In curling, quantitative assessment of ice surface conditions during actual play is challenging, and existing sensor-on-stone approaches cannot simultaneously capture ice-contact vibration and athlete-related measurements. We developed a self-contained wearable slider unit embedding two IMUs (LSM6DSV16X), a wideband accelerometer (IIS3DWB), and plantar pressure sensors in a commercially compatible curling slider. Measurements were conducted with two participants under four ice surface conditions (used pebble, no-pebble, extra-fine, and coarse-fine pebble) at an actual curling hall. The root mean square (RMS) amplitude of the DC-subtracted IIS3DWB Z-axis vibration signal distinguished no-pebble from pebbled ice but did not distinguish among the three pebbled conditions. The spectral centroid of the no-pebble condition was also biased toward higher frequencies, although participant-dependent effects remained among pebbled conditions. The slider acquired plantar-pressure variation during delivery, and an exploratory pooled analysis showed a pattern consistent with greater right/left balance variation in trials with greater MOCAP-derived lateral wobble. Because only two participants were tested and the lateral pressure channels reached the calibration limit, participant-specific validation requires a wider measurement range and additional participants. These results support the feasibility of simultaneous ice-contact vibration and plantar-pressure measurement during curling delivery.
Curling is so strategic that it is called ”chess on ice,” and has an element of uncertainty due to the changing conditions on the ice. In this study, we implemented a client development environment in Python for digital curling, which is used to study the strategy of curling. The conventional client development environment was implemented in C++, but Python leads in terms of readability and the richness of the library for machine learning. In addition, with the version change, changes were made to the means of communication and the content of communication in digital curling. Whereas in previous versions, both server and client had to be prepared within a single PC, the new version allows communication between server and client in remote locations. Based on these changes, we implemented a development environment for the client and distributed this development environment on GitHub and PyPI. This is expected to contribute to improving the level of the thinking engine.
1 January 2025 in Transactions of the Society of Instrument and Control Engineers
Curling is a two-player, zero-sum, finite, complete-information, uncertain game in which stones are delivered to a point approximately 37 m (120 ft). Despite its popularity, the dynamics of curling stones are unclear, and significant variations exist in the conditions of curling stones and curling sheets. It is essential to have a highly reproducible delivery apparatus that can perform tests in various environments to clarify stone dynamics and evaluate curling stones and sheets more accurately. In this study, we developed a delivery robot capable of delivering stones as quickly and accurately as, if not better than, a human using a large-diameter pneumatic cylinder. The delivery robot could deliver stones with high repeatability at 2.0 to 4.0 m/s by controlling the velocity of the pneumatic cylinder using multiple solenoid valves. In addition, we verified the accuracy of the robot’s velocity meter using motion capture to ensure that the throwing velocity measured by the delivery robot was sufficiently accurate. Finally, we conducted repeated delivery experiments using the delivery robot and demonstrated that the robot could deliver stones with high repeatability.
1 January 2023 in The Proceedings of the Symposium on sports and human dynamics
In sports and technology, the fusion of artificial intelligence and image processing has introduced innovative avenues to elevate performance and precision in conventional sports. Curling, distinguished for its strategic complexities, revolves around the trajectory and positioning of its uniquely contoured stones. The accurate determination of stone positions assumes a pivotal role in devising strategies and attaining favorable throwing outcomes. This study presents a foundational methodology that aims to position estimation of curling stones around house by mobile robot. The approach seamlessly integrates two key components: image recognition and interpolation, leveraging the Support Vector Machine (SVM) algorithm for stone identification, complemented by sophisticated image interpolation techniques to achieve unparalleled accuracy. We conducted trials of our method using real image data collected from curling field. Leveraging SVM enabled effective stone recognition, followed by the application of image interpolation techniques to precisely estimate stone positions, based on their shapes and relative placements. Experimental results on real data have shown the impressive performance of the proposed method. The combination of SVM and interpolated image processing has greatly improved the ability to estimate the position of the stones in the sport of curling. This method not only yields accurate results, but also opens the door for future optimization and development.