This review presents a comprehensive analysis of AI-based methodologies for exoskeleton-assisted lower-limb rehabilitation. The study reviews 37 peer-reviewed papers, categorizing them based on robotic application scenarios or AI methodologies. It provides a detailed summary of input features, AI model performance, enrolled populations, exoskeletal systems used in validation, and specific tasks for each paper. The review highlights the suitability of different algorithms for specific tasks, aiming to guide future developments and support informed decision-making in lower-limb exoskeleton and AI applications. The review discusses the integration of AI methodologies in exoskeleton-assisted lower-limb rehabilitation, focusing on tasks such as Robot Control (RC), Locomotion Classification (LC), Intention Detection (ID), and Human Joints Trajectory Prediction (HJTP). AI dynamically adapts to the wearer's movements, enhancing responsiveness and personalization. The synergy between AI and exoskeletons improves movement coordination, enabling more efficient and tailored therapeutic interventions. The review also discusses the current state of research, highlighting the use of AI in lower-limb rehabilitation. It presents a detailed analysis of AI approaches, including Reinforcement Learning (RL), Neural Networks (NN), Support Vector Machine (SVM), and Decision Tree (DT). The review evaluates the effectiveness of these methods in various applications, such as gait analysis, motion prediction, and control systems. The study concludes that AI-based methodologies offer significant potential for improving the effectiveness and safety of lower-limb exoskeletons in rehabilitation. The review provides insights into the application of AI in exoskeleton-assisted rehabilitation, emphasizing the importance of selecting appropriate algorithms and considering the specific requirements of each task. The findings suggest that AI can enhance the adaptability and efficiency of control systems while reducing computational burden and energy consumption. The review also highlights the need for further research to explore the full potential of AI in lower-limb rehabilitation.This review presents a comprehensive analysis of AI-based methodologies for exoskeleton-assisted lower-limb rehabilitation. The study reviews 37 peer-reviewed papers, categorizing them based on robotic application scenarios or AI methodologies. It provides a detailed summary of input features, AI model performance, enrolled populations, exoskeletal systems used in validation, and specific tasks for each paper. The review highlights the suitability of different algorithms for specific tasks, aiming to guide future developments and support informed decision-making in lower-limb exoskeleton and AI applications. The review discusses the integration of AI methodologies in exoskeleton-assisted lower-limb rehabilitation, focusing on tasks such as Robot Control (RC), Locomotion Classification (LC), Intention Detection (ID), and Human Joints Trajectory Prediction (HJTP). AI dynamically adapts to the wearer's movements, enhancing responsiveness and personalization. The synergy between AI and exoskeletons improves movement coordination, enabling more efficient and tailored therapeutic interventions. The review also discusses the current state of research, highlighting the use of AI in lower-limb rehabilitation. It presents a detailed analysis of AI approaches, including Reinforcement Learning (RL), Neural Networks (NN), Support Vector Machine (SVM), and Decision Tree (DT). The review evaluates the effectiveness of these methods in various applications, such as gait analysis, motion prediction, and control systems. The study concludes that AI-based methodologies offer significant potential for improving the effectiveness and safety of lower-limb exoskeletons in rehabilitation. The review provides insights into the application of AI in exoskeleton-assisted rehabilitation, emphasizing the importance of selecting appropriate algorithms and considering the specific requirements of each task. The findings suggest that AI can enhance the adaptability and efficiency of control systems while reducing computational burden and energy consumption. The review also highlights the need for further research to explore the full potential of AI in lower-limb rehabilitation.