Our paper proposes a direct sparse visual odometry method that combines event and RGB-D data to estimate the pose of agile-legged robots during dynamic locomotion and acrobatic behaviors. Event cameras offer high temporal resolution and dynamic range, which can eliminate the issue of blurred RGB images during fast movements. This unique strength holds a potential for accurate pose estimation of agile-legged robots, which has been a challenging problem to tackle. Our framework leverages the benefits of both RGB-D and event cameras to achieve robust and accurate pose estimation, even during dynamic maneuvers such as jumping and landing a quadruped robot, the Mini-Cheetah. Our major contributions are threefold: Firstly, we introduce an adaptive time surface (ATS) method that addresses the whiteout and blackout issue in conventional time surfaces by formulating pixel-wise decay rates based on scene complexity and motion speed. Secondly, we develop an effective pixel selection method that directly samples from event data and applies sample filtering through ATS, enabling us to pick pixels on distinct features. Lastly, we propose a nonlinear pose optimization formula that simultaneously performs 3D-2D alignment on both RGB-based and event-based maps and images, allowing the algorithm to fully exploit the benefits of both data streams. We extensively evaluate the performance of our framework on both public datasets and our own quadruped robot dataset, demonstrating its effectiveness in accurately estimating the pose of agile robots during dynamic movements.
Estimating the camera's pose given images from a single camera is a traditional task in mobile robots and autonomous vehicles. This problem is called monocular visual odometry and often relies on geometric approaches that require considerable engineering effort for a specific scenario. Deep learning methods have been shown to be generalizable after proper training and with a large amount of available data. Transformer-based architectures have dominated the state-of-the-art in natural language processing and computer vision tasks, such as image and video understanding. In this work, we deal with the monocular visual odometry as a video understanding task to estimate the 6 degrees of freedom of a camera's pose. We contribute by presenting the TSformer-VO model based on spatio-temporal self-attention mechanisms to extract features from clips and estimate the motions in an end-to-end manner. Our approach achieved competitive state-of-the-art performance compared with geometry-based and deep learning-based methods on the KITTI visual odometry dataset, outperforming the DeepVO implementation highly accepted in the visual odometry community. The code is publicly available at https://github.com/aofrancani/TSformer-VO.
Effectively localizing an agent in a realistic, noisy setting is crucial for many embodied vision tasks. Visual Odometry (VO) is a practical substitute for unreliable GPS and compass sensors, especially in indoor environments. While SLAM-based methods show a solid performance without large data requirements, they are less flexible and robust w.r.t. to noise and changes in the sensor suite compared to learning-based approaches. Recent deep VO models, however, limit themselves to a fixed set of input modalities, e.g., RGB and depth, while training on millions of samples. When sensors fail, sensor suites change, or modalities are intentionally looped out due to available resources, e.g., power consumption, the models fail catastrophically. Furthermore, training these models from scratch is even more expensive without simulator access or suitable existing models that can be fine-tuned. While such scenarios get mostly ignored in simulation, they commonly hinder a model's reusability in real-world applications. We propose a Transformer-based modality-invariant VO approach that can deal with diverse or changing sensor suites of navigation agents. Our model outperforms previous methods while training on only a fraction of the data. We hope this method opens the door to a broader range of real-world applications that can benefit from flexible and learned VO models.
Predicting accurate depth with monocular images is important for low-cost robotic applications and autonomous driving. This study proposes a comprehensive self-supervised framework for accurate scale-aware depth prediction on autonomous driving scenes utilizing inter-frame poses obtained from inertial measurements. In particular, we introduce a Full-Scale depth prediction network named FSNet. FSNet contains four important improvements over existing self-supervised models: (1) a multichannel output representation for stable training of depth prediction in driving scenarios, (2) an optical-flow-based mask designed for dynamic object removal, (3) a self-distillation training strategy to augment the training process, and (4) an optimization-based post-processing algorithm in test time, fusing the results from visual odometry. With this framework, robots and vehicles with only one well-calibrated camera can collect sequences of training image frames and camera poses, and infer accurate 3D depths of the environment without extra labeling work or 3D data. Extensive experiments on the KITTI dataset, KITTI-360 dataset and the nuScenes dataset demonstrate the potential of FSNet. More visualizations are presented in \url{https://sites.google.com/view/fsnet/home}
This paper presents a novel visual-LiDAR odometry and mapping method with low-drift characteristics. The proposed method is based on two popular approaches, ORB-SLAM and A-LOAM, with monocular scale correction and visual-bootstrapped LiDAR poses initialization modifications. The scale corrector calculates the proportion between the depth of image keypoints recovered by triangulation and that provided by LiDAR, using an outlier rejection process for accuracy improvement. Concerning LiDAR poses initialization, the visual odometry approach gives the initial guesses of LiDAR motions for better performance. This methodology is not only applicable to high-resolution LiDAR but can also adapt to low-resolution LiDAR. To evaluate the proposed SLAM system's robustness and accuracy, we conducted experiments on the KITTI Odometry and S3E datasets. Experimental results illustrate that our method significantly outperforms standalone ORB-SLAM2 and A-LOAM. Furthermore, regarding the accuracy of visual odometry with scale correction, our method performs similarly to the stereo-mode ORB-SLAM2.
Keypoint detection & descriptors are foundational tech-nologies for computer vision tasks like image matching, 3D reconstruction and visual odometry. Hand-engineered methods like Harris corners, SIFT, and HOG descriptors have been used for decades; more recently, there has been a trend to introduce learning in an attempt to improve keypoint detectors. On inspection however, the results are difficult to interpret; recent learning-based methods employ a vast diversity of experimental setups and design choices: empirical results are often reported using different backbones, protocols, datasets, types of supervisions or tasks. Since these differences are often coupled together, it raises a natural question on what makes a good learned keypoint detector. In this work, we revisit the design of existing keypoint detectors by deconstructing their methodologies and identifying the key components. We re-design each component from first-principle and propose Simple Learned Keypoints (SiLK) that is fully-differentiable, lightweight, and flexible. Despite its simplicity, SiLK advances new state-of-the-art on Detection Repeatability and Homography Estimation tasks on HPatches and 3D Point-Cloud Registration task on ScanNet, and achieves competitive performance to state-of-the-art on camera pose estimation in 2022 Image Matching Challenge and ScanNet.
We propose learning a depth covariance function with applications to geometric vision tasks. Given RGB images as input, the covariance function can be flexibly used to define priors over depth functions, predictive distributions given observations, and methods for active point selection. We leverage these techniques for a selection of downstream tasks: depth completion, bundle adjustment, and monocular dense visual odometry.
Modern robotic platforms need a reliable localization system to operate daily beside humans. Simple pose estimation algorithms based on filtered wheel and inertial odometry often fail in the presence of abrupt kinematic changes and wheel slips. Moreover, despite the recent success of visual odometry, service and assistive robotic tasks often present challenging environmental conditions where visual-based solutions fail due to poor lighting or repetitive feature patterns. In this work, we propose an innovative online learning approach for wheel odometry correction, paving the way for a robust multi-source localization system. An efficient attention-based neural network architecture has been studied to combine precise performances with real-time inference. The proposed solution shows remarkable results compared to a standard neural network and filter-based odometry correction algorithms. Nonetheless, the online learning paradigm avoids the time-consuming data collection procedure and can be adopted on a generic robotic platform on-the-fly.
Many practitioners in robotics regularly depend on classic, hand-designed algorithms. Often the performance of these algorithms is tuned across a dataset of annotated examples which represent typical deployment conditions. Automatic tuning of these settings is traditionally known as algorithm configuration. In this work, we extend algorithm configuration to automatically discover multiple modes in the tuning dataset. Unlike prior work, these configuration modes represent multiple dataset instances and are detected automatically during the course of optimization. We propose three methods for mode discovery: a post hoc method, a multi-stage method, and an online algorithm using a multi-armed bandit. Our results characterize these methods on synthetic test functions and in multiple robotics application domains: stereoscopic depth estimation, differentiable rendering, motion planning, and visual odometry. We show the clear benefits of detecting multiple modes in algorithm configuration space.
We propose an automatic method for pose and motion estimation against a ground surface for a ground-moving robot-mounted monocular camera. The framework adopts a semi-dense approach that benefits from both a feature-based method and an image-registration-based method by setting multiple patches in the image for displacement computation through a highly accurate image-registration technique. To improve accuracy, we introduce virtual inverse perspective mapping (IPM) in the refinement step to eliminate the perspective effect on image registration. The pose and motion are jointly and robustly estimated by a formulation of geometric bundle adjustment via virtual IPM. Unlike conventional visual odometry methods, the proposed method is free from cumulative error because it directly estimates pose and motion against the ground by taking advantage of a camera configuration mounted on a ground-moving robot where the camera's vertical motion is ignorable compared to its height within the frame interval and the nearby ground surface is approximately flat. We conducted experiments in which the relative mean error of the pitch and roll angles was approximately 1.0 degrees and the absolute mean error of the travel distance was 0.3 mm, even under camera shaking within a short period.
Data-driven visual odometry (VO) is a critical subroutine for autonomous edge robotics, and recent progress in the field has produced highly accurate point predictions in complex environments. However, emerging autonomous edge robotics devices like insect-scale drones and surgical robots lack a computationally efficient framework to estimate VO's predictive uncertainties. Meanwhile, as edge robotics continue to proliferate into mission-critical application spaces, awareness of model's the predictive uncertainties has become crucial for risk-aware decision-making. This paper addresses this challenge by presenting a novel, lightweight, and statistically robust framework that leverages conformal inference (CI) to extract VO's uncertainty bands. Our approach represents the uncertainties using flexible, adaptable, and adjustable prediction intervals that, on average, guarantee the inclusion of the ground truth across all degrees of freedom (DOF) of pose estimation. We discuss the architectures of generative deep neural networks for estimating multivariate uncertainty bands along with point (mean) prediction. We also present techniques to improve the uncertainty estimation accuracy, such as leveraging Monte Carlo dropout (MC-dropout) for data augmentation. Finally, we propose a novel training loss function that combines interval scoring and calibration loss with traditional training metrics--mean-squared error and KL-divergence--to improve uncertainty-aware learning. Our simulation results demonstrate that the presented framework consistently captures true uncertainty in pose estimations across different datasets, estimation models, and applied noise types, indicating its wide applicability.
Visibility underwater is challenging, and degrades as the distance between the subject and camera increases, making vision tasks in the forward-looking direction more difficult. We have collected underwater forward-looking stereo-vision and visual-inertial image sets in the Mediterranean and Red Sea. To our knowledge there are no other public datasets in the underwater environment acquired with this camera-sensor orientation published with ground-truth. These datasets are critical for the development of several underwater applications, including obstacle avoidance, visual odometry, 3D tracking, Simultaneous Localization and Mapping (SLAM) and depth estimation. The stereo datasets include synchronized stereo images in dynamic underwater environments with objects of known-size. The visual-inertial datasets contain monocular images and IMU measurements, aligned with millisecond resolution timestamps and objects of known size which were placed in the scene. Both sensor configurations allow for scale estimation, with the calibrated baseline in the stereo setup and the IMU in the visual-inertial setup. Ground truth depth maps were created offline for both dataset types using photogrammetry. The ground truth is validated with multiple known measurements placed throughout the imaged environment. There are 5 stereo and 8 visual-inertial datasets in total, each containing thousands of images, with a range of different underwater visibility and ambient light conditions, natural and man-made structures and dynamic camera motions. The forward-looking orientation of the camera makes these datasets unique and ideal for testing underwater obstacle-avoidance algorithms and for navigation close to the seafloor in dynamic environments. With our datasets, we hope to encourage the advancement of autonomous functionality for underwater vehicles in dynamic and/or shallow water environments.
The Artemis program requires robotic and crewed lunar rovers for resource prospecting and exploitation, construction and maintenance of facilities, and human exploration. These rovers must support navigation for 10s of kilometers (km) from base camps. A lunar science rover mission concept - Endurance-A, has been recommended by the new Decadal Survey as the highest priority medium-class mission of the Lunar Discovery and Exploration Program, and would be required to traverse approximately 2000 km in the South Pole-Aitkin (SPA) Basin, with individual drives of several kilometers between stops for downlink. These rover mission scenarios require functionality that provides onboard, autonomous, global position knowledge ( aka absolute localization). However, planetary rovers have no onboard global localization capability to date; they have only used relative localization, by integrating combinations of wheel odometry, visual odometry, and inertial measurements during each drive to track position relative to the start of each drive. In this work, we summarize recent developments from the LunarNav project, where we have developed algorithms and software to enable lunar rovers to estimate their global position and heading on the Moon with a goal performance of position error less than 5 meters (m) and heading error less than 3-degree, 3-sigma, in sunlit areas. This will be achieved autonomously onboard by detecting craters in the vicinity of the rover and matching them to a database of known craters mapped from orbit. The overall technical framework consists of three main elements: 1) crater detection, 2) crater matching, and 3) state estimation. In previous work, we developed crater detection algorithms for three different sensing modalities. Our results suggest that rover localization with an error less than 5 m is highly probable during daytime operations.
In this paper, we present a novel visual SLAM and long-term localization benchmark for autonomous driving in challenging conditions based on the large-scale 4Seasons dataset. The proposed benchmark provides drastic appearance variations caused by seasonal changes and diverse weather and illumination conditions. While significant progress has been made in advancing visual SLAM on small-scale datasets with similar conditions, there is still a lack of unified benchmarks representative of real-world scenarios for autonomous driving. We introduce a new unified benchmark for jointly evaluating visual odometry, global place recognition, and map-based visual localization performance which is crucial to successfully enable autonomous driving in any condition. The data has been collected for more than one year, resulting in more than 300 km of recordings in nine different environments ranging from a multi-level parking garage to urban (including tunnels) to countryside and highway. We provide globally consistent reference poses with up to centimeter-level accuracy obtained from the fusion of direct stereo-inertial odometry with RTK GNSS. We evaluate the performance of several state-of-the-art visual odometry and visual localization baseline approaches on the benchmark and analyze their properties. The experimental results provide new insights into current approaches and show promising potential for future research. Our benchmark and evaluation protocols will be available at https://www.4seasons-dataset.com/.
We propose a 6D RGB-D odometry approach that finds the relative camera pose between consecutive RGB-D frames by keypoint extraction and feature matching both on the RGB and depth image planes. Furthermore, we feed the estimated pose to the highly accurate KinectFusion algorithm, which uses a fast ICP (Iterative Closest Point) to fine-tune the frame-to-frame relative pose and fuse the depth data into a global implicit surface. We evaluate our method on a publicly available RGB-D SLAM benchmark dataset by Sturm et al. The experimental results show that our proposed reconstruction method solely based on visual odometry and KinectFusion outperforms the state-of-the-art RGB-D SLAM system accuracy. Moreover, our algorithm outputs a ready-to-use polygon mesh (highly suitable for creating 3D virtual worlds) without any postprocessing steps.
Local feature detection is a key ingredient of many image processing and computer vision applications, such as visual odometry and localization. Most existing algorithms focus on feature detection from a sharp image. They would thus have degraded performance once the image is blurred, which could happen easily under low-lighting conditions. To address this issue, we propose a simple yet both efficient and effective keypoint detection method that is able to accurately localize the salient keypoints in a blurred image. Our method takes advantages of a novel multi-layer perceptron (MLP) based architecture that significantly improve the detection repeatability for a blurred image. The network is also light-weight and able to run in real-time, which enables its deployment for time-constrained applications. Extensive experimental results demonstrate that our detector is able to improve the detection repeatability with blurred images, while keeping comparable performance as existing state-of-the-art detectors for sharp images.
This paper reviews vision-based localization methods in GPS-denied environments and classifies the mainstream methods into Relative Vision Localization (RVL) and Absolute Vision Localization (AVL). For RVL, we discuss the broad application of optical flow in feature extraction-based Visual Odometry (VO) solutions and introduce advanced optical flow estimation methods. For AVL, we review recent advances in Visual Simultaneous Localization and Mapping (VSLAM) techniques, from optimization-based methods to Extended Kalman Filter (EKF) based methods. We also introduce the application of offline map registration and lane vision detection schemes to achieve Absolute Visual Localization. This paper compares the performance and applications of mainstream methods for visual localization and provides suggestions for future studies.
We introduce visual hints expansion for guiding stereo matching to improve generalization. Our work is motivated by the robustness of Visual Inertial Odometry (VIO) in computer vision and robotics, where a sparse and unevenly distributed set of feature points characterizes a scene. To improve stereo matching, we propose to elevate 2D hints to 3D points. These sparse and unevenly distributed 3D visual hints are expanded using a 3D random geometric graph, which enhances the learning and inference process. We evaluate our proposal on multiple widely adopted benchmarks and show improved performance without access to additional sensors other than the image sequence. To highlight practical applicability and symbiosis with visual odometry, we demonstrate how our methods run on embedded hardware.
With inputs from RGB-D camera, industrial camera and wheel odometer, in this letter, we propose a geometry-based detecting method, by which the 3-D modulated LED map can be acquired with the aid of visual odometry algorithm from ORB-SLAM2 system when the decoding result of LED-ID is inaccurate. Subsequently, an enhanced cost function is proposed to optimize the mapping result of LEDs. The average 3-D mapping error (8.5cm) is evaluated with a real-world experiment. This work can be viewed as a preliminary work of visible light positioning systems, offering a way to prevent the labor-intensive manual site surveys of LEDs.
This work introduces the problem of initial orbit determination (IOD) from only heading measurements. Such a problem occurs in practice when estimating the orbit of a spacecraft using visual odometry measurements from an optical camera. After reviewing the problem geometry, a simple solution is developed in the form of an iterative scheme on the parameters describing the orbital hodograph. Numerical results are presented for an example spacecraft in low lunar orbit. The principal intent of this brief study is to communicate the existence of a new class of IOD problem to the community and to encourage the broader study of hodographs and heading-only IOD.