Challenges on the Application of Automated Planning for Comprehensive Geriatric Assessment Using an Autonomous Social Robot.

Comprehensive Geriatric Assessment is a medical procedure to evaluate the physical, social and psychological status of elder patients. One of its phases consists of performing different tests to the patient or relatives. In this paper we present the challenges to apply Automated Planning to control an autonomous robot helping the clinician to perform such tests. On the one hand the paper focuses on the modelling decisions taken, from an initial approach where each test was encoded using slightly different domains, to the final unified domain allowing any test to be represented. On the other hand, the paper deals with practical issues arisen when executing the plans. Preliminary tests performed with real users show that the proposed approach is able to seamlessly handle the patient-robot interaction in real time, recovering from unexpected events and adapting to the users’ preferred input method, while being able to gather all the information needed by the clinician.