The present clinical investigation was to ascertain whether the effects of WALKBOT-assisted locomotor training (WLT) on balance, gait, and motor recovery were superior or similar to the conventional locomotor training (CLT) in patients with hemiparetic stroke. Thirty individuals with hemiparetic stroke were randomly assigned to either WLT or CLT. WLT emphasized on a progressive, conventional locomotor retraining practice (40 min) combined with the WALKBOT-assisted, haptic guidance and random variable locomotor training (40 min) whereas CLT involved conventional physical therapy alone (80 min). Both intervention dosages were standardized and provided for 80 min, five days/week for four weeks. Clinical outcomes included function ambulation category (FAC), Berg balance scale (BBS), Korean modified Barthel index (K-MBI), modified Ashworth scale (MAS), and EuroQol-5 dimension (EQ-5D) before and after the four-week program as well as at follow-up four weeks after the intervention. Two-way repeated measure ANOVA showed significant interaction effect (time × group) for FAC (p=0.02), BBS (p=0.03) , and K-MBI (p=0.00) across the pre-training, post-training, and follow-up tests, indicating that WLT was more beneficial for balance, gait and daily activity function than CLT alone. However, no significant difference in other variables was observed. This is the first clinical trial that highlights the superior, augmented effects of the WALKBOT-assisted locomotor training on balance, gait and motor recovery when compared to the conventional locomotor training alone in patients with hemiparetic stroke.