Objective To explore the effect of smart powered hip exoskeleton-assisted gait training on lower limb motor function in stroke patients. Methods Stroke patients hospitalized at the China Rehabilitation Research Center (Beijing Bo’ai Hospital) between December 2023 and March 2025 were enrolled. The patients were randomly assigned to either the exoskeleton group or the conventional gait training group (control group). All patients received conventional rehabilitation therapy, including occupational therapy and physiotherapy. Additionally, the experimental group underwent gait training with a smart hip-powered exoskeleton. The control group received conventional gait training using traditional rehabilitation methods. Functional assessments were conducted before treatment, after 2 weeks and 4 weeks of treatment using the following scales: Fugl-Meyer Assessment Scale for Lower Extremity (FMA-LE), Fugl-Meyer Balance Assessment Scale (FMA-B), Modified Ashworth Scale (MAS), 6-Minute Walk Test, Modified Barthel Index (MBI). Patients in the exoskeleton group underwent subjective satisfaction assessment after 4 weeks of treatment. Results A total of 29 patients were included. Among them, there were 15 cases in the exoskeleton group and 14 cases in the control group. There was no statistically significant difference in gender, age, stroke type, disease duration, and hemiplegic side between the two groups (P>0.05). There was no statistically significant difference in motor function indicators between the two groups before and after treatment (P>0.05). After 4 weeks of treatment, FMA-LE, FMA-B, and MBI scores in both groups were higher than before treatment. (P<0.05). After 2 weeks of treatment, the FMA-LE score in the foreign group showed an improvement (P<0.05), while the control group showed an improvement until 4 weeks later (P<0.05). After 2 weeks of treatment, there was a statistically significant difference in the improvement rate of FMA-LE between the two groups (Z=−2.076, P=0.041). After 4 weeks of treatment, the subjective satisfaction of patients in the exoskeleton group was relatively high, with an average score of (33.07±4.96). Conclusions Smart powered hip exoskeleton-assisted gait training combined with conventional rehabilitation can improve lower limb motor function, balance, activities of daily living, and walking capacity in post-stroke patients. The exoskeleton demonstrated superior efficacy in enhancing lower limb function compared to conventional training. Patients demonstrated high acceptance of the exoskeleton-assisted gait training in terms of safety and comfort.