虚拟现实中用户抓取意图的预测
Predicting User Grasp Intentions in Virtual Reality
AI总结：
本文研究VR中用户抓取意图预测，通过810次试验对比分类与回归方法，发现基于LSTM的回归模型在时间与距离误差上表现更稳健，为自适应触觉反馈和实时动作预测奠定基础。
摘要：
在虚拟现实（VR）中预测用户意图对于创造沉浸式体验至关重要，尤其是在涉及复杂抓取动作的任务中，准确的触觉反馈必不可少。在本工作中，我们利用手部运动的时间序列数据，在810次试验中评估了分类和回归两种方法，试验涵盖了不同的物体类型、尺寸和操作方式。我们的研究结果表明，分类模型难以跨用户泛化，导致性能不稳定。相比之下，基于回归的方法，特别是使用长短期记忆（LSTM）网络的方法，表现出更稳健的性能，在抓取前关键的两秒窗口内，时间误差在0.25秒以内，距离误差约为5-20厘米。尽管有这些改进，预测精确的手部姿态仍然具有挑战性。通过对用户差异性和模型可解释性的全面分析，我们探讨了某些模型失败的原因，以及回归模型如何更好地适应VR中用户行为的动态和复杂特性。我们的结果强调了机器学习模型在增强VR交互方面的潜力，特别是通过自适应触觉反馈，并为未来在VR中实时预测用户动作的进展奠定了基础。
英文摘要：
Predicting user intentions in virtual reality (VR) is crucial for creating immersive experiences, particularly in tasks involving complex grasping motions where accurate haptic feedback is essential. In this work, we leverage time-series data from hand movements to evaluate both classification and regression approaches across 810 trials with varied object types, sizes, and manipulations. Our findings reveal that classification models struggle to generalize across users, leading to inconsistent performance. In contrast, regression-based approaches, particularly those using Long Short Term Memory (LSTM) networks, demonstrate more robust performance, with timing errors within 0.25 seconds and distance errors around 5-20 cm in the critical two-second window before a grasp. Despite these improvements, predicting precise hand postures remains challenging. Through a comprehensive analysis of user variability and model interpretability, we explore why certain models fail and how regression models better accommodate the dynamic and complex nature of user behavior in VR. Our results underscore the potential of machine learning models to enhance VR interactions, particularly through adaptive haptic feedback, and lay the groundwork for future advancements in real-time prediction of user actions in VR.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
