People with Parkinson's (PwP) experience gait impairment that can significantly reduce their quality of life. External feedback such as visual, auditory, and tactile cues can be used to improve the mobility of PwP. However, current cueing strategies are limited as the same cue is provided regardless of the person’s condition or medication state. This thesis proposes an adaptive cue-provision framework that can provide personalized assistance based on the individual’s real-time response. The framework is validated with healthy adults, older adults, and PwP. The results show that the adaptive framework can improve gait performance in all three groups of participants.