Learning Long Short-Term Intention within Human Daily Behaviors

2025-04-10

AI Summary

Household service robots often fail to handle human behavioral errors, posing safety and operational challenges. Method: This paper introduces the novel task of “Long-Short-Term Intention Prediction,” which jointly models value-driven long-term intentions and action-driven short-term intentions, and detects inconsistencies between them to trigger timely warnings and interventions. We first construct the first annotated dataset supporting this task. Then, we propose an interpretable two-stage framework: (i) a hybrid joint intention prediction model integrating finite-state machines with neural networks, and (ii) a consistency diagnosis module based on behavioral sequence alignment. Contribution/Results: Experiments demonstrate significant improvements—+12.3% in long-term intention prediction accuracy and +18.7% in inconsistency detection F1-score. Real-world home deployments validate the framework’s effectiveness in supporting safe, adaptive decision-making and proactive intervention.

Technology Category

• Intelligent Robots: Human-Robot Interaction
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Natural Language Processing: Safety and Robustness

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

In the domain of autonomous household robots, it is of utmost importance for robots to understand human behaviors and provide appropriate services. This requires the robots to possess the capability to analyze complex human behaviors and predict the true intentions of humans. Traditionally, humans are perceived as flawless, with their decisions acting as the standards that robots should strive to align with. However, this raises a pertinent question: What if humans make mistakes? In this research, we present a unique task, termed"long short-term intention prediction". This task requires robots can predict the long-term intention of humans, which aligns with human values, and the short term intention of humans, which reflects the immediate action intention. Meanwhile, the robots need to detect the potential non-consistency between the short-term and long-term intentions, and provide necessary warnings and suggestions. To facilitate this task, we propose a long short-term intention model to represent the complex intention states, and build a dataset to train this intention model. Then we propose a two-stage method to integrate the intention model for robots: i) predicting human intentions of both value-based long-term intentions and action-based short-term intentions; and 2) analyzing the consistency between the long-term and short-term intentions. Experimental results indicate that the proposed long short-term intention model can assist robots in comprehending human behavioral patterns over both long-term and short-term durations, which helps determine the consistency between long-term and short-term intentions of humans.

Problem

• Predicting human long-term and short-term intentions accurately
• Detecting inconsistencies between short-term and long-term intentions
• Providing warnings and suggestions based on intention analysis

Innovation

• Predicts long-term and short-term human intentions
• Detects inconsistencies between short and long-term intentions
• Uses a two-stage method for intention analysis