A wearable gait recognition sensor system based on laser-engraved graphene (LIG) is introduced for exoskeleton robots. The system uses pressure sensor arrays fabricated via laser-induced graphene on flexible substrates to detect real-time plantar pressure. The sensor system integrates multiple units into an insole to capture key foot pressure points, and is enhanced with circuit hardware and algorithms for gait recognition. Experimental results show a recognition accuracy of 99.85%, demonstrating the system's effectiveness in exoskeleton robot applications. The system is designed to provide real-time gait information for human-robot interaction, with an intelligent insole that includes LIG/PDMS sensitive units and interdigital LIG electrodes. The insole is flexible and foldable, ensuring comfort during use. It is embedded into the exoskeleton robot's foot to monitor plantar pressure and provide feedback for control. The system uses a machine learning algorithm based on support vector machines (SVM) to improve gait recognition accuracy. The pressure sensors are fabricated using a laser-texturing process that creates hierarchical microstructures, enhancing sensitivity. The system's performance is validated through experiments on an exoskeleton robot, showing high accuracy and stability under various conditions. The sensor system is capable of detecting gait phases such as initial contact, loading response, mid-stance, terminal stance, and swing. The results demonstrate the system's reliability and potential for use in rehabilitation and gait analysis. The system's design includes a flexible pressure sensor with a high sensitivity and long-term stability, making it suitable for real-time gait recognition. The sensor is integrated into the exoskeleton robot, providing feedback for control and assistance. The system's performance is further validated through experiments on different gait frequencies, showing consistent results. The LIG-based gait recognition sensor system is proposed for future applications in rehabilitation and pathologic gait analysis.A wearable gait recognition sensor system based on laser-engraved graphene (LIG) is introduced for exoskeleton robots. The system uses pressure sensor arrays fabricated via laser-induced graphene on flexible substrates to detect real-time plantar pressure. The sensor system integrates multiple units into an insole to capture key foot pressure points, and is enhanced with circuit hardware and algorithms for gait recognition. Experimental results show a recognition accuracy of 99.85%, demonstrating the system's effectiveness in exoskeleton robot applications. The system is designed to provide real-time gait information for human-robot interaction, with an intelligent insole that includes LIG/PDMS sensitive units and interdigital LIG electrodes. The insole is flexible and foldable, ensuring comfort during use. It is embedded into the exoskeleton robot's foot to monitor plantar pressure and provide feedback for control. The system uses a machine learning algorithm based on support vector machines (SVM) to improve gait recognition accuracy. The pressure sensors are fabricated using a laser-texturing process that creates hierarchical microstructures, enhancing sensitivity. The system's performance is validated through experiments on an exoskeleton robot, showing high accuracy and stability under various conditions. The sensor system is capable of detecting gait phases such as initial contact, loading response, mid-stance, terminal stance, and swing. The results demonstrate the system's reliability and potential for use in rehabilitation and gait analysis. The system's design includes a flexible pressure sensor with a high sensitivity and long-term stability, making it suitable for real-time gait recognition. The sensor is integrated into the exoskeleton robot, providing feedback for control and assistance. The system's performance is further validated through experiments on different gait frequencies, showing consistent results. The LIG-based gait recognition sensor system is proposed for future applications in rehabilitation and pathologic gait analysis.