Background: Robot-assisted gait training is increasingly used in pediatric neurorehabilitation, but its effects on the full time-course of gait kinematics remain insufficiently understood. This study aimed to determine whether intensive gait training with the automated PRODROBOT device could improve frontal- and transverse-plane kinematic profiles in children with neurological disorders and shift them toward the gait pattern of healthy peers. Methods: A prospective single-arm pre–post study was conducted in 10 children with cerebral palsy aged 8–13 years who underwent 20 PRODROBOT training sessions over 4 weeks. A control group comprised 18 healthy age-matched children. Three-dimensional gait analysis was performed before intervention (KF1) and after intervention (KF2). The primary outcome was the similarity of full frontal- and transverse-plane kinematic waveforms of the hip, knee, and ankle/foot relative to pre–post changes and to the healthy reference profiles, assessed using the difference factor (f1) and similarity factor (f2). Results: Only two within-group pre–post comparisons met both similarity criteria: hip rotation KF2 versus KF1 (f1 = 13.9%, f2 = 83.7) and ankle rotation KF2 versus KF1 (f1 = 4.1%, f2 = 67.4). These findings indicate similarity between the pre- and post-intervention profiles within the intervention group, rather than normalization relative to the control group. In comparisons with healthy controls, most variables retained elevated f1 values, indicating persistent quantitative deviation from the reference gait pattern. Conclusions: PRODROBOT-assisted gait training was associated with partial reorganization of selected kinematic waveforms rather than full normalization of gait. The intervention appeared more effective in improving waveform consistency and selected transverse-plane features than in correcting persistent distal and rotational deviations linked to more complex structural or neuromuscular factors.

Background: Gait disturbances are among the most disabling manifestations of cerebral palsy (CP) and substantially affect functional mobility and quality of life. Robot-assisted gait training (RAGT) has been introduced to improve gait performance; however, its effects on lower-limb kinematics remain inconsistent. The aim of this study was to evaluate changes in sagittal-plane gait kinematics in children with CP following a four-week gait rehabilitation program using the PRODROBOT robotic gait trainer. Methods: A prospective quasi-experimental pre–post study with a reference group was conducted. Ten children with spastic cerebral palsy at GMFCS level III aged 8–13 years completed a four-week intervention comprising 20 sessions of robot-assisted gait training. Three-dimensional gait analysis (Vicon) was performed before (KF1) and within 72 h after the end of the intervention (KF2); for each participant, 15 gait cycles were averaged. Eighteen typically developing children aged 7–14 years constituted the normative reference group (CG) and were assessed once. Sagittal plane angular waveforms for the hip, knee, and ankle joints were compared using the difference factor (f₁) and the similarity factor (f₂). Results: The intervention produced selective changes in lower-limb kinematics. At the ankle joint, the range of motion deficit in the sagittal plane relative to the CG decreased from 4.5° to 2.9°, and the difference modulus at 55–60% of the gait cycle decreased from 7.5% to 4.0%. At the knee joint, the difference factor relative to the CG decreased from f₁ = 22.2% to f₁ = 17.4%, with a reduction of the difference modulus by 2–3 percentage points during the loading response phase, terminal stance phase, and terminal swing phase. At the hip joint, the profiles before and after the intervention were respectively f₁ = 2.0% and f₂ = 95.6, and the deviation from the reference pattern remained at the level of f₁ = 54.1% vs. 53.0%; f₂ = 50.2 in both comparisons, with persistent flexion of approximately 10° and a lack of extension in the terminal stance phase. Conclusions: Robot-assisted gait training with the PRODROBOT system produced selective improvements in sagittal-plane gait kinematics in children with cerebral palsy, with the most pronounced effects observed at the ankle joint and, to a lesser extent, the knee. The intervention did not restore a normal gait pattern, particularly at the hip joint. These findings suggest that robotic gait training may serve as a valuable component of comprehensive rehabilitation but should be combined with interventions targeting muscle strength, joint mobility and postural control. Larger randomized studies with long-term follow-up are needed to confirm the clinical effectiveness of this approach.