When to Act: Calibrated Confidence for Reliable Human Intention Prediction in Assistive Robotics
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
A Calibrated Reflection Approach for Enhancing Confidence Estimation in LLMs
A critical challenge in deploying Large Language Models (LLMs) is developing reliable mechanisms to estimate their confidence, enabling systems to determine when to trust model outputs versus seek human intervention. We …
Learning Multimodal Confidence for Intention Recognition in Human-Robot Interaction
The rapid development of collaborative robotics has provided a new possibility of helping the elderly who has difficulties in daily life, allowing robots to operate according to specific intentions. However, efficient hu…
Intent DetectionWhen Models Know When They Do Not Know: Calibration, Cascading, and Cleaning
When a model knows when it does not know, many possibilities emerge. The first question is how to enable a model to recognize that it does not know. A promising approach is to use confidence, computed from the model's in…
Calibrated Selective Classification
Selective classification allows models to abstain from making predictions (e.g., say "I don't know") when in doubt in order to obtain better effective accuracy. While typical selective models can be effective at producin…
Classificationimage-classificationImage ClassificationCHiL(L)Grader: Calibrated Human-in-the-Loop Short-Answer Grading
Scaling educational assessment with large language models requires not just accuracy, but the ability to recognize when predictions are trustworthy. Instruction-tuned models tend to be overconfident, and their reliabilit…
Continual Learning