arXiv subjects

Sven Behnke

Publications and source records attributed to Sven Behnke.

At least 145 records · Page 8Linked to original sources

arXiv2020

EasyPBR: A Lightweight Physically-Based Renderer

Modern rendering libraries provide unprecedented realism, producing real-time photorealistic 3D graphics on commodity hardware. Visual fidelity, however, comes at the cost of increased complexity and difficulty of usage, with many rendering parameters requiring a deep understanding of the pipeline. We propose EasyPBR as an alternative rendering library that strikes a balance between ease-of-use and visual quality. EasyPBR consists of a deferred renderer that implements recent state-of-the-art approaches in physically based rendering. It offers an easy-to-use Python and C++ interface that allows high-quality images to be created in only a few lines of code or directly through a graphical user interface. The user can choose between fully controlling the rendering pipeline or letting EasyPBR automatically infer the best parameters based on the current scene composition. The EasyPBR library can help the community to more easily leverage the power of current GPUs to create realistic images. These can then be used as synthetic data for deep learning or for creating animations for academic purposes.

cs.GR↗

arXiv2020

Capture Steps: Robust Walking for Humanoid Robots

Stable bipedal walking is a key prerequisite for humanoid robots to reach their potential of being versatile helpers in our everyday environments. Bipedal walking is, however, a complex motion that requires the coordination of many degrees of freedom while it is also inherently unstable and sensitive to disturbances. The balance of a walking biped has to be constantly maintained. The most effective way of controlling balance are well timed and placed recovery steps -- capture steps -- that absorb the expense momentum gained from a push or a stumble. We present a bipedal gait generation framework that utilizes step timing and foot placement techniques in order to recover the balance of a biped even after strong disturbances. Our framework modifies the next footstep location instantly when responding to a disturbance and generates controllable omnidirectional walking using only very little sensing and computational power. We exploit the open-loop stability of a central pattern generated gait to fit a linear inverted pendulum model to the observed center of mass trajectory. Then, we use the fitted model to predict suitable footstep locations and timings in order to maintain balance while following a target walking velocity. Our experiments show qualitative and statistical evidence of one of the strongest push-recovery capabilities among humanoid robots to date.

cs.RO↗

arXiv2020

Trajectory Generation with Fast Lidar-based 3D Collision Avoidance for Agile MAVs

Micro aerial vehicles (MAVs), are frequently used for exploration, examination, and surveillance during search and rescue missions. Manually piloting these robots under stressful conditions provokes pilot errors and can result in crashes with disastrous consequences. Also, during fully autonomous flight, planned high-level trajectories can be erroneous and steer the robot into obstacles. In this work, we propose an approach to efficiently compute smooth, time-optimal trajectories MAVs that avoid obstacles. Our method first computes a trajectory from the start to an arbitrary target state, including position, velocity, and acceleration. It respects input- and state-constraints and is thus dynamically feasible. Afterward, we efficiently check the trajectory for collisions in the 3D-point cloud, recorded with the onboard lidar. We exploit the piecewise polynomial formulation of our trajectories to analytically compute axis-aligned bounding boxes (AABB) to speed up the collision checking process. If collisions occur, we generate a set of alternative trajectories in real-time. Alternative trajectories bring the MAV in a safe state, while still pursuing the original goal. Subsequently, we choose and execute the best collision-free alternative trajectory based on a distance metric. The evaluation in simulation and during a real firefighting exercise shows the capability of our method.

cs.RO↗

arXiv2020

Autonomous Wall Building with a UGV-UAV Team at MBZIRC 2020

Constructing large structures with robots is a challenging task with many potential applications that requires mobile manipulation capabilities. We present two systems for autonomous wall building that we developed for the Mohamed Bin Zayed International Robotics Challenge 2020. Both systems autonomously perceive their environment, find bricks, and build a predefined wall structure. While the UGV uses a 3D LiDAR-based perception system which measures brick poses with high precision, the UAV employs a real-time camera-based system for visual servoing. We report results and insights from our successful participation at the MBZIRC 2020 Finals, additional lab experiments, and discuss the lessons learned from the competition.

cs.RO↗

arXiv2020

Visually Guided Balloon Popping with an Autonomous MAV at MBZIRC 2020

Visually guided control of micro aerial vehicles (MAV) demands for robust real-time perception, fast trajectory generation, and a capable flight platform. We present a fully autonomous MAV that is able to pop balloons, relying only on onboard sensing and computing. The system is evaluated with real robot experiments during the Mohamed Bin Zayed International Robotics Challenge (MBZIRC) 2020 where it showed its resilience and speed. In all three competition runs we were able to pop all five balloons in less than two minutes flight time with a single MAV.

cs.RO↗

arXiv2020

Robust Skeletonization for Plant Root Structure Reconstruction from MRI

Structural reconstruction of plant roots from MRI is challenging, because of low resolution and low signal-to-noise ratio of the 3D measurements which may lead to disconnectivities and wrongly connected roots. We propose a two-stage approach for this task. The first stage is based on semantic root vs. soil segmentation and finds lowest-cost paths from any root voxel to the shoot. The second stage takes the largest fully connected component generated in the first stage and uses 3D skeletonization to extract a graph structure. We evaluate our method on 22 MRI scans and compare to human expert reconstructions.

cs.CV↗

arXiv2020

NimbRo-OP2X: Affordable Adult-sized 3D-printed Open-Source Humanoid Robot for Research

For several years, high development and production costs of humanoid robots restricted researchers interested in working in the field. To overcome this problem, several research groups have opted to work with simulated or smaller robots, whose acquisition costs are significantly lower. However, due to scale differences and imperfect simulation replicability, results may not be directly reproducible on real, adult-sized robots. In this paper, we present the NimbRo-OP2X, a capable and affordable adult-sized humanoid platform aiming to significantly lower the entry barrier for humanoid robot research. With a height of 135 cm and weight of only 19 kg, the robot can interact in an unmodified, human environment without special safety equipment. Modularity in hardware and software allow this platform enough flexibility to operate in different scenarios and applications with minimal effort. The robot is equipped with an on-board computer with GPU, which enables the implementation of state-of-the-art approaches for object detection and human perception demanded by areas such as manipulation and human-robot interaction. Finally, the capabilities of the NimbRo-OP2X, especially in terms of locomotion stability and visual perception, are evaluated. This includes the performance at RoboCup 2018, where NimbRo-OP2X won all possible awards in the AdultSize class.

cs.RO↗

arXiv2020

Category-Level 3D Non-Rigid Registration from Single-View RGB Images

In this paper, we propose a novel approach to solve the 3D non-rigid registration problem from RGB images using Convolutional Neural Networks (CNNs). Our objective is to find a deformation field (typically used for transferring knowledge between instances, e.g., grasping skills) that warps a given 3D canonical model into a novel instance observed by a single-view RGB image. This is done by training a CNN that infers a deformation field for the visible parts of the canonical model and by employing a learned shape (latent) space for inferring the deformations of the occluded parts. As result of the registration, the observed model is reconstructed. Because our method does not need depth information, it can register objects that are typically hard to perceive with RGB-D sensors, e.g. with transparent or shiny surfaces. Even without depth data, our approach outperforms the Coherent Point Drift (CPD) registration method for the evaluated object categories.

cs.CV↗

arXiv2020

LatticeNet: Fast Point Cloud Segmentation Using Permutohedral Lattices

Deep convolutional neural networks (CNNs) have shown outstanding performance in the task of semantically segmenting images. However, applying the same methods on 3D data still poses challenges due to the heavy memory requirements and the lack of structured data. Here, we propose LatticeNet, a novel approach for 3D semantic segmentation, which takes as input raw point clouds. A PointNet describes the local geometry which we embed into a sparse permutohedral lattice. The lattice allows for fast convolutions while keeping a low memory footprint. Further, we introduce DeformSlice, a novel learned data-dependent interpolation for projecting lattice features back onto the point cloud. We present results of 3D segmentation on various datasets where our method achieves state-of-the-art performance.

cs.CV↗

arXiv2020

Fast Whole-Body Motion Control of Humanoid Robots with Inertia Constraints

We introduce a new, analytical method for generating whole-body motions for humanoid robots, which approximate the desired Composite Rigid Body (CRB) inertia. Our approach uses a reduced five mass model, where four of the masses are attributed to the limbs and one is used for the trunk. This compact formulation allows for finding an analytical solution that combines the kinematics with mass distribution and inertial properties of a humanoid robot. The positioning of the masses in Cartesian space is then directly used to obtain joint angles with relations based on simple geometry. Motions are achieved through the time evolution of poses generated through the desired foot positioning and CRB inertia properties. As a result, we achieve short computation times in the order of tens of microseconds. This makes the method suited for applications with limited computation resources, or leaving them to be spent on higher-layer tasks such as model predictive control. The approach is evaluated by performing a dynamic kicking motion with an igus Humanoid Open Platform robot.

cs.RO↗

arXiv2020

Multi-Staged Cross-Lingual Acoustic Model Adaption for Robust Speech Recognition in Real-World Applications -- A Case Study on German Oral History Interviews

While recent automatic speech recognition systems achieve remarkable performance when large amounts of adequate, high quality annotated speech data is used for training, the same systems often only achieve an unsatisfactory result for tasks in domains that greatly deviate from the conditions represented by the training data. For many real-world applications, there is a lack of sufficient data that can be directly used for training robust speech recognition systems. To address this issue, we propose and investigate an approach that performs a robust acoustic model adaption to a target domain in a cross-lingual, multi-staged manner. Our approach enables the exploitation of large-scale training data from other domains in both the same and other languages. We evaluate our approach using the challenging task of German oral history interviews, where we achieve a relative reduction of the word error rate by more than 30% compared to a model trained from scratch only on the target domain, and 6-7% relative compared to a model trained robustly on 1000 hours of same-language out-of-domain training data.

eess.AS↗

arXiv2020

NAT: Noise-Aware Training for Robust Neural Sequence Labeling

Sequence labeling systems should perform reliably not only under ideal conditions but also with corrupted inputs - as these systems often process user-generated text or follow an error-prone upstream component. To this end, we formulate the noisy sequence labeling problem, where the input may undergo an unknown noising process and propose two Noise-Aware Training (NAT) objectives that improve robustness of sequence labeling performed on perturbed input: Our data augmentation method trains a neural model using a mixture of clean and noisy samples, whereas our stability training algorithm encourages the model to create a noise-invariant latent representation. We employ a vanilla noise model at training time. For evaluation, we use both the original data and its variants perturbed with real OCR errors and misspellings. Extensive experiments on English and German named entity recognition benchmarks confirmed that NAT consistently improved robustness of popular sequence labeling models, preserving accuracy on the original input. We make our code and data publicly available for the research community.

cs.CL↗

arXiv2020

Stillleben: Realistic Scene Synthesis for Deep Learning in Robotics

Training data is the key ingredient for deep learning approaches, but difficult to obtain for the specialized domains often encountered in robotics. We describe a synthesis pipeline capable of producing training data for cluttered scene perception tasks such as semantic segmentation, object detection, and correspondence or pose estimation. Our approach arranges object meshes in physically realistic, dense scenes using physics simulation. The arranged scenes are rendered using high-quality rasterization with randomized appearance and material parameters. Noise and other transformations introduced by the camera sensors are simulated. Our pipeline can be run online during training of a deep neural network, yielding applications in life-long learning and in iterative render-and-compare approaches. We demonstrate the usability by learning semantic segmentation on the challenging YCB-Video dataset without actually using any training frames, where our method achieves performance comparable to a conventionally trained model. Additionally, we show successful application in a real-world regrasping system.

cs.CV↗

arXiv2020

Motion Segmentation using Frequency Domain Transformer Networks

Self-supervised prediction is a powerful mechanism to learn representations that capture the underlying structure of the data. Despite recent progress, the self-supervised video prediction task is still challenging. One of the critical factors that make the task hard is motion segmentation, which is segmenting individual objects and the background and estimating their motion separately. In video prediction, the shape, appearance, and transformation of each object should be understood only by predicting the next frame in pixel space. To address this task, we propose a novel end-to-end learnable architecture that predicts the next frame by modeling foreground and background separately while simultaneously estimating and predicting the foreground motion using Frequency Domain Transformer Networks. Experimental evaluations show that this yields interpretable representations and that our approach can outperform some widely used video prediction methods like Video Ladder Network and Predictive Gated Pyramids on synthetic data.

cs.CV↗

arXiv2020

Visual Descriptor Learning from Monocular Video

Correspondence estimation is one of the most widely researched and yet only partially solved area of computer vision with many applications in tracking, mapping, recognition of objects and environment. In this paper, we propose a novel way to estimate dense correspondence on an RGB image where visual descriptors are learned from video examples by training a fully convolutional network. Most deep learning methods solve this by training the network with a large set of expensive labeled data or perform labeling through strong 3D generative models using RGB-D videos. Our method learns from RGB videos using contrastive loss, where relative labeling is estimated from optical flow. We demonstrate the functionality in a quantitative analysis on rendered videos, where ground truth information is available. Not only does the method perform well on test data with the same background, it also generalizes to situations with a new background. The descriptors learned are unique and the representations determined by the network are global. We further show the applicability of the method to real-world videos.

cs.CV↗

arXiv2020

Beyond Photometric Consistency: Gradient-based Dissimilarity for Improving Visual Odometry and Stereo Matching

Pose estimation and map building are central ingredients of autonomous robots and typically rely on the registration of sensor data. In this paper, we investigate a new metric for registering images that builds upon on the idea of the photometric error. Our approach combines a gradient orientation-based metric with a magnitude-dependent scaling term. We integrate both into stereo estimation as well as visual odometry systems and show clear benefits for typical disparity and direct image registration tasks when using our proposed metric. Our experimental evaluation indicats that our metric leads to more robust and more accurate estimates of the scene depth as well as camera trajectory. Thus, the metric improves camera pose estimation and in turn the mapping capabilities of mobile robots. We believe that a series of existing visual odometry and visual SLAM systems can benefit from the findings reported in this paper.

cs.CV↗

arXiv2020

3D U-Net for Segmentation of Plant Root MRI Images in Super-Resolution

Magnetic resonance imaging (MRI) enables plant scientists to non-invasively study root system development and root-soil interaction. Challenging recording conditions, such as low resolution and a high level of noise hamper the performance of traditional root extraction algorithms, though. We propose to increase signal-to-noise ratio and resolution by segmenting the scanned volumes into root and soil in super-resolution using a 3D U-Net. Tests on real data show that the trained network is capable to detect most roots successfully and even finds roots that were missed by human annotators. Our experiments show that the segmentation performance can be further improved with modifications of the loss function.

cs.CV↗

arXiv2020

A VR System for Immersive Teleoperation and Live Exploration with a Mobile Robot

Applications like disaster management and industrial inspection often require experts to enter contaminated places. To circumvent the need for physical presence, it is desirable to generate a fully immersive individual live teleoperation experience. However, standard video-based approaches suffer from a limited degree of immersion and situation awareness due to the restriction to the camera view, which impacts the navigation. In this paper, we present a novel VR-based practical system for immersive robot teleoperation and scene exploration. While being operated through the scene, a robot captures RGB-D data that is streamed to a SLAM-based live multi-client telepresence system. Here, a global 3D model of the already captured scene parts is reconstructed and streamed to the individual remote user clients where the rendering for e.g. head-mounted display devices (HMDs) is performed. We introduce a novel lightweight robot client component which transmits robot-specific data and enables a quick integration into existing robotic systems. This way, in contrast to first-person exploration systems, the operators can explore and navigate in the remote site completely independent of the current position and view of the capturing robot, complementing traditional input devices for teleoperation. We provide a proof-of-concept implementation and demonstrate the capabilities as well as the performance of our system regarding interactive object measurements and bandwidth-efficient data streaming and visualization. Furthermore, we show its benefits over purely video-based teleoperation in a user study revealing a higher degree of situation awareness and a more precise navigation in challenging environments.

cs.HC↗