We present GreenAuto, an end-to-end automated platform designed for sustainable AI model exploration, generation, deployment, and evaluation. GreenAuto employs a Pareto front-based search method within an expanded neural architecture search (NAS) space, guided by gradient descent to optimize model exploration. Pre-trained kernel-level energy predictors estimate energy consumption across all models, providing a global view that directs the search toward more sustainable solutions. By automating performance measurements and iteratively refining the search process, GreenAuto demonstrates the efficient identification of sustainable AI models without the need for human intervention.

Abstract--We are developing a self-learning mechatronic golf robot using combined data-driven and physics-based methods, to have the robot autonomously learn to putt the ball from an arbitrary point on the green. Apart from the mechatronic control design of the robot, this task is accomplished by a camera system with image recognition and a neural network for predicting the stroke velocity vector required for a successful hole-in-one. To minimize the number of time-consuming interactions with the real system, the neural network is pretrained by evaluating basic physical laws on a model, which approximates the golf ball dynamics on the green surface in a data-driven manner. Thus, we demonstrate the synergetic combination of data-driven and physics-based methods on the golf robot as a mechatronic example system. With the aid of autonomous robots, the everyday life of many people should be made easier in the near future, e.g., by For this, a prudent action of the autonomous robot is essential.

While Airbnb brought enormous attention to the short-term vacation rental space, more specialized players are now entering the industry, bringing differentiated offerings to a new trend in hospitality. As the amount of vacation rentals available flourishes, the trickiness in pricing rentals relevant to demand and the competition becomes more critical. Portland-based Vacasa, currently the second largest vacation rental management company in the United States, is bringing a new pricing model that utilizes machine learning and artificial intelligence to the industry to combat this issue. I was able to stay at one of Vacasa's properties in La Quinta, California, shortly before the Coachella Music festival kicked off, which brought in huge wave of demand for vacation rentals for festival goers in the Coachella valley. The new dynamic pricing technology, Yield Management 2.0, will set pricing for more than 5,000 vacation rentals across the country.