Classification of a video segment into a single human action (action recognition)
A data set of 1.8 billion measurements from a mechanical wrist with three axes that can hold tools, for example, for spray painting in combination with a pump. The data set spans six months in 1-second intervals.
Stable Baselines is a set of improved implementations of reinforcement learning algorithms based on OpenAI Baselines.
While reinforcement learning algorithms converge towards a single policy, it may be useful to generate multiple policies instead of just one.
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.
An AI resource to track "group-leader" social interactions within videos
Traffic Control in a Simulated Environment for Pollution Reduction
Monitoring vehicle flows in cities by counting cars from images acquired from smart cameras.