Under the Radar: Learning to Predict Robust Keypoints for Odometry Estimation and Metric Localisation in Radar

Barnes, Dan; Posner, Ingmar

doi:10.1109/icra40945.2020.9196835

Cited by 93 publications

(122 citation statements)

References 21 publications

Supporting

Mentioning

122

Contrasting

Order By: Relevance

“…However, each of these methods relies on either hand-crafted feature detectors and descriptors or cumbersome phase correlation techniques. Barnes and Posner [9] showed that learned features can result in superior radar odometry performance. Their work currently represents the state of the art for point-based radar odometry.…”

Section: Related Workmentioning

confidence: 99%

“…Previous works in this area have made significant progress towards radar-based odometry [2-4, 9, 11, 14-16, 26, 34, 39] and place recognition [20,22,31,43,46]. However, previous approaches to radar odometry have either relied on handcrafted feature extraction [2-4, 14-16, 26, 34], correlative scan matching [11,39], or a (self-)supervised learning algorithm [9,11] that relies on trajectory groundtruth. Barnes and Posner [9] previously showed that learned features have the potential to outperform hand-crafted features.…”

Section: Introductionmentioning

confidence: 99%

“…However, previous approaches to radar odometry have either relied on handcrafted feature extraction [2-4, 14-16, 26, 34], correlative scan matching [11,39], or a (self-)supervised learning algorithm [9,11] that relies on trajectory groundtruth. Barnes and Posner [9] previously showed that learned features have the potential to outperform hand-crafted features. On the other hand, it has not yet been shown whether correlative scan matching systems can be scaled up to large-scale mapping and localization.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Radar Odometry Combining Probabilistic Estimation and Unsupervised Feature Learning

Burnett

Yoon

Schoellig

et al. 2021

Robotics: Science and Systems XVII

View full text Add to dashboard Cite

This paper presents a radar odometry method that combines probabilistic trajectory estimation and deep learned features without needing groundtruth pose information. The feature network is trained unsupervised, using only the on-board radar data. With its theoretical foundation based on a data likelihood objective, our method leverages a deep network for processing rich radar data, and a non-differentiable classic estimator for probabilistic inference. We provide extensive experimental results on both the publicly available Oxford Radar RobotCar Dataset and an additional 100 km of driving collected in an urban setting. Our sliding-window implementation of radar odometry outperforms most hand-crafted methods and approaches the current state of the art without requiring a groundtruth trajectory for training. We also demonstrate the effectiveness of radar odometry under adverse weather conditions. Code for this project can be found at: https://github.com/utiasASRL/hero radar odometry

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Radar Odometry Combining Probabilistic Estimation and Unsupervised Feature Learning

Burnett

Yoon

Schoellig

et al. 2021

Robotics: Science and Systems XVII

View full text Add to dashboard Cite

show abstract

“…The local descriptors are then fed to a PointNetVLAD layer with attention to learn a global descriptor for place recognition. Barnes and Posner [3] learned key-points from radar images for odometry, and pooled local descriptors across spatial dimensions into a global one per image for place recognition.…”

Section: Deep Learning For Point-cloud Place Recognitionmentioning

confidence: 99%

“…We set λ = 10 in our experiments. The points extraction step in Algorithm 1 is fully differentiable, allowing the loss in Equation ( 5) to not only optimise the DCP network, but also fine-tune the pretrained network for f o , without needing to also apply the loss in Equation (3). The data flow for pose estimation is shown on the left of Figure 7.…”

Section: Learning Pose Estimationmentioning

confidence: 99%

Get to the Point: Learning Lidar Place Recognition and Metric Localisation Using Overhead Imagery

Tang¹,

Martini²,

Newman³

2021

Robotics: Science and Systems XVII

View full text Add to dashboard Cite

This paper is about localising a robot in overhead images using lidar. Specifically, we show how to solve both place recognition and metric localisation of a lidar using only publicly available overhead imagery as a map proxy. This is in contrast to current approaches that rely on prior sensor maps. To handle the drastic modality difference (overhead image vs. on the ground lidar), our method learns a representation that purposely and suitably transforms a given overhead image into a collection of 2D points, allowing for direct comparison against lidar scans. After both modalities are expressed as points, point-based methods can then be leveraged to learn the registration and place recognition task. Our method is the first to learn the place recognition of a lidar using only overhead imagery, and outperforms prior work for metric localisation with large initial pose offsets.

show abstract

FMCW Radar on LiDAR map localization in structural urban environments

Ma,

Li,

Zhao

et al. 2024

Journal of Field Robotics

View full text Add to dashboard Cite

Multisensor fusion‐based localization technology has achieved high accuracy in autonomous systems. How to improve the robustness is the main challenge at present. The most commonly used LiDAR and camera are weather‐sensitive, while the frequency‐modulated continuous wave Radar has strong adaptability but suffers from noise and ghost effects. In this paper, we propose a heterogeneous localization method called Radar on LiDAR Map, which aims to enhance localization accuracy without relying on loop closures by mitigating the accumulated error in Radar odometry in real time. To accomplish this, we utilize LiDAR scans and ground truth paths as Teach paths and Radar scans as the trajectories to be estimated, referred to as Repeat paths. By establishing a correlation between the Radar and LiDAR scan data, we can enhance the accuracy of Radar odometry estimation. Our approach involves embedding the data from both Radar and LiDAR sensors into a density map. We calculate the spatial vector similarity with an offset to determine the corresponding place index within the candidate map and estimate the rotation and translation. To refine the alignment, we utilize the Iterative Closest Point algorithm to achieve optimal matching on the LiDAR submap. The estimated bias is subsequently incorporated into the Radar SLAM for optimizing the position map. We conducted extensive experiments on the Mulran Radar Data set, Oxford Radar RobotCar Dataset, and our data set to demonstrate the feasibility and effectiveness of our proposed approach. Our proposed scan projection descriptors achieves homogeneous and heterogeneous place recognition and works much better than existing methods. Its application to the Radar SLAM system also substantially improves the positioning accuracy. All sequences' root mean square error is 2.53 m for positioning and 1.83° for angle.

show abstract

Under the Radar: Learning to Predict Robust Keypoints for Odometry Estimation and Metric Localisation in Radar

Cited by 93 publications

References 21 publications

Radar Odometry Combining Probabilistic Estimation and Unsupervised Feature Learning

Radar Odometry Combining Probabilistic Estimation and Unsupervised Feature Learning

Get to the Point: Learning Lidar Place Recognition and Metric Localisation Using Overhead Imagery

FMCW Radar on LiDAR map localization in structural urban environments

Contact Info

Product

Resources

About