Scalable predictive processing framework for multitask caregiving robots

Abstract: The rapid aging of societies is intensifying demand for autonomous care robots; however, most existing systems are task - specific and rely on handcrafted preprocessing, limiting their ability to generalize across diverse scenarios. A prevailing theory in cognitive neuroscience proposes that the human brain operates through hierarchical predictive processing, which underlies flexible cognition and behavior by integrating multimodal sensory signals . Inspired by this principle, we introduce a hierarchical multimodal recurrent neural network grounded in predictive processing under the free - energy principle, capable of directly integrating over 30,000 - dimensional visuo - proprioceptive inputs without dimensionality reduction. The model was able to learn two representative caregiving tasks, rigid - body repositioning and flexible - towel wiping, without task - specific feature engineering. We demonstrate three key proper ties: (i) self - organization of hierarchical latent dynamics that regulate task transitions, capture variability in uncertainty, and infer occluded states; (ii) robustness to degraded vision through visuo - proprioceptive integration; and (iii) asymmetric interference in multitask learning, where the more variable wiping task had little influence on repositioning, whereas learning the repositioning task led to a modest reduction in wiping performance, while the model maintained overall robustness . Although the evaluat ion was limit ed to simulation, these results establish predictive processing as a universal and scalable computational principle, pointing toward robust, flexible, and autonomous care giving robots while offering theoretical insight into the human brain's ability to achieve flexible adaptation in uncertain real - world environments. Main Text: INTRODUCTION As societies worldwide age rapid ly, the growing demand for long - term care is exacerbated by an increasingly severe shortage of professional caregivers ( 1 - 3) . Physically demanding tasks such as patient repositioning or body cleaning are not only labor intensive but also a leading cause of musculoskeletal disorders, particularly lower - back pain, among caregivers ( 4, 5) . To address these challenges, various assistive robotic technologies have been developed ( 6 - 12), ranging from transfer devices and exoskeletons to humanoid systems designed for lifting or repositioning patients. However, most existing systems are either intended to support human operators or are specialized for a single, narrowly defined task, thus limiting their utility across the diverse and unpredictable scenarios encountered in real care settings.