Why apply AI to figure skating? Skaters can always keep pushing, higher, faster, stronger. OOFSkate is all about helping skaters figure out a way to rotate a little bit faster in their jumps or jump a little bit higher. The system helps skaters catch things that perhaps could pass an eye test, but that might allow them to target some high-value areas of opportunity. The artistic side of skating is much harder to evaluate than the technical elements because it's subjective.

Figure Skaters at the 2026 Winter Olympics Are Pushing the Limits of What's Possible For years, quad axel jumps seemed impossible. Then Ilia Malinin landed one in 2022. As he heads to the Milano Cortina Games everyone wants to know what's next. In 2021, famed Russian figure skating coach Alexei Mishin said that no figure skater would ever be able to successfully perform a quad axel in his lifetime. The following year, two-time Olympic gold medalist Yuzuru Hanyu was training to master the jump, but when he attempted it at the 2022 Winter Games in Beijing, he fell short of finishing the four-and-a-half revolutions in the air. Mishin's pronouncement, it seemed, had been validated.

Skateboarders call it "pumping," and it's a skill that both Olympic medalists and aspiring thrashers use to build launch speed from what seems like thin air. But what separates the steeziest pro from the sketchiest beginner is the years' worth of practice it takes to develop the know-how to execute the cleanest pump -- or at least that was the case until now. In a paper published Monday in the journal Physical Review Research, scientists have revealed the secret of achieving serious airtime. A skateboarder rides the bowls at Etnies skatepark in Lake Forest. With a bit of coding, researchers were able to describe the optimal technique for pumping -- a tactic where skateboarders crouch down low momentarily and then push their body upright on inclines.

In this letter, we present a novel bi-modal bi-copter robot called Skater, which is adaptable to air and various ground surfaces. Skater consists of a bi-copter moving along its longitudinal direction with two passive wheels on both sides. Using a longitudinally arranged bi-copter as the unified actuation system for both aerial and ground modes, this robot not only keeps a concise and lightweight mechanism but also possesses exceptional terrain traversing capability and strong steering capacity. Moreover, leveraging the vectored thrust characteristic of bi-copters, the Skater can actively generate the centripetal force needed for steering, enabling it to achieve stable movement even on slippery surfaces. Furthermore, we model the comprehensive dynamics of the Skater, analyze its differential flatness, and introduce a controller using nonlinear model predictive control for trajectory tracking. The outstanding performance of the system is verified by extensive real-world experiments and benchmark comparisons.

AI-driven Action Quality Assessment (AQA) of sports videos can mimic Olympic judges to help score performances as a second opinion or for training. However, these AI methods are uninterpretable and do not justify their scores, which is important for algorithmic accountability. Indeed, to account for their decisions, instead of scoring subjectively, sports judges use a consistent set of criteria - rubric - on multiple actions in each performance sequence. Therefore, we propose IRIS to perform Interpretable Rubric-Informed Segmentation on action sequences for AQA. We investigated IRIS for scoring videos of figure skating performance. IRIS predicts (1) action segments, (2) technical element score differences of each segment relative to base scores, (3) multiple program component scores, and (4) the summed final score. In a modeling study, we found that IRIS performs better than non-interpretable, state-of-the-art models. In a formative user study, practicing figure skaters agreed with the rubric-informed explanations, found them useful, and trusted AI judgments more. This work highlights the importance of using judgment rubrics to account for AI decisions.

In 2022, Tony Hawk is a household name, skateboarding is an olympic sport and it's possible to master digital laser flips in any number of video games on TV. Early skate screen media consisted mostly of skeptical documentaries or whimsical California dreaming-style chronicles. Things changed when, in 1983, Stacy Peralta – who managed the ragtag team of skaters that Tony Hawk was a member of – effectively invented the modern skate video. Thanks to its performative nature, skateboarding would soon form a symbiotic relationship with the technology that showcased it. Peralta claims he hoped a few hundred copies of his first video might find their way into the new VHS players that were taking the US by storm.

Regionalization is the act of breaking a dataset into contiguous homogeneous regions that are heterogeneous from each other. Many different algorithms exist for performing regionalization; however, using these algorithms on large real world data sets have only become feasible in terms of compute power in recent years. Very few studies have been done comparing different regionalization methods, and those that do lack analysis in memory, scalability, geographic metrics, and large-scale real-world applications. This study compares state-of-the-art regionalization methods, namely, Agglomerative Clustering, SKATER, REDCAP, AZP, and Max-P-Regions using real world social determinant of health (SDOH) data. The scale of real world SDOH data, up to 1 million data points in this study, not only compares the algorithms over different data sets but provides a stress test for each individual regionalization algorithm, most of which have never been run on such scales previously. We use several new geographic metrics to compare algorithms as well as perform a comparative memory analysis. The prevailing regionalization method is then compared with unconstrained K-Means clustering on their ability to separate real health data in Virginia and Washington DC.

When you drop into every arena in "Rollerdrome," you're faced with waves of enemies perched in various parts of each skate park. The game is all about forward momentum. Once you give Kara a first push of the analog stick you don't have to tell her to keep skating. She'll do it on her own. So, it can get frustrating when certain parts of the maps feel just out of reach.

Interpreting a machine learning model is a difficult task because we need to understand how a model works in the backend, what all parameters the model uses, and how the model is generating the prediction. There are different python libraries that we can use to create machine learning model visualizations and analyze who the model is working. Staker is an open-source python library that enables machine learning model interpretations for different types of black-box models. It helps us create different types of visualization, making it easier to understand how a model is working. In this article, we will explore Skater and what are its different functionalities.

Interpreting a machine learning model is a difficult task because we need to understand how a model works in the backend, what all parameters the model uses, and how the model is generating the prediction. There are different python libraries that we can use to create machine learning model visualizations and analyze who the model is working. Staker is an open-source python library that enables machine learning model interpretations for different types of black-box models. It helps us create different types of visualization, making it easier to understand how a model is working. In this article, we will explore Skater and what are its different functionalities.