Navigating the Landscape for Real-time Localisation and Mapping for Robotics and Virtual and Augmented Reality

TL;DR

This paper presents a comprehensive suite of tools, methodologies, and systems for evaluating, optimizing, and deploying real-time SLAM algorithms across diverse hardware architectures for robotics and AR/VR applications.

Contribution

It introduces systematic evaluation tools, machine-learning-guided exploration, and end-to-end simulation methods for optimizing SLAM algorithms and hardware configurations.

Findings

Development of quantitative evaluation tools for SLAM algorithms.

Automated exploration of algorithmic and hardware design space.

Simulation tools for optimizing heterogeneous architectures.

Abstract

Visual understanding of 3D environments in real-time, at low power, is a huge computational challenge. Often referred to as SLAM (Simultaneous Localisation and Mapping), it is central to applications spanning domestic and industrial robotics, autonomous vehicles, virtual and augmented reality. This paper describes the results of a major research effort to assemble the algorithms, architectures, tools, and systems software needed to enable delivery of SLAM, by supporting applications specialists in selecting and configuring the appropriate algorithm and the appropriate hardware, and compilation pathway, to meet their performance, accuracy, and energy consumption goals. The major contributions we present are (1) tools and methodology for systematic quantitative evaluation of SLAM algorithms, (2) automated, machine-learning-guided exploration of the algorithmic and implementation design space with respect to multiple objectives, (3) end-to-end simulation tools to enable optimisation of heterogeneous, accelerated architectures for the specific algorithmic requirements of the various SLAM algorithmic approaches, and (4) tools for delivering, where appropriate, accelerated, adaptive SLAM solutions in a managed, JIT-compiled, adaptive runtime context.