Abstract
Intention prediction is essential for enabling intuitive and adaptive control in upper-limb exoskeletons, especially in dynamic industrial environments. However, the suitability of different cues, sensors, and computational models for real-world industrial applications remains unclear. This systematic review, conducted according to PRISMA guidelines, analyzes 29 studies published between 2007 and 2024 that investigate intention prediction in active exoskeletons. Most studies rely on motion capture (14) and electromyography (14) to estimate joint torque or trajectories, predicting from 450 ms before to 660 ms after motion onset. Approaches include model-based and model-free regression, as well as classification methods, but vary significantly in complexity, sensor setups, and evaluation procedures. Only a subset evaluates usability or support effectiveness, often under laboratory conditions with small, non-representative participant groups. Based on these insights, we outline recommendations for robust and adaptable intention prediction tailored to industrial task requirements. We propose four generalized support modes to guide sensor selection and control strategies in practical applications. Future research should leverage wearable sensors, integrate cognitive and contextual cues, and adopt transfer learning, federated learning, or LLM-based feedback mechanisms. Additionally, studies should prioritize real-world validation, diverse participant samples, and comprehensive evaluation metrics to support scalable, acceptable deployment of exoskeletons in industrial settings.