augKlimb: Interactive Data-Led Augmentation of Bouldering Training

• URL: http://arxiv.org/abs/2001.07944v1
• Date: Wed, 22 Jan 2020 10:26:59 GMT
• Title: augKlimb: Interactive Data-Led Augmentation of Bouldering Training
• Authors: Luke Storry
• Abstract summary: Climbing is a popular sport, especially indoors, where climbers can train on man-made routes using artificial holds. Various aspects of adding computer-interaction to climbing have been studied in recent years. There is a large space for research into lightweight tools to aid recreational intermediate climbers.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Climbing is a popular and growing sport, especially indoors, where climbers can train on man-made routes using artificial holds. Both strength and good technique is required to successfully reach the top of a climb, and often coaches work to improve technique so less strength is required, enabling a climber to ascent more difficult climbs. Various aspects of adding computer-interaction to climbing have been studied in recent years, but there is a large space for research into lightweight tools to aid recreational intermediate climbers, both with trickier climbs and to improve their own technique. In this CS Masters final project, I explored which form of data-capture and output-features could improve a climber's training, and analysed how climbers responded to viewing their data throughout a climbing session, then conducted a user-centred design to build a lightweight mobile application for intermediate climbers. A variety of hardware and software solutions were explored, tested and developed through series of surveys, discussions, wizard-of-oz studies and prototyping, resulting in a system that most closely meets the needs of local indoor boulderers given the project's time scope. This consists of an iteratively developed interactive mobile app that: can record, graph, and score the acceleration of a climber, as both a training tool and gamification incentive for good technique; can link a video recording to the acceleration graph, to enable frame-by-frame inspection of weaknesses; is fully approved and distributed on the Google play Store and currently being regularly used by 15 local climbers. Then I conducted a final usability study, comprising a thematic analysis of forty minutes's worth of interview transcripts, to gain a deep understanding of the app's impact on the climbers using it, along with its benefits and limitations.

Related papers

• Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion [62.3543999991324]
  Autoregressive (AR) video diffusion models have achieved remarkable performance.<n>Due to their limited training durations, a train-test gap emerges when testing at longer horizons, leading to rapid visual degradations.<n>Rolling Sink scales the AR video synthesis to ultra-long durations at test time, with consistent subjects, stable colors, coherent structures, and smooth motions.
  arXiv  Detail & Related papers  (2026-02-08T02:16:02Z)
• Training and Simulation of Quadrupedal Robot in Adaptive Stair Climbing for Indoor Firefighting: An End-to-End Reinforcement Learning Approach [4.901516178319544]
  Quadruped robots are used for primary searches during the early stages of indoor fires.<n> situational awareness in complex indoor environments and rapid stair climbing across different staircases remain the main challenges.<n>This project explores how to balance navigation and locomotion and how end-to-end RL methods can enable quadrupeds to adapt to different stair shapes.
  arXiv  Detail & Related papers  (2026-02-03T04:23:50Z)
• The Way Up: A Dataset for Hold Usage Detection in Sport Climbing [1.3812010983144802]
  We introduce a dataset of 22 annotated climbing videos, providing ground-truth labels for hold locations, usage order, and time of use.<n>We also explore the application of keypoint-based 2D pose-estimation models for detecting hold usage in sport climbing.
  arXiv  Detail & Related papers  (2025-05-19T08:41:18Z)
• ClimbingCap: Multi-Modal Dataset and Method for Rock Climbing in World Coordinate [41.90481583757255]
  Human Motion Recovery (HMR) research mainly focuses on ground-based motions such as running. To address the insufficiency of climbing motion datasets, we collect AscendMotion, a large-scale well-annotated, and challenging climbing motion dataset. We propose ClimbingCap, a motion recovery method that reconstructs continuous 3D human climbing motion in a global coordinate system.
  arXiv  Detail & Related papers  (2025-03-27T08:49:33Z)
• Open-World Drone Active Tracking with Goal-Centered Rewards [62.21394499788672]
  Drone Visual Active Tracking aims to autonomously follow a target object by controlling the motion system based on visual observations.<n>We propose DAT, the first open-world drone active air-to-ground tracking benchmark.<n>We also propose GC-VAT, which aims to improve the performance of drone tracking targets in complex scenarios.
  arXiv  Detail & Related papers  (2024-12-01T09:37:46Z)
• Raising the Bar(ometer): Identifying a User's Stair and Lift Usage Through Wearable Sensor Data Analysis [4.453838343573515]
  This research describes a new exploratory dataset, to examine the patterns and behaviors related to using stairs and lifts. We collected data from 20 participants while climbing and descending stairs and taking a lift in a variety of scenarios. Our method is highly accurate at classifying stair and lift operations with an accuracy of 87.61% and a multi-class weighted F1-score of 87.56% over 8-second time windows.
  arXiv  Detail & Related papers  (2024-09-18T06:26:50Z)
• Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations [62.132347451049455]
  Scale has become a main ingredient in obtaining strong machine learning models. In this work, we argue that scale and training research has been needlessly complex due to reliance on the cosine schedule. We show that weight averaging yields improved performance along the training trajectory, without additional training costs, across different scales.
  arXiv  Detail & Related papers  (2024-05-28T17:33:54Z)
• Board-to-Board: Evaluating Moonboard Grade Prediction Generalization [0.0]
  Bouldering is a sport where athletes aim to climb up an obstacle using a set of defined holds called a route. The variation in individual climbers technical and physical attributes and many nuances of an individual route make grading a difficult and often biased task. We apply classical and deep-learning modelling techniques to the 2016, 2017 and 2019 Moonboard datasets.
  arXiv  Detail & Related papers  (2023-11-21T08:16:01Z)
• Barkour: Benchmarking Animal-level Agility with Quadruped Robots [70.97471756305463]
  We introduce the Barkour benchmark, an obstacle course to quantify agility for legged robots. Inspired by dog agility competitions, it consists of diverse obstacles and a time based scoring mechanism. We present two methods for tackling the benchmark.
  arXiv  Detail & Related papers  (2023-05-24T02:49:43Z)
• Surgical tool classification and localization: results and methods from the MICCAI 2022 SurgToolLoc challenge [69.91670788430162]
  We present the results of the SurgLoc 2022 challenge. The goal was to leverage tool presence data as weak labels for machine learning models trained to detect tools. We conclude by discussing these results in the broader context of machine learning and surgical data science.
  arXiv  Detail & Related papers  (2023-05-11T21:44:39Z)
• Learning and Adapting Agile Locomotion Skills by Transferring Experience [71.8926510772552]
  We propose a framework for training complex robotic skills by transferring experience from existing controllers to jumpstart learning new tasks. We show that our method enables learning complex agile jumping behaviors, navigating to goal locations while walking on hind legs, and adapting to new environments.
  arXiv  Detail & Related papers  (2023-04-19T17:37:54Z)
• Robust and Versatile Bipedal Jumping Control through Reinforcement Learning [141.56016556936865]
  This work aims to push the limits of agility for bipedal robots by enabling a torque-controlled bipedal robot to perform robust and versatile dynamic jumps in the real world. We present a reinforcement learning framework for training a robot to accomplish a large variety of jumping tasks, such as jumping to different locations and directions. We develop a new policy structure that encodes the robot's long-term input/output (I/O) history while also providing direct access to a short-term I/O history.
  arXiv  Detail & Related papers  (2023-02-19T01:06:09Z)
• Lowering Detection in Sport Climbing Based on Orientation of the Sensor Enhanced Quickdraw [3.9504711818127425]
  A prototype is developed to collect data using accelerometer sensors attached to a piece of climbing equipment mounted on the wall. The corresponding sensors are configured to be energy-efficient, hence become practical in terms of expenses and time consumption for replacement. This paper describes hardware specifications, studies data measured by the sensors in ultra-low power mode, detect sensors' orientation patterns during lowering different routes, and develop an supervised approach to identify lowering.
  arXiv  Detail & Related papers  (2023-01-17T15:06:33Z)
• Climbing Routes Clustering Using Energy-Efficient Accelerometers Attached to the Quickdraws [7.47577255773279]
  A prototype is developed to collect data using accelerometer sensors attached to a piece of climbing equipment mounted on the wall. The corresponding sensors are configured to be energy-efficient, hence becoming practical in terms of expenses and time consumption for replacement. This paper describes hardware specifications, studies data measured by the sensors in ultra-low power mode, detect patterns in data during climbing different routes, and develops an unsupervised approach for route clustering.
  arXiv  Detail & Related papers  (2022-11-04T19:08:01Z)
• Learning Perceptual Locomotion on Uneven Terrains using Sparse Visual Observations [75.60524561611008]
  This work aims to exploit the use of sparse visual observations to achieve perceptual locomotion over a range of commonly seen bumps, ramps, and stairs in human-centred environments. We first formulate the selection of minimal visual input that can represent the uneven surfaces of interest, and propose a learning framework that integrates such exteroceptive and proprioceptive data. We validate the learned policy in tasks that require omnidirectional walking over flat ground and forward locomotion over terrains with obstacles, showing a high success rate.
  arXiv  Detail & Related papers  (2021-09-28T20:25:10Z)
• Embedding and generation of indoor climbing routes with variational autoencoder [0.0]
  We employ a variational autoencoder to climbing routes in a standardized training apparatus MoonBoard. 22 generated problems are uploaded to the Moonboard app for user review.
  arXiv  Detail & Related papers  (2020-09-16T23:23:04Z)
• Visual Imitation Made Easy [102.36509665008732]
  We present an alternate interface for imitation that simplifies the data collection process while allowing for easy transfer to robots. We use commercially available reacher-grabber assistive tools both as a data collection device and as the robot's end-effector. We experimentally evaluate on two challenging tasks: non-prehensile pushing and prehensile stacking, with 1000 diverse demonstrations for each task.
  arXiv  Detail & Related papers  (2020-08-11T17:58:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.