Search

Road boundaries, or curbs, provide autonomous vehicles with essential information when interpreting road scenes and generating behaviour plans. Although curbs convey important information, they are difficult to detect in complex urban environments (in particular in comparison to other elements of the road such as traffic signs and road markings). These difficulties arise from occlusions by other traffic participants as well as changing lighting and/or weather conditions. Moreover, road boundaries have various shapes, colours and structures while motion planning algorithms require accurate and precise metric information in real-time to generate their plans. In this paper, we present a real-time LIDAR-based approach for accurate curb detection around the vehicle (360 degree). Our approach deals with both occlusions from traffic and changing environmental conditions. To this end, we project 3D LIDAR pointcloud data into 2D bird's-eye view images (akin to Inverse Perspective Mapping). These images are then processed by trained deep networks to infer both visible and occluded road boundaries. Finally, a post-processing step filters detected curb segments and tracks them over time. Experimental results demonstrate the effectiveness of the proposed approach on real-world driving data. Hence, we believe that our LIDAR-based approach provides an efficient and effective way to detect visible and occluded curbs around the vehicles in challenging driving scenarios., Comment: Accepted at the 22nd IEEE Intelligent Transportation Systems Conference (ITSC19), October, 2019, Auckland, New Zealand

Road markings provide guidance to traffic participants and enforce safe driving behaviour, understanding their semantic meaning is therefore paramount in (automated) driving. However, producing the vast quantities of road marking labels required for training state-of-the-art deep networks is costly, time-consuming, and simply infeasible for every domain and condition. In addition, training data retrieved from virtual worlds often lack the richness and complexity of the real world and consequently cannot be used directly. In this paper, we provide an alternative approach in which new road marking training pairs are automatically generated. To this end, we apply principles of domain randomization to the road layout and synthesize new images from altered semantic labels. We demonstrate that training on these synthetic pairs improves mIoU of the segmentation of rare road marking classes during real-world deployment in complex urban environments by more than 12 percentage points, while performance for other classes is retained. This framework can easily be scaled to all domains and conditions to generate large-scale road marking datasets, while avoiding manual labelling effort., Comment: presented at ITSC 2019

The availability of a large quantity of labelled training data is crucial for the training of modern object detectors. Hand labelling training data is time consuming and expensive while automatic labelling methods inevitably add unwanted noise to the labels. We examine the effect of different types of label noise on the performance of an object detector. We then show how co-teaching, a method developed for handling noisy labels and previously demonstrated on a classification problem, can be improved to mitigate the effects of label noise in an object detection setting. We illustrate our results using simulated noise on the KITTI dataset and on a vehicle detection task using automatically labelled data.

Radar detects stable, long-range objects under variable weather and lighting conditions, making it a reliable and versatile sensor well suited for ego-motion estimation. In this work, we propose a radar-only odometry pipeline that is highly robust to radar artifacts (e.g., speckle noise and false positives) and requires only one input parameter. We demonstrate its ability to adapt across diverse settings, from urban UK to off-road Iceland, achieving a scan matching accuracy of approximately 5.20 cm and 0.0929 deg when using GPS as ground truth (compared to visual odometry's 5.77 cm and 0.1032 deg). We present algorithms for keypoint extraction and data association, framing the latter as a graph matching optimization problem, and provide an in-depth system analysis., Comment: 6 content pages, 1 page of references, 5 figures, 4 tables, 2019 IEEE International Conference on Robotics and Automation (ICRA)

For autonomous vehicles to be able to operate successfully they need to be aware of other vehicles with sufficient time to make safe, stable plans. Given the possible closing speeds between two vehicles, this necessitates the ability to accurately detect distant vehicles. Many current image-based object detectors using convolutional neural networks exhibit excellent performance on existing datasets such as KITTI. However, the performance of these networks falls when detecting small (distant) objects. We demonstrate that incorporating radar data can boost performance in these difficult situations. We also introduce an efficient automated method for training data generation using cameras of different focal lengths.

We analyse the possibilities for the study of inclusive diffraction offered by future electron--proton/nucleus colliders in the TeV regime, the Large Hadron-electron Collider as an upgrade of the HL-LHC and the Future Circular Collider in electron-hadron mode. Compared to $ep$ collisions at HERA, we find an extension of the available kinematic range in $x$ by a factor of order $20$ and of the maximum $Q^2$ by a factor of order $100$ for LHeC, while the FCC version would extend the coverage by a further order of magnitude both in $x$ and $Q^2$. This translates into a range of available momentum fraction of the diffractive exchange with respect to the hadron ($\xi$), down to $10^{-4}-10^{-5}$ for a wide range of the momentum fraction of the parton with respect to the diffractive exchange ($\beta$). Using the same framework and methodology employed in previous studies at HERA, considering only the experimental uncertainties and not those stemming from the functional form of the initial conditions or other ones of theoretical origin, and under very conservative assumptions for the luminosities and systematic errors, we find an improvement in the extraction of diffractive parton densities from fits to reduced cross sections for inclusive coherent diffraction in $ep$ by about an order of magnitude. For $eA$, we also perform the simulations for the Electron Ion Collider. We find that an extraction of the currently unmeasured nuclear diffractive parton densities is possible with similar accuracy to that in $ep$., Comment: 24 pages, 16 figures

We present a method for improving segmentation tasks on images affected by adherent rain drops and streaks. We introduce a novel stereo dataset recorded using a system that allows one lens to be affected by real water droplets while keeping the other lens clear. We train a denoising generator using this dataset and show that it is effective at removing the effect of real water droplets, in the context of image reconstruction and road marking segmentation. To further test our de-noising approach, we describe a method of adding computer-generated adherent water droplets and streaks to any images, and use this technique as a proxy to demonstrate the effectiveness of our model in the context of general semantic segmentation. We benchmark our results using the CamVid road marking segmentation dataset, Cityscapes semantic segmentation datasets and our own real-rain dataset, and show significant improvement on all tasks., Comment: Submitted to ICRA2019

This work examines the role of reinforcement learning in reducing the severity of on-road collisions by controlling velocity and steering in situations in which contact is imminent. We construct a model, given camera images as input, that is capable of learning and predicting the dynamics of obstacles, cars and pedestrians, and train our policy using this model. Two policies that control both braking and steering are compared against a baseline where the only action taken is (conventional) braking in a straight line. The two policies are trained using two distinct reward structures, one where any and all collisions incur a fixed penalty, and a second one where the penalty is calculated based on already established delta-v models of injury severity. The results show that both policies exceed the performance of the baseline, with the policy trained using injury models having the highest performance., Comment: Presented at ITSC2018

The diverse community of scientists involved in Deep Inelastic Scattering includes about 2000 experimental and theoretical physicists worldwide and envisages projects such as the EIC, LHeC, FCC-eh and VHEeP as future lepton-hadron scattering facilities. The proposed facilities will address fundamental questions in strong interaction / QCD physics, including a first-ever tomographic mapping of the hadrons' internal structure, a solution to the proton mass and spin problems, understanding of the high-energy structure of hadronic matter and insight into connections between gravity and the strong interactions. They also extend and enhance the CERN programme of searches for new physics at the energy frontier, through a standalone precision Higgs and top programme, considerable sensitivity to the direct production of new particles and the most precise determinations of proton and nuclear structure in the kinematic range that is relevant to the LHC. In particular, we highlight the complementary aspects of the different lepton-hadron projects, and underscore how all are required to provide a complete characterization of the physics across the full kinematic reach. This review of the proposed facilities and their vast potential for particle physics was inspired by the discussions in the 2018 "DIS and Related Subjects" Workshop., Comment: 15 pages, 7 figures, EPPSU Strategy Document #103

Many tasks performed by autonomous vehicles such as road marking detection, object tracking, and path planning are simpler in bird's-eye view. Hence, Inverse Perspective Mapping (IPM) is often applied to remove the perspective effect from a vehicle's front-facing camera and to remap its images into a 2D domain, resulting in a top-down view. Unfortunately, however, this leads to unnatural blurring and stretching of objects at further distance, due to the resolution of the camera, limiting applicability. In this paper, we present an adversarial learning approach for generating a significantly improved IPM from a single camera image in real time. The generated bird's-eye-view images contain sharper features (e.g. road markings) and a more homogeneous illumination, while (dynamic) objects are automatically removed from the scene, thus revealing the underlying road layout in an improved fashion. We demonstrate our framework using real-world data from the Oxford RobotCar Dataset and show that scene understanding tasks directly benefit from our boosted IPM approach., Comment: equal contribution of first two authors, 8 full pages, 6 figures, accepted at IV 2019

Radar presents a promising alternative to lidar and vision in autonomous vehicle applications, able to detect objects at long range under a variety of weather conditions. However, distinguishing between occupied and free space from raw radar power returns is challenging due to complex interactions between sensor noise and occlusion. To counter this we propose to learn an Inverse Sensor Model (ISM) converting a raw radar scan to a grid map of occupancy probabilities using a deep neural network. Our network is self-supervised using partial occupancy labels generated by lidar, allowing a robot to learn about world occupancy from past experience without human supervision. We evaluate our approach on five hours of data recorded in a dynamic urban environment. By accounting for the scene context of each grid cell our model is able to successfully segment the world into occupied and free space, outperforming standard CFAR filtering approaches. Additionally by incorporating heteroscedastic uncertainty into our model formulation, we are able to quantify the variance in the uncertainty throughout the sensor observation. Through this mechanism we are able to successfully identify regions of space that are likely to be occluded., Comment: 6 full pages, 1 page of references

This paper is about alerting acoustic event detection and sound source localisation in an urban scenario. Specifically, we are interested in spotting the presence of horns, and sirens of emergency vehicles. In order to obtain a reliable system able to operate robustly despite the presence of traffic noise, which can be copious, unstructured and unpredictable, we propose to treat the spectrograms of incoming stereo signals as images, and apply semantic segmentation, based on a Unet architecture, to extract the target sound from the background noise. In a multi-task learning scheme, together with signal denoising, we perform acoustic event classification to identify the nature of the alerting sound. Lastly, we use the denoised signals to localise the acoustic source on the horizon plane, by regressing the direction of arrival of the sound through a CNN architecture. Our experimental evaluation shows an average classification rate of 94%, and a median absolute error on the localisation of 7.5{\deg} when operating on audio frames of 0.5s, and of 2.5{\deg} when operating on frames of 2.5s. The system offers excellent performance in particularly challenging scenarios, where the noise level is remarkably high., Comment: 6 pages, 9 figures

Estimating motion from images is a well-studied problem in computer vision and robotics. Previous work has developed techniques to estimate the motion of a moving camera in a largely static environment (e.g., visual odometry) and to segment or track motions in a dynamic scene using known camera motions (e.g., multiple object tracking). It is more challenging to estimate the unknown motion of the camera and the dynamic scene simultaneously. Most previous work requires a priori object models (e.g., tracking-by-detection), motion constraints (e.g., planar motion), or fails to estimate the full SE(3) motions of the scene (e.g., scene flow). While these approaches work well in specific application domains, they are not generalizable to unconstrained motions. This paper extends the traditional visual odometry (VO) pipeline to estimate the full SE(3) motion of both a stereo/RGB-D camera and the dynamic scene. This multimotion visual odometry (MVO) pipeline requires no a priori knowledge of the environment or the dynamic objects. Its performance is evaluated on a real-world dynamic dataset with ground truth for all motions from a motion capture system., Comment: This updated manuscript corrects the experimental results published in the proceedings of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).. 8 Pages. 7 Figures. Video available at https://www.youtube.com/watch?v=84tXCJOlj00

We present a method of improving visual place recognition and metric localisation under very strong appear- ance change. We learn an invertable generator that can trans- form the conditions of images, e.g. from day to night, summer to winter etc. This image transforming filter is explicitly designed to aid and abet feature-matching using a new loss based on SURF detector and dense descriptor maps. A network is trained to output synthetic images optimised for feature matching given only an input RGB image, and these generated images are used to localize the robot against a previously built map using traditional sparse matching approaches. We benchmark our results using multiple traversals of the Oxford RobotCar Dataset over a year-long period, using one traversal as a map and the other to localise. We show that this method significantly improves place recognition and localisation under changing and adverse conditions, while reducing the number of mapping runs needed to successfully achieve reliable localisation., Comment: Accepted at ICRA2018

Surveying 3D scenes is a common task in robotics. Systems can do so autonomously by iteratively obtaining measurements. This process of planning observations to improve the model of a scene is called Next Best View (NBV) planning. NBV planning approaches often use either volumetric (e.g., voxel grids) or surface (e.g., triangulated meshes) representations. Volumetric approaches generalise well between scenes as they do not depend on surface geometry but do not scale to high-resolution models of large scenes. Surface representations can obtain high-resolution models at any scale but often require tuning of unintuitive parameters or multiple survey stages. This paper presents a scene-model-free NBV planning approach with a density representation. The Surface Edge Explorer (SEE) uses the density of current measurements to detect and explore observed surface boundaries. This approach is shown experimentally to provide better surface coverage in lower computation time than the evaluated state-of-the-art volumetric approaches while moving equivalent distances.

Dense reconstructions often contain errors that prior work has so far minimised using high quality sensors and regularising the output. Nevertheless, errors still persist. This paper proposes a machine learning technique to identify errors in three dimensional (3D) meshes. Beyond simply identifying errors, our method quantifies both the magnitude and the direction of depth estimate errors when viewing the scene. This enables us to improve the reconstruction accuracy. We train a suitably deep network architecture with two 3D meshes: a high-quality laser reconstruction, and a lower quality stereo image reconstruction. The network predicts the amount of error in the lower quality reconstruction with respect to the high-quality one, having only view the former through its input. We evaluate our approach by correcting two-dimensional (2D) inverse-depth images extracted from the 3D model, and show that our method improves the quality of these depth reconstructions by up to a relative 10% RMSE., Comment: Accepted for the International Conference on Robotics and Automation (ICRA) 2018

This paper presents a mercantile framework for the decentralised sharing of navigation expertise amongst a fleet of robots which perform regular missions into a common but variable environment. We build on our earlier work and allow individual agents to intermittently initiate trades based on a real-time assessment of the nature of their missions or demand for localisation capability, and to choose trading partners with discrimination based on an internally evolving set of beliefs in the expected value of trading with each other member of the team. To this end, we suggest some obligatory properties that a formalisation of the distributed versioning of experience maps should exhibit, to ensure the eventual convergence in the state of each agent's map under a sequence of pairwise exchanges, as well as the uninterrupted integrity of the representation under versioning operations. To mitigate limitations in hardware and network resources, the "data market" is catalogued by distinct sections of the world, which the agents treat as "products" for appraisal and purchase. To this end, we demonstrate and evaluate our system using the publicly available Oxford RobotCar Dataset, the hand-labelled data market catalogue (approaching 446km of fully indexed sections-of-interest) for which we plan to release alongside the existing raw stereo imagery. We show that, by refining market policies over time, agents achieve improved localisation in a directed and accelerated manner.

We propose a novel method to fit and segment multi-structural data via convex relaxation. Unlike greedy methods --which maximise the number of inliers-- this approach efficiently searches for a soft assignment of points to models by minimising the energy of the overall classification. Our approach is similar to state-of-the-art energy minimisation techniques which use a global energy. However, we deal with the scaling factor (as the number of models increases) of the original combinatorial problem by relaxing the solution. This relaxation brings two advantages: first, by operating in the continuous domain we can parallelize the calculations. Second, it allows for the use of different metrics which results in a more general formulation. We demonstrate the versatility of our technique on two different problems of estimating structure from images: plane extraction from RGB-D data and homography estimation from pairs of images. In both cases, we report accurate results on publicly available datasets, in most of the cases outperforming the state-of-the-art.

The design of mobile autonomous robots is challenging due to the limited on-board resources such as processing power and energy. A promising approach is to generate intelligent schedules that reduce the resource consumption while maintaining best performance, or more interestingly, to trade off reduced resource consumption for a slightly lower but still acceptable level of performance. In this paper, we provide a framework to aid designers in exploring such resource-performance trade-offs and finding schedules for mobile robots, guided by questions such as "what is the minimum resource budget required to achieve a given level of performance?" The framework is based on a quantitative multi-objective verification technique which, for a collection of possibly conflicting objectives, produces the Pareto front that contains all the optimal trade-offs that are achievable. The designer then selects a specific Pareto point based on the resource constraints and desired performance level, and a correct-by-construction schedule that meets those constraints is automatically generated. We demonstrate the efficacy of this framework on several robotic scenarios in both simulations and experiments with encouraging results., Comment: Technical report accompanying RA-L/ICRA'17 submission

This paper is about the efficient generation of dense, colored models of city-scale environments from range data and in particular, stereo cameras. Better maps make for better understanding; better understanding leads to better robots, but this comes at a cost. The computational and memory requirements of large dense models can be prohibitive. We provide the theory and the system needed to create city-scale dense reconstructions. To do so, we apply a regularizer over a compressed 3D data structure while dealing with the complex boundary conditions this induces during the data-fusion stage. We show that only with these considerations can we swiftly create neat, large, "well behaved" reconstructions. We evaluate our system using the KITTI dataset and provide statistics for the metric errors in all surfaces created compared to those measured with 3D laser. Our regularizer reduces the median error by 40% in 3.4 km of dense reconstructions with a median accuracy of 6 cm. For subjective analysis, we provide a qualitative review of 6.1 km of our dense reconstructions in an attached video. These are the largest dense reconstructions from a single passive camera we are aware of in the literature.

The hadronic final state in electron-proton collisions at HERA has provided a rich testing ground for development of the theory of the strong force, QCD. In this review, over 200 publications from the H1 and ZEUS Collaborations are summarised. Short distance physics, the measurement of processes at high energy scales, has provided rigorous tests of perturbative QCD and constrained the structure of the proton as well as allowing precise measurements of the strong coupling constant to be made. Non-perturbative or low energy processes have also been investigated and results on hadronisation interpreted together with those from other experiments. Searches for exotic QCD objects, such as pentaquarks, glueballs and instantons have been performed. The subject of diffraction has been re-invigorated through its precise measurement, such that it can now be described by perturbative QCD. After discussion of HERA, the H1 and ZEUS detectors and the techniques used to reconstruct differing hadronic final states, the above subject areas are elaborated. The major achievements are then condensed further in a final section summarising what has been learned., Comment: 60 pages, 65 figures, submitted to Reviews of Modern Physics. Updated version includes comments to the text from journal referees

This report contains selected recent highlights from experimental studies of soft and semi-hard strong interactions from the Large Hadron Collider, HERA and the Tevatron. The subject is broken down into diffractive and non-diffractive channels and the most significant recent progress and open questions in each area are summarised., Comment: 13 pages. Proceedings of ICHEP 2012, Melbourne, Australia