Unsupervised Online Learning for Robotic Interestingness with Visual Memory
This addresses the need for fast deployment in robotic exploration and cooperation scenarios, though it is incremental as it builds on prior work by adding online adaptation.
The paper tackles the problem of enabling autonomous robots to detect interesting scenes quickly with little training data by proposing an online learning method that adapts to the environment, achieving 20% higher accuracy than state-of-the-art unsupervised methods in subterranean tunnels and comparable performance to supervised methods.
Autonomous robots frequently need to detect "interesting" scenes to decide on further exploration, or to decide which data to share for cooperation. These scenarios often require fast deployment with little or no training data. Prior work considers "interestingness" based on data from the same distribution. Instead, we propose to develop a method that automatically adapts online to the environment to report interesting scenes quickly. To address this problem, we develop a novel translation-invariant visual memory and design a three-stage architecture for long-term, short-term, and online learning, which enables the system to learn human-like experience, environmental knowledge, and online adaption, respectively. With this system, we achieve an average of 20% higher accuracy than the state-of-the-art unsupervised methods in a subterranean tunnel environment. We show comparable performance to supervised methods for robot exploration scenarios showing the efficacy of our approach. We expect that the presented method will play an important role in the robotic interestingness recognition exploration tasks.