Shunichi Sekiguchi

Shunichi Sekiguchi

Machine Learning and Robotics Research Engineer

Human-VLM Collaborative Labeling Framework with Consistency-Guided Viewpoint Optimization for Preference-Based Reinforcement Learning

Published in IEEE Access, 2026

IEEE Access Project Page Code
Illustration for Human-VLM Collaborative Labeling Framework with Consistency-Guided Viewpoint Optimization for Preference-Based Reinforcement Learning

We developed a human-VLM collaborative framework for preference labeling in reinforcement learning. It uses label consistency to estimate VLM reliability and Bayesian optimization to select camera viewpoints, improving annotation quality while reducing the need for human feedback.