用校准置信度判断何时干预，让助老机器人更安全可靠。
When to Act: Calibrated Confidence for Reliable Human Intention Prediction in Assistive Robotics
- 通过事后校准使模型置信度真实反映预测正确率。
- 置信度校准后误判率降低近一个数量级，准确率不变。
- 设定高低置信阈值，高置信才行动，适合安全要求高的场景。
辅助设备需同时判断用户意图及预测可靠性才能提供支持。本文提出基于校准概率的多模态日常活动下一步动作预测安全触发框架。原始模型置信度常无法反映真实正确性，带来安全隐患。事后校准使预测置信度与实际可靠性对齐，将误校准程度降低约一个数量级，且不损失准确性。校准后的置信度驱动简单的ACT/HOLD规则：仅当可靠性高时执行动作，否则保持不动。该机制将置信度阈值转化为可量化的安全参数，实现助人控制回路中可验证的行为。
原文摘要 · Abstract (English)
Assistive devices must determine both what a user intends to do and how reliable that prediction is before providing support. We introduce a safety-critical triggering framework based on calibrated probabilities for multimodal next-action prediction in Activities of Daily Living. Raw model confidence often fails to reflect true correctness, posing a safety risk. Post-hoc calibration aligns predicted confidence with empirical reliability and reduces miscalibration by about an order of magnitude without affecting accuracy. The calibrated confidence drives a simple ACT/HOLD rule that acts only when reliability is high and withholds assistance otherwise. This turns the confidence threshold into a quantitative safety parameter for assisted actions and enables verifiable behavior in an assistive control loop.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。