On memory systems for companion robots: Implementation methodologies and legal implications

Abstract

Companion robots are becoming increasingly prevalent in a wide variety of domains. The development of realistic long-term human-robot interaction is desirable and this entails the extension of interactions over multiple episodes. Memory systems are thus required in support of this goal. While current memory systems for artificial agents (and companion robots in particular) are currently restricted to symbolic database structures, this is not guaranteed to remain the case, with an increasing number of approaches using sub-symbolic representation schemes. This position paper explores the legal and ethical consequences of this shift of perspective by examining a range of solutions to the problem of data removal from artificial memory systems, specifically in the context of healthcare applications, and concludes that the current legislative provisions for data processing and protection may be inadequate for the next generations of companion robots.