AI-driven Shape Memory Alloys for Robotic Systems

Shape Memory Alloys (SMAs) have emerged as critical components in the field of robotics, offering compact and energy-efficient actuation solutions. Despite their potential, SMAs face challenges including nonlinearities like hysteresis, thermal sensitivity, and material fatigue. In recent years, the integration of Artificial Intelligence (AI)—comprising optimization algorithms, reasoning systems, and machine learning techniques—has shown promise in addressing these complexities. Advances have been made in real-time SMA-driven surgical tools, deployable aerospace structures, and improved fatigue resistance in soft robotics through AI-driven approaches. However, there remains an unmet need to systematically explore and leverage the synergy between AI and SMA technologies fully, in pursuit of scalable and adaptive solutions for innovative robotic systems.



This Research Topic aims to establish comprehensive frameworks for AI-enhanced SMA robotics by confronting several key challenges: optimizing the balance between precision and reliability in SMA actuation, synergizing diverse AI paradigms for co-design and adaptive control, and guaranteeing robust deployment of intelligent systems in extreme or unstructured environments. We seek contributions that deliver innovative theoretical and practical models for depicting nonlinear SMA behaviors, including hysteresis and fatigue, and propose efficacious control strategies using machine learning, fuzzy logic, or hybrid optimization algorithms. Further, we encourage insights into best practices for AI-SMA integration in soft robotics, medical devices, and aerospace structures, along with proposals for standardized benchmarks for performance evaluation and durability.



To gather further insights in the realm of AI-integrated SMAs, we welcome articles addressing, but not limited to, the following themes:

• AI-Optimized Designs: Utilizing genetic algorithms/particle swarm optimization for SMA geometry and control in soft, surgical, and space applications

• Reasoning-Based Control: Fuzzy/MPC systems focusing on precision and hysteresis compensation

• Learning-Driven Dynamics: Utilizing neural networks/reinforcement learning for fatigue prediction and adaptive modeling

• Embedded Intelligence: Developing self-sensing SMA actuators for surgical and aerospace applications

• Sustainable Robotics: Designing energy-harvesting and recyclable SMA-based systems

• Ethical Autonomy: Ensuring safety and transparency in AI-integrated SMA technologies



Manuscript types accepted include Original Research, Reviews, Brief Research Reports, and Perspectives. Please note that submissions focusing solely on empirical SMA studies without AI integration, as well as theoretical AI explorations lacking robotic validation, are not within this scope.

Article types and fees

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Editorial
• FAIR² Data
• Mini Review
• Original Research
• Perspective
• Review

Articles that are accepted for publication by our external editors following rigorous peer review incur a publishing fee charged to Authors, institutions, or funders.

Article types

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Editorial
• FAIR² Data
• Mini Review
• Original Research
• Perspective
• Review

Keywords: Shape memory alloys (SMAs), AI-driven control systems, Soft robotics actuation, Surgical robotics, Optimization algorithms (GA/PSO), Reinforcement learning, Self-sensing actuator, Energy-efficient robotics, Smart material robotics, Hysteresis compensation

Important note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.