State-of-the-art soft robotic systems for unstructured and real-world environments: A systematic review

Soft robotics has emerged as a transformative paradigm in automation, offering unprecedented compliance, adaptability, and safety for operation in unstructured and dynamic environments. This study systematically reviews the latest advances in soft robotic systems, spanning novel material innovations, intelligent hybrid architectures, and cutting-edge actuation and control strategies. Key developments in integration with artificial intelligence, computer vision, and machine learning are highlighted, enabling enhanced perception, autonomy, and adaptive behavior. Application-driven case studies in healthcare, exploration, and search-and-rescue showcase the evolving capabilities of soft robots in challenging real-world settings. Persistent challenges, such as untethered operation, robust sensorimotor integration, scalable fabrication, and interpretable AI, are discussed alongside emerging multidisciplinary solutions. The review concludes by outlining future research directions, emphasizing the need for unified codesign approaches and collaboration across robotics, materials science, AI, and biology. This synthesis provides a roadmap for advancing next-generation soft robotic systems, aiming to bridge the gap between laboratory innovations and impactful deployment in complex, unpredictable environments, in support of industrial and innovation progress.