Abstract Background Parkinson’s disease is one of the most frequent causes of disability among the older adults. It is a chronic-progressive neuro-degenerative disease, characterized by several motor disorders. Balance disorders are a symptom that involves the body axis and do not respond to dopaminergic therapy used in Parkinson’s disease. Therefore, physiotherapy becomes an important intervention for the management of motor disorders. Originally, these rehabilitative approaches were based on empirical experiences, but several scientific evidences suggests that neuronal plasticity is exercise-dependent. In this context, robotic rehabilitation plays an important role because it allows to perform task-oriented exercises and to increase the number of repetitions and their intensity. This protocol study aims to evaluate the effectiveness of robotic-based intervention of the older adults with Parkinson’s disease, designed to improve the gait and to reduce the risk of falling. Methods This study is a single-blinded randomized controlled trial. The primary outcomes are: risk of falling, gait performance and fear of falling measured through Performance-Oriented Mobility Assessment (POMA), instrumental gait analysis and Short Falls Efficacy Scale – International (FES-I), respectively. One hundred ninety-five patients with PD will be recruited and randomly divided into three groups, to receive a traditional rehabilitation program or a robotic rehabilitation using Tymo system or Walker View in addition to the traditional therapy. Assessments will be performed at baseline, at the end of treatment and 6 months, 1 year and 2 years from the end of the treatment. A 10-treatment session will be conducted, divided into 2 training sessions per week, for 5 weeks. The control group will perform traditional therapy sessions lasting 50 min. The technological intervention group will carry out 30 min of traditional therapy and 20 min of treatment with a robotic system. Discussion The final goals of the present study are to propose a new approach in the PD rehabilitation, focused on the use of robotic device, and to check the results not only at the end of the treatment but also in the long term. Trial registration NCT04087031, registration date September 12, 2019.