paper-with-me

홈 › Papers

When to Act: Calibrated Confidence for Reliable Human Intention Prediction in Assistive Robotics

2026-01-08 · Johannes A. Gaus, Winfried Ilg, Daniel Haeufle arxiv

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.

📄 PDF Abstract BibTeX arXiv:2601.04982

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A Calibrated Reflection Approach for Enhancing Confidence Estimation in LLMs

2026-09-03 · Umesh Bodhwani, Yuan Ling, Shujing Dong, Yarong Feng 외 arxiv

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

2024-05-23 · Xiyuan Zhao, Huijun Li, Tianyuan Miao, Xianyi Zhu 외

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 Detection

When Models Know When They Do Not Know: Calibration, Cascading, and Cleaning

2026-01-12 · Chenjie Hao, Weyl Lu, Yuko Ishiwaka, Zengyi Li 외 arxiv

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

2022-08-25 · Adam Fisch, Tommi Jaakkola, Regina Barzilay

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 Classification

CHiL(L)Grader: Calibrated Human-in-the-Loop Short-Answer Grading

2026-03-12 · Pranav Raikote, Korbinian Randl, Ioanna Miliou, Athanasios Lakes 외 arxiv

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