Laser2Vec: Similarity-based Retrieval for Robotic Perception Data
This addresses the need for tools to discover systemic failures in robotic systems, though it is incremental as it builds on existing methods like VAEs for a specific domain.
The paper tackles the problem of analyzing large volumes of robotic perception data by developing a system for similarity-based retrieval of 2D LiDAR scans, using compressed representations and efficient query evaluation to accurately identify similar scans across deployments.
As mobile robot capabilities improve and deployment times increase, tools to analyze the growing volume of data are becoming necessary. Current state-of-the-art logging, playback, and exploration systems are insufficient for practitioners seeking to discover systemic points of failure in robotic systems. This paper presents a suite of algorithms for similarity-based queries of robotic perception data and implements a system for storing 2D LiDAR data from many deployments cheaply and evaluating top-k queries for complete or partial scans efficiently. We generate compressed representations of laser scans via a convolutional variational autoencoder and store them in a database, where a light-weight dense network for distance function approximation is run at query time. Our query evaluator leverages the local continuity of the embedding space to generate evaluation orders that, in expectation, dominate full linear scans of the database. The accuracy, robustness, scalability, and efficiency of our system is tested on real-world data gathered from dozens of deployments and synthetic data generated by corrupting real data. We find our system accurately and efficiently identifies similar scans across a number of episodes where the robot encountered the same location, or similar indoor structures or objects.