Objective Robot-assisted gait training (RAGT) is often used as a rehabilitation tool for neurological impairments. The purpose of this study is to investigate the effects of rehabilitation with robotic devices on quality of life and depression. Data sources Two electronic databases (MEDLINE and Scopus) were searched for studies from inception up to December 2022. Review methods Randomized controlled trials (RCTs) and non-RCTs were pooled separately for analyses, studying each one’s mental and physical health and depression. Random effect meta-analyses were run using standardized mean difference and 95% confidence interval (CI). Results A total of 853 studies were identified from the literature search. 31 studies (17 RCTs and 14 non-RCTs) including 1151 subjects met the inclusion criteria. 31 studies were selected for the systematic review and 27 studies for the meta-analysis. The outcome measure of mental health significantly improved in favor of the RAGT group in RCTs and non-RCTs (adjusted Hedges’g 0.72, 95% CI: 0.34–1.10, adjusted Hedges g = 0.80, 95% CI 0.21-1.39, respectively). We observed a significant effect of RAGT on physical health in RCTs and non-RCTs (adjusted Hedges’g 0.58, 95% CI 0.28, 0.88, adjusted Hedges g = 0.73, 95% CI 0.12, 1.33). After realizing a sensitivity analysis in RCTs, a positive impact on depression is observed (Hedges’ g of −0.66, 95% CI −1.08 to −0.24). Conclusion This study suggests that RAGT could improve the quality of life of patients with neurological impairments. A positive impact on depression is also observed in the short term. Further studies are needed to differentiate grounded and overgrounded exoskeletons as well as RCT comparing overground exoskeletons with a control group.