Kidnapped Radar: Topological Radar Localisation using Rotationally-Invariant Metric Learning
Authors:
- Ştefan SăftescuŞSŞtefan Săftescu
- Matthew GaddMatthew Gadd
- Daniele De MartiniDMDaniele De Martini
- Dan BarnesDBDan Barnes
- Paul NewmanPNPaul Newman
Preprint
Abstract
This paper presents a system for robust, large-scale topological localisation using Frequency-Modulated Continuous-Wave (FMCW) scanning radar. We learn a metric space for embedding polar radar scans using CNN and NetVLAD architectures traditionally applied to the visual domain. However, we tailor the feature extraction for more suitability to the polar nature of radar scan formation using cylindrical convolutions, anti-aliasing blurring, and azimuth-wise max-pooling; all in order to bolster the rotational invariance. The enforced metric space is then used to encode a reference trajectory, serving as a map, which is queried for nearest neighbours (NNs) for recognition of places at run-time. We demonstrate the performance of our topological localisation system over the course of many repeat forays using the largest radar-focused mobile autonomy dataset released to date, totalling 280 km of urban driving, a small portion of which we also use to learn the weights of the modified architecture. As this work represents a novel application for FMCW radar, we analyse the utility of the proposed method via a comprehensive set of metrics which provide insight into the efficacy when used in a realistic system, showing improved performance over the root architecture even in the face of random rotational perturbation.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- The Oxford Radar RobotCar Dataset: A Radar Extension to the Oxford RobotCar Dataset2020
- A Holistic Visual Place Recognition Approach Using Lightweight CNNs for Significant ViewPoint and Appearance ChangesIEEE Transactions on Robotics, 2019
- Local Descriptor for Robust Place Recognition Using LiDAR IntensityIEEE Robotics and Automation Letters, 2019
- Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World GraphsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- X-View: Graph-Based Semantic Multi-View LocalizationIEEE Robotics and Automation Letters, 2018
- Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception AgeIEEE Transactions on Robotics, 2016
- 1 year, 1000 km: The Oxford RobotCar datasetThe International Journal of Robotics Research, 2016
- Radar Sensing for Intelligent Vehicles in Urban EnvironmentsSensors, 2015
- FAB-MAP: Probabilistic Localization and Mapping in the Space of AppearanceThe International Journal of Robotics Research, 2008
- Multidimensional binary search trees used for associative searchingCommunications of the ACM, 1975