A Deconfounding Framework for Human Behavior Prediction: Enhancing Robotic Systems in Dynamic Environments

TL;DR

This paper introduces a deconfounding framework that improves human behavior prediction accuracy in robotic systems by isolating true causal factors from sensor data, enhancing real-time decision-making in dynamic environments.

Contribution

The paper presents a novel deconfounding approach integrated with time series prediction to address bias caused by hidden confounders in human behavior data.

Findings

Significantly outperforms traditional prediction methods

Enhances reliability of human-robot interaction systems

Improves real-time behavior forecasting accuracy

Abstract

Accurate prediction of human behavior is crucial for effective human-robot interaction (HRI) systems, especially in dynamic environments where real-time decisions are essential. This paper addresses the challenge of forecasting future human behavior using multivariate time series data from wearable sensors, which capture various aspects of human movement. The presence of hidden confounding factors in this data often leads to biased predictions, limiting the reliability of traditional models. To overcome this, we propose a robust predictive model that integrates deconfounding techniques with advanced time series prediction methods, enhancing the model's ability to isolate true causal relationships and improve prediction accuracy. Evaluation on real-world datasets demonstrates that our approach significantly outperforms traditional methods, providing a more reliable foundation for responsive and adaptive HRI systems.