Search Results for "pollen"

Microduck RL provides reinforcement-learning environments for training behaviors for Pollen Robotics' small bipedal Microduck robot. It is built on mjlab with MuJoCo Warp and trains PPO policies at a 50 Hz control rate. The repository includes tasks for walking, standing up, sitting, kicking, rolling, skating, crouching, and other physical behaviors. Its sim-to-real setup models actuator physics, backlash, domain randomization, and reward design.

Some framework.

The service takes advantage of the environmental control networks existing along the city of Bilbao and the indicators elaborated by their data. These networks consist in a number of networked meteorological stations metering atmospheric variables and other related to pollution, level of pollen in the air, etc. The system uses other data sources in order to provide the user with a complete information overview, including predictions, and taking account predictive simulation and risk models that are being used by some public administrations. The more relevant features for the model are: Geo-referenced data sets about: - Quality of the air in the city - Pollen level - Weather information - Weather forecast