GaitIntent: A Kinematic Dataset Focusing on Steady-State to Transitional Locomotion for Lower-Limb Motion Rehabilitation

Abstract

Motion intent recognition (MIR), the real-time interpretation of user movement, is crucial for advanced motion rehabilitation. MIR enables responsive control of prostheses and exoskeletons, enhancing mobility for lower-limb impaired individuals. Most existing datasets prioritize steady-state locomotion, often overlooking complex transitional movements critical in daily activities, which limits anticipatory control development. We introduce GaitIntent, a novel kinematic dataset. Inspired by gait symmetry, it uses sound limb kinematics for predictive MIR for the affected side—an approach less comprehensively covered. We collected multi-node Inertial Measurement Units (IMUs) data from the thigh, shank, and foot of 11 subjects’ sound limbs performing 13 daily activities, emphasizing eight distinct transitional movements. GaitIntent provides a valuable resource for developing low-latency, robust algorithms for wearable rehabilitation and human-centric control systems.