Assistance Without Interruption: A Benchmark and LLM-based Framework for Non-Intrusive Human-Robot Assistance

2026-05-02

AI Summary

This study addresses the challenge of enabling robots to proactively and effectively assist humans in multi-step tasks without disrupting their ongoing activities. It formally introduces non-intrusive assistance as a distinct paradigm in human–robot interaction (HRI), emphasizing a human-plan-led joint decision-making framework. The authors propose a hybrid architecture that integrates large language models with scoring models, leveraging semantic retrieval to prune candidate actions and employing a ranker to evaluate the synergy between human and robot action pairs. To support systematic evaluation, they develop NIABench, a simulation benchmark accompanied by tailored metrics. Experimental results demonstrate that the proposed approach significantly reduces human cognitive and physical workload in both simulated and real-world settings while maintaining task efficiency, thereby validating the efficacy and practicality of non-intrusive robotic assistance.

Abstract

Human-robot interaction (HRI) has long studied how agents and people coordinate to achieve shared goals. In this work, we formalize and benchmark the non-intrusive assistance as an independent paradigm of HRI, where a robot proactively supports a human's ongoing multi-step activities while strictly avoiding interruptions. Unlike conventional HRI tasks that rely on direct commands, explicit negotiation, or proactive interventions based on user habits and history, our task treats the human's plan as the primary process and formulates assistance as a joint decision over when to act and what to do. To systematically evaluate this problem, we establish a simulation benchmark, NIABench, along with new metrics tailored to the non-intrusive assistance task. We further propose a hybrid architecture that integrates an LLM with a scoring model. The scoring model first applies semantic retrieval to prune large candidate action sets, and then a ranker evaluates human-step and robot-action pairs, enabling reasoning over timing and cross-step dependencies. Comprehensive experiments on both NIABench and real-world scenarios demonstrate that our method achieves proactive, non-intrusive assistance that reduces human effort while preserving task effectiveness.

Problem

• non-intrusive assistance
• human-robot interaction
• proactive support
• task interruption avoidance
• multi-step activities

Innovation

• non-intrusive assistance
• human-robot interaction
• LLM-based framework
• NIABench
• proactive support