PathSpace: Rapid continuous map approximation for efficient SLAM using B-Splines in constrained environments
This work addresses efficiency and resource constraints in semantic SLAM for autonomous vehicles, particularly in constrained environments like racing, but it is incremental as it builds on existing SLAM techniques with a novel representation.
The paper tackles the problem of dense geometric representations limiting semantic SLAM by proposing PathSpace, a framework using B-splines for compact continuous map approximation, which in autonomous racing tests achieved significantly reduced representations with comparable accuracy to traditional methods.
Simultaneous Localization and Mapping (SLAM) plays a crucial role in enabling autonomous vehicles to navigate previously unknown environments. Semantic SLAM mostly extends visual SLAM, leveraging the higher density information available to reason about the environment in a more human-like manner. This allows for better decision making by exploiting prior structural knowledge of the environment, usually in the form of labels. Current semantic SLAM techniques still mostly rely on a dense geometric representation of the environment, limiting their ability to apply constraints based on context. We propose PathSpace, a novel semantic SLAM framework that uses continuous B-splines to represent the environment in a compact manner, while also maintaining and reasoning through the continuous probability density functions required for probabilistic reasoning. This system applies the multiple strengths of B-splines in the context of SLAM to interpolate and fit otherwise discrete sparse environments. We test this framework in the context of autonomous racing, where we exploit pre-specified track characteristics to produce significantly reduced representations at comparable levels of accuracy to traditional landmark based methods and demonstrate its potential in limiting the resources used by a system with minimal accuracy loss.