HUMAN-INSPIRED ROBOTIC FORGETTING: FILTERING TO IMPROVE ESTIMATION ACCURACY

Abstract

Perfect memory and recall provides a mixed blessing. While flawless recollection of episodic data allows for increased reasoning, photographic memory can hinder a robot’s ability to operate in real-time dynamic environments. Human-inspired forgetting methods may enable robotic systems to rid themselves of out-dated, irrelevant, and erroneous data. This paper presents the ActSimple algorithm and an associated experimental analysis. The Act-Simple algorithm is a novel approach to improving robotic performance by filtering data available to existing algorithms. The experimental analysis tested the effectiveness of five forgetting algorithms in a WiFi signal strength estimation task. The results suggest that forgetting can improve estimation accuracy while reducing the number of sensor readings required. The simplified version of Act-Simple outperformed the other forgetting methods and appears to be a flexible and adaptable means of incorporating human-inspired forgetting into robotic systems.