A three-layer planning architecture for the autonomous control of rehabilitation therapies based on social robots

This manuscript focuses on the description of a novel cognitive architecture called NAOTherapist, which provides a social robot with enough autonomy to carry out a non-contact upper limb rehabilitation therapy for patients with physical impairments, such as cerebral palsy and obstetric brachial plexus palsy. NAOTherapist comprises three levels of Automated Planning. In the high-level planning, the physician establishes the parameters of the therapy such as the scheduling of the sessions, the therapeutic objectives to be achieved and certain constraints based on the medical records of the patient. This information is used to establish a customized therapy plan. The objective of the medium-level planning is to execute and monitor every previous planned session with the humanoid robot. Finally, the low-level planning involves the execution of path-planning actions by the robot to carry out different low-level instructions such as performing poses. The technical evaluation shows an accurate definition and monitoring of the therapies and sessions and a fluent interaction with the robot. This automated process is expected to save time for the professionals while guaranteeing the medical criteria.