Feasibility of Embodied Dynamics Based Bayesian Learning for Continuous Pursuit Motion Control of Assistive Mobile Robots in the Built Environment

2025-11-21

AI Summary

Current non-invasive EEG-based brain–computer interfaces (BCIs) are largely confined to discrete command execution, limiting their applicability for real-time, continuous speed and directional control of mobile robots—such as wheelchairs—in complex indoor environments (e.g., hospitals, transit hubs). Method: We propose an embodied-dynamics-inspired Bayesian inference framework that directly decodes acceleration-level motor representations from motor imagery, enabling continuous trajectory tracking. Our approach integrates non-invasive EEG acquisition, automatic relevance determination for feature selection, continuous online learning, and session-wise cumulative transfer learning. Contribution/Results: Evaluated on a public dataset, our method reduces normalized mean squared error by 72% compared to autoregressive models and EEGNet. It significantly improves control accuracy, stability, and naturalness of interaction, thereby overcoming the fundamental limitations of conventional discrete-control paradigms in non-invasive EEG-BCI systems.

Technology Category

• Intelligent Robots: Behavior Learning & Control
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Bayesian Learning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Non-invasive electroencephalography (EEG)-based brain-computer interfaces (BCIs) offer an intuitive means for individuals with severe motor impairments to independently operate assistive robotic wheelchairs and navigate built environments. Despite considerable progress in BCI research, most current motion control systems are limited to discrete commands, rather than supporting continuous pursuit, where users can freely adjust speed and direction in real time. Such natural mobility control is, however, essential for wheelchair users to navigate complex public spaces, such as transit stations, airports, hospitals, and indoor corridors, to interact socially with the dynamic populations with agility, and to move flexibly and comfortably as autonomous driving is refined to allow movement at will. In this study, we address the gap of continuous pursuit motion control in BCIs by proposing and validating a brain-inspired Bayesian inference framework, where embodied dynamics in acceleration-based motor representations are decoded. This approach contrasts with conventional kinematics-level decoding and deep learning-based methods. Using a public dataset with sixteen hours of EEG from four subjects performing motor imagery-based target-following, we demonstrate that our method, utilizing Automatic Relevance Determination for feature selection and continual online learning, reduces the normalized mean squared error between predicted and true velocities by 72% compared to autoregressive and EEGNet-based methods in a session-accumulative transfer learning setting. Theoretically, these findings empirically support embodied cognition theory and reveal the brain's intrinsic motor control dynamics in an embodied and predictive nature. Practically, grounding EEG decoding in the same dynamical principles that govern biological motion offers a promising path toward more stable and intuitive BCI control.

Problem

• Developing continuous motion control for brain-computer interface robotic wheelchairs
• Enabling real-time speed and direction adjustment for motor-impaired users
• Improving BCI control stability through embodied dynamics Bayesian learning

Innovation

• Embodied dynamics Bayesian learning for continuous motion control
• Automatic Relevance Determination for EEG feature selection
• Continual online learning in session-accumulative transfer setting