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.

The predictive brain hypothesis suggests that perception can be interpreted as the process of minimizing the error between predicted perception tokens generated by an internal world model and actual sensory input tokens. When implementing working examples of this hypothesis in the context of in-air sonar, significant difficulties arise due to the sparse nature of the reflection model that governs ultrasonic sensing. Despite these challenges, creating consistent world models using sonar data is crucial for implementing predictive processing of ultrasound data in robotics. In an effort to enable robust robot behavior using ultrasound as the sole exteroceptive sensor modality, this paper introduces EchoPT, a pretrained transformer architecture designed to predict 2D sonar images from previous sensory data and robot ego-motion information. We detail the transformer architecture that drives EchoPT and compare the performance of our model to several state-of-the-art techniques. In addition to presenting and evaluating our EchoPT model, we demonstrate the effectiveness of this predictive perception approach in two robotic tasks.

Advances in reinforcement learning (RL) often rely on massive compute resources and remain notoriously sample inefficient. In contrast, the human brain is able to efficiently learn effective control strategies using limited resources. This raises the question whether insights from neuroscience can be used to improve current RL methods. Predictive processing is a popular theoretical framework which maintains that the human brain is actively seeking to minimize surprise. We show that recurrent neural networks which predict their own sensory states can be leveraged to minimise surprise, yielding substantial gains in cumulative reward. Specifically, we present the Predictive Processing Proximal Policy Optimization (P4O) agent; an actor-critic reinforcement learning agent that applies predictive processing to a recurrent variant of the PPO algorithm by integrating a world model in its hidden state. P4O significantly outperforms a baseline recurrent variant of the PPO algorithm on multiple Atari games using a single GPU. It also outperforms other state-of-the-art agents given the same wall-clock time and exceeds human gamer performance on multiple games including Seaquest, which is a particularly challenging environment in the Atari domain. Altogether, our work underscores how insights from the field of neuroscience may support the development of more capable and efficient artificial agents.

Knowing the position of the robot in the world is crucial for navigation. Nowadays, Bayesian filters, such as Kalman and particle-based, are standard approaches in mobile robotics. Recently, end-to-end learning has allowed for scaling-up to high-dimensional inputs and improved generalization. However, there are still limitations to providing reliable laser navigation. Here we show a proof-of-concept of the predictive processing-inspired approach to perception applied for localization and navigation using laser sensors, without the need for odometry. We learn the generative model of the laser through self-supervised learning and perform both online state-estimation and navigation through stochastic gradient descent on the variational free-energy bound. We evaluated the algorithm on a mobile robot (TIAGo Base) with a laser sensor (SICK) in Gazebo. Results showed improved state-estimation performance when comparing to a state-of-the-art particle filter in the absence of odometry. Furthermore, conversely to standard Bayesian estimation approaches our method also enables the robot to navigate when providing the desired goal by inferring the actions that minimize the prediction error.

Everything became imbued with a sense of vitality and life and vividness. If I picked up a pebble from the beach, it would move. It would glisten and gleam and sparkle and be absolutely captivating," says neuroscientist Anil Seth. "Somebody looking at me would see me staring at a stone for hours." Or what seemed like hours to Seth. A researcher at the United Kingdom's University of Sussex, he studies how the brain helps us perceive the world within and without, and is intrigued by what psychedelics such as LSD can tell us about how the brain creates these perceptions. So, a few years ago, he decided to try some, in controlled doses and with trusted people by his side. He had a notebook to keep track of his experiences. "I didn't write very much in the notebook," he says, laughing. Instead, while on LSD, he reveled in a sense of well-being and marveled at the "fluidity of time and space." He found himself staring at clouds and seeing them change into faces of people he was thinking of.