Learning Multimodal Confidence for Intention Recognition in Human-Robot Interaction

TL;DR

This paper introduces a novel multimodal fusion framework, BMCLOP, that enhances intention recognition accuracy and reliability in human-robot interaction by combining Bayesian fusion with confidence learning, validated on a robot with multiple modalities.

Contribution

The paper proposes a new learning-based multimodal fusion framework, BMCLOP, that improves intention recognition accuracy and uncertainty reduction in human-robot collaboration.

Findings

BMCLOP outperforms baseline methods in intention recognition accuracy.

The framework effectively reduces uncertainty in multimodal intention recognition.

Validated on a six-DoF robot with gestures, speech, and gaze modalities.

Abstract

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 human-robot cooperation requires natural, accurate and reliable intention recognition in shared environments. The current paramount challenge for this is reducing the uncertainty of multimodal fused intention to be recognized and reasoning adaptively a more reliable result despite current interactive condition. In this work we propose a novel learning-based multimodal fusion framework Batch Multimodal Confidence Learning for Opinion Pool (BMCLOP). Our approach combines Bayesian multimodal fusion method and batch confidence learning algorithm to improve accuracy, uncertainty reduction and success rate given the interactive condition. In particular, the generic and practical multimodal intention recognition framework can be easily extended further. Our desired assistive scenarios consider three modalities gestures, speech and gaze, all of which produce categorical distributions over all the finite intentions. The proposed method is validated with a six-DoF robot through extensive experiments and exhibits high performance compared to baselines.