In recent years, the field of robotics has undergone significant transformation, driven increasingly by advances in brain-inspired and neurally grounded computational principles. As robots evolve from rigidly programmed machines toward adaptive, cognitive, and autonomous systems, there is growing recognition of the value of algorithms that emulate biological neural and cognitive mechanisms. Approaches such as recurrent neural networks, neural oscillators, and bio-inspired reinforcement learning frameworks offer robots the ability to process information in ways more akin to biological systems, supporting efficient, low-power, and explainable decision-making. These approaches not only enhance real-time sensorimotor integration and adaptive control but also facilitate human-robot interaction through more natural and intuitive behavioral models. By embedding principles from neuroscience and cognitive science into robotic architectures, this research direction aims to bridge the gap between artificial intelligence and biological intelligence, opening new pathways for developing resilient, interactive, and cognitively enriched robotic systems applicable in fields ranging from assistive and medical robotics to cooperative and sociable robots.

The primary objective of this Research Topic is to address the key challenge of enhancing learning and control capabilities in advanced robots to meet the demands of complex and dynamic real-world environments. Current robotic systems often struggle to autonomously adapt to unfamiliar tasks, uncertain conditions, and unstructured settings due to inherent limitations in traditional control and learning paradigms. These constraints hinder robots from achieving the necessary levels of adaptability, efficiency, and reliability required for large-scale deployment in critical domains such as healthcare, manufacturing, and personal assistance.

To bridge this gap, we seek to harness cutting-edge advances in brain-inspired and neurally grounded intelligent algorithms, including recurrent neural networks, bio-inspired reinforcement learning, neural dynamical systems, and other neuro-mechanistic approaches that mirror biological computation. We welcome contributions introducing novel methodologies and architectures integrating such mechanisms to enable more robust, interpretable, and energy-efficient robot learning and control. Topics of interest include the development of new neural-inspired models, improvements in computational and learning efficiency, and co-design of control systems with robotic hardware. We also encourage submissions that demonstrate applications across a wide spectrum of robotic platforms—such as humanoid, industrial, service, and mobile robots, showcasing how neurally grounded and cognitively motivated designs can advance autonomy and interaction in real-world scenarios.

The scope of this Research Topic is to explore the application of brain-inspired and neurally grounded intelligent algorithms in the learning and control of advanced robotic systems. We welcome contributions addressing themes including, but not limited to:

• Brain-inspired and neurally grounded architectures for adaptive control

• Recurrent and oscillatory neural models for perception–action integration

• Bio-inspired Reinforcement Learning for Reward-based Autonomous Decision Making

• Neural Dynamics and attractor-based Models for Continuous Motor Control

• Hybrid neuro-mechanical systems for stable and interpretable behavior

• Neural principles for safe adaptation and resilience in real-world robotics

• Computational models of human–robot interaction grounded in neurocognitive mechanisms

• Cross-disciplinary insights from neuroscience to improve robot cognition and learning efficiency

Are you interested in contributing a manuscript to this Research Topic?

Brain-Inspired and neurally grounded algorithms in learning and control of advanced robots