VERAGMIL：结合模仿学习模型的颗粒食品舀取虚拟环境
VERAGMIL: Virtual Environment for Scooping Granular Foods with Imitation Learning Models
浏览论文内容
中文总结 AI 辅助
VERAGMIL框架结合高保真模拟器与VR界面，用于训练BC、BC-RNN、BCQ模型处理颗粒食品舀取任务，实验表明其性能优于3D空间鼠标数据，BCQ表现最佳。
中文摘要 AI 辅助
机器人辅助进食（RAF）系统对协助残障或运动障碍人群完成进食任务至关重要。操控大米、豆类等颗粒食品因具有动态物理特性而面临重大挑战，从人类演示中学习是颇具前景的解决方案，但获取高质量演示的过程较为复杂。为解决这一问题，本文提出VERAGMIL，该框架将高保真模拟器与直观的虚拟现实（VR）界面相结合，用于记录演示并支持不同的模仿学习方法。VERAGMIL为训练RAF系统处理颗粒材料提供了真实环境，包含机器人、传感器以及具有不同物理特性的各类食品。我们通过在颗粒舀取和搬运任务上训练BC、BC-RNN和BCQ三种模仿学习模型来评估VERAGMIL，使用VR界面和3D空间鼠标两种方式采集演示数据，并与人类专家基准进行对比。模型在成功率、洒落量、对未见过食品的泛化能力以及任务完成时间等指标上接受评估。结果显示，基于VR的演示数据的表现显著优于3D空间鼠标数据，其中BCQ模型取得了最佳综合性能，尤其在减少洒落量方面表现突出，且性能接近人类水平。这些发现凸显了本框架在训练处理颗粒材料的RAF系统方面的有效性。本框架的代码可公开获取：this https URL。
英文摘要
Robot-Assisted Feeding (RAF) systems are essential for assisting individuals with disabilities or motor impairments in eating tasks. Manipulating granular food items, such as rice and beans, poses significant challenges due to their dynamic physical properties. Learning from human demonstrations offers a promising solution, but acquiring high-quality demonstrations is complex. To address this, we present VERAGMIL, a framework that combines a high-fidelity simulator with an intuitive Virtual Reality (VR) interface for recording demonstrations and supporting different imitation learning methods. VERAGMIL provides a realistic environment for training RAF systems to handle granular materials, including robots, sensors, and various food items with distinct physical characteristics. We evaluate VERAGMIL by training three imitation learning models, BC, BC-RNN, and BCQ, on granular scooping and transporting tasks using both VR interface and 3D space mouse demonstrations, comparing them with a human-expert baseline. The models are assessed on success rate, spillage, generalization to unseen food items, and task completion time. Results show that VR-based demonstrations significantly outperform 3D space mouse data, with BCQ achieving the best overall performance, particularly in reducing spillage and approaching human performance. These findings underscore the effectiveness of our framework for training RAF systems in granular material handling. The code for our framework is publicly available at: https://github.com/AmanuelErgogo/VERAGMIL.git.
发表机构
- SANO Centre for Computational Personalized Medicine（SANO计算个性化医学中心）
- University of South Florida（南佛罗里达大学）
- University of Verona（维罗纳大学）
机构由 AI 辅助整理，请以论文原文为准。
