arXiv subjects

John Folkesson

Publications and source records attributed to John Folkesson.

At least 37 records · Page 2Linked to original sources

arXiv2022

Online Stochastic Variational Gaussian Process Mapping for Large-Scale SLAM in Real Time

Autonomous underwater vehicles (AUVs) are becoming standard tools for underwater exploration and seabed mapping in both scientific and industrial applications \cite{graham2022rapid, stenius2022system}. Their capacity to dive untethered allows them to reach areas inaccessible to surface vessels and to collect data more closely to the seafloor, regardless of the water depth. However, their navigation autonomy remains bounded by the accuracy of their dead reckoning (DR) estimate of their global position, severely limited in the absence of a priori maps of the area and GPS signal. Global localization systems equivalent to the later exists for the underwater domain, such as LBL or USBL. However they involve expensive external infrastructure and their reliability decreases with the distance to the AUV, making them unsuitable for deep sea surveys.

cs.RO↗

arXiv2022

Data-driven Loop Closure Detection in Bathymetric Point Clouds for Underwater SLAM

Simultaneous localization and mapping (SLAM) frameworks for autonomous navigation rely on robust data association to identify loop closures for back-end trajectory optimization. In the case of autonomous underwater vehicles (AUVs) equipped with multibeam echosounders (MBES), data association is particularly challenging due to the scarcity of identifiable landmarks in the seabed, the large drift in dead-reckoning navigation estimates to which AUVs are prone and the low resolution characteristic of MBES data. Deep learning solutions to loop closure detection have shown excellent performance on data from more structured environments. However, their transfer to the seabed domain is not immediate and efforts to port them are hindered by the lack of bathymetric datasets. Thus, in this paper we propose a neural network architecture aimed to showcase the potential of adapting such techniques to correspondence matching in bathymetric data. We train our framework on real bathymetry from an AUV mission and evaluate its performance on the tasks of loop closure detection and coarse point cloud alignment. Finally, we show its potential against a more traditional method and release both its implementation and the dataset used.

cs.RO↗

arXiv2022

Neural Network Normal Estimation and Bathymetry Reconstruction from Sidescan Sonar

Sidescan sonar intensity encodes information about the changes of surface normal of the seabed. However, other factors such as seabed geometry as well as its material composition also affect the return intensity. One can model these intensity changes in a forward direction from the surface normals from bathymetric map and physical properties to the measured intensity or alternatively one can use an inverse model which starts from the intensities and models the surface normals. Here we use an inverse model which leverages deep learning's ability to learn from data; a convolutional neural network is used to estimate the surface normal from the sidescan. Thus the internal properties of the seabed are only implicitly learned. Once this information is estimated, a bathymetric map can be reconstructed through an optimization framework that also includes altimeter readings to provide a sparse depth profile as a constraint. Implicit neural representation learning was recently proposed to represent the bathymetric map in such an optimization framework. In this article, we use a neural network to represent the map and optimize it under constraints of altimeter points and estimated surface normal from sidescan. By fusing multiple observations from different angles from several sidescan lines, the estimated results are improved through optimization. We demonstrate the efficiency and scalability of the approach by reconstructing a high-quality bathymetry using sidescan data from a large sidescan survey. We compare the proposed data-driven inverse model approach of modeling a sidescan with a forward Lambertian model. We assess the quality of each reconstruction by comparing it with data constructed from a multibeam sensor.

cs.RO↗

arXiv2022

Neural Shape-from-Shading for Survey-Scale Self-Consistent Bathymetry from Sidescan

Sidescan sonar is a small and cost-effective sensing solution that can be easily mounted on most vessels. Historically, it has been used to produce high-definition images that experts may use to identify targets on the seafloor or in the water column. While solutions have been proposed to produce bathymetry solely from sidescan, or in conjunction with multibeam, they have had limited impact. This is partly a result of mostly being limited to single sidescan lines. In this paper, we propose a modern, salable solution to create high quality survey-scale bathymetry from many sidescan lines. By incorporating multiple observations of the same place, results can be improved as the estimates reinforce each other. Our method is based on sinusoidal representation networks, a recent advance in neural representation learning. We demonstrate the scalability of the approach by producing bathymetry from a large sidescan survey. The resulting quality is demonstrated by comparing to data collected with a high-precision multibeam sensor.

cs.RO↗

arXiv2022

High-Resolution Bathymetric Reconstruction From Sidescan Sonar With Deep Neural Networks

We propose a novel data-driven approach for high-resolution bathymetric reconstruction from sidescan. Sidescan sonar (SSS) intensities as a function of range do contain some information about the slope of the seabed. However, that information must be inferred. Additionally, the navigation system provides the estimated trajectory, and normally the altitude along this trajectory is also available. From these we obtain a very coarse seabed bathymetry as an input. This is then combined with the indirect but high-resolution seabed slope information from the sidescan to estimate the full bathymetry. This sparse depth could be acquired by single-beam echo sounder, Doppler Velocity Log (DVL), other bottom tracking sensors or bottom tracking algorithm from sidescan itself. In our work, a fully convolutional network is used to estimate the depth contour and its aleatoric uncertainty from the sidescan images and sparse depth in an end-to-end fashion. The estimated depth is then used together with the range to calculate the point's 3D location on the seafloor. A high-quality bathymetric map can be reconstructed after fusing the depth predictions and the corresponding confidence measures from the neural networks. We show the improvement of the bathymetric map gained by using sparse depths with sidescan over estimates with sidescan alone. We also show the benefit of confidence weighting when fusing multiple bathymetric estimates into a single map.

cs.RO↗

arXiv2022

Towards Differentiable Rendering for Sidescan Sonar Imagery

Recent advances in differentiable rendering, which allow calculating the gradients of 2D pixel values with respect to 3D object models, can be applied to estimation of the model parameters by gradient-based optimization with only 2D supervision. It is easy to incorporate deep neural networks into such an optimization pipeline, allowing the leveraging of deep learning techniques. This also largely reduces the requirement for collecting and annotating 3D data, which is very difficult for applications, for example when constructing geometry from 2D sensors. In this work, we propose a differentiable renderer for sidescan sonar imagery. We further demonstrate its ability to solve the inverse problem of directly reconstructing a 3D seafloor mesh from only 2D sidescan sonar data.

cs.GR↗

arXiv2022

Fully-probabilistic Terrain Modelling with Stochastic Variational Gaussian Process Maps

Gaussian processes (GPs) are becoming a standard tool to build terrain representations thanks to their capacity to model map uncertainty. This effectively yields a reliability measure of the areas of the map, which can be directly utilized by Bayes filtering algorithms in robot localization problems. A key insight is that this uncertainty can incorporate the noise intrinsic to the terrain surveying process through the GPs ability to train on uncertain inputs (UIs). However, existing techniques to build GP maps with UIs in a tractable manner are restricted in the form and degree of the input noise. In this letter, we propose a flexible and efficient framework to build large-scale GP maps with UIs based on Stochastic Variational GPs and Monte Carlo sampling of the UIs distributions. We validate our mapping approach on a large bathymetric survey collected with an AUV and analyze its performance against the use of deterministic inputs (DI). Finally, we show how using UI SVGP maps yields more accurate particle filter localization results than DI SVGP on a real AUV mission over an entirely predicted area.

cs.RO↗

arXiv2021

Interpretability in Contact-Rich Manipulation via Kinodynamic Images

Deep Neural Networks (NNs) have been widely utilized in contact-rich manipulation tasks to model the complicated contact dynamics. However, NN-based models are often difficult to decipher which can lead to seemingly inexplicable behaviors and unidentifiable failure cases. In this work, we address the interpretability of NN-based models by introducing the kinodynamic images. We propose a methodology that creates images from the kinematic and dynamic data of a contact-rich manipulation task. Our formulation visually reflects the task's state by encoding its kinodynamic variations and temporal evolution. By using images as the state representation, we enable the application of interpretability modules that were previously limited to vision-based tasks. We use this representation to train Convolution-based Networks and we extract interpretations of the model's decisions with Grad-CAM, a technique that produces visual explanations. Our method is versatile and can be applied to any classification problem using synchronous features in manipulation to visually interpret which parts of the input drive the model's decisions and distinguish its failure modes. We evaluate this approach on two examples of real-world contact-rich manipulation: pushing and cutting, with known and unknown objects. Finally, we demonstrate that our method enables both detailed visual inspections of sequences in a task, as well as high-level evaluations of a model's behavior and tendencies. Data and code for this work are available at https://github.com/imitsioni/interpretable_manipulation.

cs.RO↗

arXiv2020

Interpreting video features: a comparison of 3D convolutional networks and convolutional LSTM networks

A number of techniques for interpretability have been presented for deep learning in computer vision, typically with the goal of understanding what the networks have based their classification on. However, interpretability for deep video architectures is still in its infancy and we do not yet have a clear concept of how to decode spatiotemporal features. In this paper, we present a study comparing how 3D convolutional networks and convolutional LSTM networks learn features across temporally dependent frames. This is the first comparison of two video models that both convolve to learn spatial features but have principally different methods of modeling time. Additionally, we extend the concept of meaningful perturbation introduced by \cite{MeaningFulPert} to the temporal dimension, to identify the temporal part of a sequence most meaningful to the network for a classification decision. Our findings indicate that the 3D convolutional model concentrates on shorter events in the input sequence, and places its spatial focus on fewer, contiguous areas.

cs.CV↗

arXiv2020

Towards Autonomous Industrial-Scale Bathymetric Surveying

Both higher efficiency and cost reduction can be gained from automating bathymetric surveying for offshore applications such as pipeline, telecommunication or power cables installation and inspection on the seabed. We present a SLAM system that optimizes the geo-referencing of bathymetry surveys by fusing the dead-reckoning sensor data from the surveying vehicle with constraints from the maximization of the geometric consistency of overlapping regions of the survey. The framework has been extensively tested on bathymetric maps from both simulation and several actual industrial surveys and has proved robustness over different types of terrain. We demonstrate that our system is able to maximize the consistency of the final map even when there are large sections of the survey with reduced topographic variation. The framework has been made publicly available together with the simulation environment used to test it and some of the datasets.

cs.RO↗

arXiv2020

PointNetKL: Deep Inference for GICP Covariance Estimation in Bathymetric SLAM

Registration methods for point clouds have become a key component of many SLAM systems on autonomous vehicles. However, an accurate estimate of the uncertainty of such registration is a key requirement to a consistent fusion of this kind of measurements in a SLAM filter. This estimate, which is normally given as a covariance in the transformation computed between point cloud reference frames, has been modelled following different approaches, among which the most accurate is considered to be the Monte Carlo method. However, a Monte Carlo approximation is cumbersome to use inside a time-critical application such as online SLAM. Efforts have been made to estimate this covariance via machine learning using carefully designed features to abstract the raw point clouds. However, the performance of this approach is sensitive to the features chosen. We argue that it is possible to learn the features along with the covariance by working with the raw data and thus we propose a new approach based on PointNet. In this work, we train this network using the KL divergence between the learned uncertainty distribution and one computed by the Monte Carlo method as the loss. We test the performance of the general model presented applying it to our target use-case of SLAM with an autonomous underwater vehicle (AUV) restricted to the 2-dimensional registration of 3D bathymetric point clouds.

cs.RO↗

arXiv2019

GCNv2: Efficient Correspondence Prediction for Real-Time SLAM

In this paper, we present a deep learning-based network, GCNv2, for generation of keypoints and descriptors. GCNv2 is built on our previous method, GCN, a network trained for 3D projective geometry. GCNv2 is designed with a binary descriptor vector as the ORB feature so that it can easily replace ORB in systems such as ORB-SLAM2. GCNv2 significantly improves the computational efficiency over GCN that was only able to run on desktop hardware. We show how a modified version of ORB-SLAM2 using GCNv2 features runs on a Jetson TX2, an embedded low-power platform. Experimental results show that GCNv2 retains comparable accuracy as GCN and that it is robust enough to use for control of a flying drone.

cs.RO↗

arXiv2019

Sparse2Dense: From direct sparse odometry to dense 3D reconstruction

In this paper, we proposed a new deep learning based dense monocular SLAM method. Compared to existing methods, the proposed framework constructs a dense 3D model via a sparse to dense mapping using learned surface normals. With single view learned depth estimation as prior for monocular visual odometry, we obtain both accurate positioning and high quality depth reconstruction. The depth and normal are predicted by a single network trained in a tightly coupled manner.Experimental results show that our method significantly improves the performance of visual tracking and depth prediction in comparison to the state-of-the-art in deep monocular dense SLAM.

cs.RO↗

arXiv2018

Deep Reinforcement Learning to Acquire Navigation Skills for Wheel-Legged Robots in Complex Environments

Mobile robot navigation in complex and dynamic environments is a challenging but important problem. Reinforcement learning approaches fail to solve these tasks efficiently due to reward sparsities, temporal complexities and high-dimensionality of sensorimotor spaces which are inherent in such problems. We present a novel approach to train action policies to acquire navigation skills for wheel-legged robots using deep reinforcement learning. The policy maps height-map image observations to motor commands to navigate to a target position while avoiding obstacles. We propose to acquire the multifaceted navigation skill by learning and exploiting a number of manageable navigation behaviors. We also introduce a domain randomization technique to improve the versatility of the training samples. We demonstrate experimentally a significant improvement in terms of data-efficiency, success rate, robustness against irrelevant sensory data, and also the quality of the maneuver skills.

cs.RO↗

arXiv2018

Detection and Tracking of General Movable Objects in Large 3D Maps

This paper studies the problem of detection and tracking of general objects with long-term dynamics, observed by a mobile robot moving in a large environment. A key problem is that due to the environment scale, it can only observe a subset of the objects at any given time. Since some time passes between observations of objects in different places, the objects might be moved when the robot is not there. We propose a model for this movement in which the objects typically only move locally, but with some small probability they jump longer distances, through what we call global motion. For filtering, we decompose the posterior over local and global movements into two linked processes. The posterior over the global movements and measurement associations is sampled, while we track the local movement analytically using Kalman filters. This novel filter is evaluated on point cloud data gathered autonomously by a mobile robot over an extended period of time. We show that tracking jumping objects is feasible, and that the proposed probabilistic treatment outperforms previous methods when applied to real world data. The key to efficient probabilistic tracking in this scenario is focused sampling of the object posteriors.

cs.RO↗

arXiv2018

Multiple Object Detection, Tracking and Long-Term Dynamics Learning in Large 3D Maps

In this work, we present a method for tracking and learning the dynamics of all objects in a large scale robot environment. A mobile robot patrols the environment and visits the different locations one by one. Movable objects are discovered by change detection, and tracked throughout the robot deployment. For tracking, we extend the Rao-Blackwellized particle filter of previous work with birth and death processes, enabling the method to handle an arbitrary number of objects. Target births and associations are sampled using Gibbs sampling. The parameters of the system are then learnt using the Expectation Maximization algorithm in an unsupervised fashion. The system therefore enables learning of the dynamics of one particular environment, and of its objects. The algorithm is evaluated on data collected autonomously by a mobile robot in an office environment during a real-world deployment. We show that the algorithm automatically identifies and tracks the moving objects within 3D maps and infers plausible dynamics models, significantly decreasing the modeling bias of our previous work. The proposed method represents an improvement over previous methods for environment dynamics learning as it allows for learning of fine grained processes.

cs.RO↗

arXiv2017

Unsupervised Object Discovery and Segmentation of RGBD-images

In this paper we introduce a system for unsupervised object discovery and segmentation of RGBD-images. The system models the sensor noise directly from data, allowing accurate segmentation without sensor specific hand tuning of measurement noise models making use of the recently introduced Statistical Inlier Estimation (SIE) method. Through a fully probabilistic formulation, the system is able to apply probabilistic inference, enabling reliable segmentation in previously challenging scenarios. In addition, we introduce new methods for filtering out false positives, significantly improving the signal to noise ratio. We show that the system significantly outperform state-of-the-art in on a challenging real-world dataset.

cs.RO↗

arXiv2017

Adaptive Cost Function for Pointcloud Registration

In this paper we introduce an adaptive cost function for pointcloud registration. The algorithm automatically estimates the sensor noise, which is important for generalization across different sensors and environments. Through experiments on real and synthetic data, we show significant improvements in accuracy and robustness over state-of-the-art solutions.

cs.RO↗