MIN-Fakultät
Fachbereich Informatik
TAMS

EPIROME - Episodic Robot Memory

Description

The EPIROME framework is an independent framework to investigate high-level episodic memory capabilities. It is developed to provide a biological inspired memory module to our service robot TASER.

Different disciplines such as psychology and neuroscience have been examining episodic memory (also referred to as declarative memory) for more than three decades. Now, engineering and computer science are developing an increasing interest in episodic memory for artificial systems. Me and my co-authors propose a novel framework EPIROME to develop and investigate high-level episodic memory mechanisms which can be used to model and compare episodic memories of high-level events for technical systems. We demonstrated how we applied the framework to the domain of service robotics.

High-level events emanate from basic skills, elementary operations, sequences of elementary operations, environmental changes and the detection of human interactions. The framework enables the service robot TASER to collect autobiographical memories to improve action planning based on past experiences. The framework provides the robot with a life-long memory since past experiences can be stored and reloaded. In practise, one main advantage of our episodic memory is that it provides one-shot learning capabilities to the robot. This reduces the disadvantage of other learning strategies where learning takes too long when used with a real robot system in natural environments and therefore is not feasible.

For further description about the EPIROME framework please read the articles mentioned below. The EPIROME cognitive robot framework is under development by Sascha Jockel

Images

Screenshot of running EPIROME application

Further Informations