SLAMBench2: Multi-Objective Head-to-Head Benchmarking for Visual SLAM

SLAM is becoming a key component of robotics and augmented reality (AR) systems. While a large number of SLAM algorithms have been presented, there has been little effort to unify the interface of such algorithms, or to perform a holistic comparison of their capabilities. This is a problem since different SLAM applications can have different functional and non-functional requirements. For example, a mobile phonebased AR application has a tight energy budget, while a UAV navigation system usually requires high accuracy. SLAMBench2 is a benchmarking framework to evaluate existing and future SLAM systems, both open and close source, over an extensible list of datasets, while using a comparable and clearly specified list of performance metrics. A wide variety of existing SLAM algorithms and datasets is supported, e.g. ElasticFusion, InfiniTAM, ORB-SLAM2, OKVIS, and integrating new ones is straightforward and clearly specified by the framework. SLAMBench2 is a publicly-available software framework which represents a starting point for quantitative, comparable and validatable experimental research to investigate trade-offs across SLAM systems.

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

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.

Introducing SLAMBench, a performance and accuracy benchmarking methodology for SLAM

Real-time dense computer vision and SLAM offer great potential for a new level of scene modelling, tracking and real environmental interaction for many types of robot, but their high computational requirements mean that use on mass market embedded platforms is challenging. Meanwhile, trends in low-cost, low-power processing are towards massive parallelism and heterogeneity, making it difficult for robotics and vision researchers to implement their algorithms in a performance-portable way. In this paper we introduce SLAMBench, a publicly-available software framework which represents a starting point for quantitative, comparable and validatable experimental research to investigate trade-offs in performance, accuracy and energy consumption of a dense RGB-D SLAM system. SLAMBench provides a KinectFusion implementation in C++, OpenMP, OpenCL and CUDA, and harnesses the ICL-NUIM dataset of synthetic RGB-D sequences with trajectory and scene ground truth for reliable accuracy comparison of different implementation and algorithms. We present an analysis and breakdown of the constituent algorithmic elements of KinectFusion, and experimentally investigate their execution time on a variety of multicore and GPUaccelerated platforms. For a popular embedded platform, we also present an analysis of energy efficiency for different configuration alternatives.

Quantifying the Impact of Parameter Tuning on Nature-Inspired Algorithms

The problem of parameterization is often central to the effective deployment of nature-inspired algorithms. However, finding the optimal set of parameter values for a combination of problem instance and solution method is highly challenging, and few concrete guidelines exist on how and when such tuning may be performed. Previous work tends to either focus on a specific algorithm or use benchmark problems, and both of these restrictions limit the applicability of any findings. Here, we examine a number of different algorithms, and study them in a "problem agnostic" fashion (i.e., one that is not tied to specific instances) by considering their performance on fitness landscapes with varying characteristics. Using this approach, we make a number of observations on which algorithms may (or may not) benefit from tuning, and in which specific circumstances.

Fitness Landscape-Based Characterisation of Nature-Inspired Algorithms

A significant challenge in nature-inspired algorithmics is the identification of specific characteristics of problems that make them harder (or easier) to solve using specific methods. The hope is that, by identifying these characteristics, we may more easily predict which algorithms are best-suited to problems sharing certain features. Here, we approach this problem using fitness landscape analysis. Techniques already exist for measuring the "difficulty" of specific landscapes, but these are often designed solely with evolutionary algorithms in mind, and are generally specific to discrete optimisation. In this paper we develop an approach for comparing a wide range of continuous optimisation algorithms. Using a fitness landscape generation technique, we compare six different nature-inspired algorithms and identify which methods perform best on landscapes exhibiting specific features.