arXiv subjects

Sven Behnke

Publications and source records attributed to Sven Behnke.

At least 91 records · Page 5Linked to original sources

arXiv2023

RoboCup 2022 AdultSize Winner NimbRo: Upgraded Perception, Capture Steps Gait and Phase-based In-walk Kicks

Beating the human world champions by 2050 is an ambitious goal of the Humanoid League that provides a strong incentive for RoboCup teams to further improve and develop their systems. In this paper, we present upgrades of our system which enabled our team NimbRo to win the Soccer Tournament, the Drop-in Games, and the Technical Challenges in the Humanoid AdultSize League of RoboCup 2022. Strong performance in these competitions resulted in the Best Humanoid award in the Humanoid League. The mentioned upgrades include: hardware upgrade of the vision module, balanced walking with Capture Steps, and the introduction of phase-based in-walk kicks.

cs.RO↗

arXiv2023

Rendering the Directional TSDF for Tracking and Multi-Sensor Registration with Point-To-Plane Scale ICP

Dense real-time tracking and mapping from RGB-D images is an important tool for many robotic applications, such as navigation and manipulation. The recently presented Directional Truncated Signed Distance Function (DTSDF) is an augmentation of the regular TSDF that shows potential for more coherent maps and improved tracking performance. In this work, we present methods for rendering depth- and color images from the DTSDF, making it a true drop-in replacement for the regular TSDF in established trackers. We evaluate the algorithm on well-established datasets and observe that our method improves tracking performance and increases re-usability of mapped scenes. Furthermore, we add color integration which notably improves color-correctness at adjacent surfaces. Our novel formulation of combined ICP with frame-to-keyframe photometric error minimization further improves tracking results. Lastly, we introduce Sim3 point-to-plane ICP for refining pose priors in a multi-sensor scenario with different scale factors.

cs.CV↗

arXiv2023

Bimanual Telemanipulation with Force and Haptic Feedback through an Anthropomorphic Avatar System

Robotic teleoperation is a key technology for a wide variety of applications. It allows sending robots instead of humans in remote, possibly dangerous locations while still using the human brain with its enormous knowledge and creativity, especially for solving unexpected problems. A main challenge in teleoperation consists of providing enough feedback to the human operator for situation awareness and thus create full immersion, as well as offering the operator suitable control interfaces to achieve efficient and robust task fulfillment. We present a bimanual telemanipulation system consisting of an anthropomorphic avatar robot and an operator station providing force and haptic feedback to the human operator. The avatar arms are controlled in Cartesian space with a direct mapping of the operator movements. The measured forces and torques on the avatar side are haptically displayed to the operator. We developed a predictive avatar model for limit avoidance which runs on the operator side, ensuring low latency. The system was successfully evaluated during the ANA Avatar XPRIZE competition semifinals. In addition, we performed in lab experiments and carried out a small user study with mostly untrained operators.

cs.RO↗

arXiv2022

Lessons from Robot-Assisted Disaster Response Deployments by the German Rescue Robotics Center Task Force

Earthquakes, fire, and floods often cause structural collapses of buildings. The inspection of damaged buildings poses a high risk for emergency forces or is even impossible, though. We present three recent selected missions of the Robotics Task Force of the German Rescue Robotics Center, where both ground and aerial robots were used to explore destroyed buildings. We describe and reflect the missions as well as the lessons learned that have resulted from them. In order to make robots from research laboratories fit for real operations, realistic test environments were set up for outdoor and indoor use and tested in regular exercises by researchers and emergency forces. Based on this experience, the robots and their control software were significantly improved. Furthermore, top teams of researchers and first responders were formed, each with realistic assessments of the operational and practical suitability of robotic systems.

cs.RO↗

arXiv2022

Accelerating Interactive Human-like Manipulation Learning with GPU-based Simulation and High-quality Demonstrations

Dexterous manipulation with anthropomorphic robot hands remains a challenging problem in robotics because of the high-dimensional state and action spaces and complex contacts. Nevertheless, skillful closed-loop manipulation is required to enable humanoid robots to operate in unstructured real-world environments. Reinforcement learning (RL) has traditionally imposed enormous interaction data requirements for optimizing such complex control problems. We introduce a new framework that leverages recent advances in GPU-based simulation along with the strength of imitation learning in guiding policy search towards promising behaviors to make RL training feasible in these domains. To this end, we present an immersive virtual reality teleoperation interface designed for interactive human-like manipulation on contact rich tasks and a suite of manipulation environments inspired by tasks of daily living. Finally, we demonstrate the complementary strengths of massively parallel RL and imitation learning, yielding robust and natural behaviors. Videos of trained policies, our source code, and the collected demonstration datasets are available at https://maltemosbach.github.io/interactive_ human_like_manipulation/.

cs.RO↗

arXiv2022

Object-level 3D Semantic Mapping using a Network of Smart Edge Sensors

Autonomous robots that interact with their environment require a detailed semantic scene model. For this, volumetric semantic maps are frequently used. The scene understanding can further be improved by including object-level information in the map. In this work, we extend a multi-view 3D semantic mapping system consisting of a network of distributed smart edge sensors with object-level information, to enable downstream tasks that need object-level input. Objects are represented in the map via their 3D mesh model or as an object-centric volumetric sub-map that can model arbitrary object geometry when no detailed 3D model is available. We propose a keypoint-based approach to estimate object poses via PnP and refinement via ICP alignment of the 3D object model with the observed point cloud segments. Object instances are tracked to integrate observations over time and to be robust against temporary occlusions. Our method is evaluated on the public Behave dataset where it shows pose estimation accuracy within a few centimeters and in real-world experiments with the sensor network in a challenging lab environment where multiple chairs and a table are tracked through the scene online, in real time even under high occlusions.

cs.CV↗

arXiv2022

State Estimation for Hybrid Locomotion of Driving-Stepping Quadrupeds

Fast and versatile locomotion can be achieved with wheeled quadruped robots that drive quickly on flat terrain, but are also able to overcome challenging terrain by adapting their body pose and by making steps. In this paper, we present a state estimation approach for four-legged robots with non-steerable wheels that enables hybrid driving-stepping locomotion capabilities. We formulate a Kalman Filter (KF) for state estimation that integrates driven wheels into the filter equations and estimates the robot state (position and velocity) as well as the contribution of driving with wheels to the above state. Our estimation approach allows us to use the control framework of the Mini Cheetah quadruped robot with minor modifications. We tested our approach on this robot that we augmented with actively driven wheels in simulation and in the real world. The experimental results are available at https://www.ais.uni-bonn.de/%7Ehosseini/se-dsq .

cs.RO↗

arXiv2022

Learning Implicit Probability Distribution Functions for Symmetric Orientation Estimation from RGB Images Without Pose Labels

Object pose estimation is a necessary prerequisite for autonomous robotic manipulation, but the presence of symmetry increases the complexity of the pose estimation task. Existing methods for object pose estimation output a single 6D pose. Thus, they lack the ability to reason about symmetries. Lately, modeling object orientation as a non-parametric probability distribution on the SO(3) manifold by neural networks has shown impressive results. However, acquiring large-scale datasets to train pose estimation models remains a bottleneck. To address this limitation, we introduce an automatic pose labeling scheme. Given RGB-D images without object pose annotations and 3D object models, we design a two-stage pipeline consisting of point cloud registration and render-and-compare validation to generate multiple symmetrical pseudo-ground-truth pose labels for each image. Using the generated pose labels, we train an ImplicitPDF model to estimate the likelihood of an orientation hypothesis given an RGB image. An efficient hierarchical sampling of the SO(3) manifold enables tractable generation of the complete set of symmetries at multiple resolutions. During inference, the most likely orientation of the target object is estimated using gradient ascent. We evaluate the proposed automatic pose labeling scheme and the ImplicitPDF model on a photorealistic dataset and the T-Less dataset, demonstrating the advantages of the proposed method.

cs.CV↗

arXiv2022

Efficient Representations of Object Geometry for Reinforcement Learning of Interactive Grasping Policies

Grasping objects of different shapes and sizes - a foundational, effortless skill for humans - remains a challenging task in robotics. Although model-based approaches can predict stable grasp configurations for known object models, they struggle to generalize to novel objects and often operate in a non-interactive open-loop manner. In this work, we present a reinforcement learning framework that learns the interactive grasping of various geometrically distinct real-world objects by continuously controlling an anthropomorphic robotic hand. We explore several explicit representations of object geometry as input to the policy. Moreover, we propose to inform the policy implicitly through signed distances and show that this is naturally suited to guide the search through a shaped reward component. Finally, we demonstrate that the proposed framework is able to learn even in more challenging conditions, such as targeted grasping from a cluttered bin. Necessary pre-grasping behaviors such as object reorientation and utilization of environmental constraints emerge in this case. Videos of learned interactive policies are available at https://maltemosbach.github. io/geometry_aware_grasping_policies.

cs.RO↗

arXiv2022

MSPred: Video Prediction at Multiple Spatio-Temporal Scales with Hierarchical Recurrent Networks

Autonomous systems not only need to understand their current environment, but should also be able to predict future actions conditioned on past states, for instance based on captured camera frames. However, existing models mainly focus on forecasting future video frames for short time-horizons, hence being of limited use for long-term action planning. We propose Multi-Scale Hierarchical Prediction (MSPred), a novel video prediction model able to simultaneously forecast future possible outcomes of different levels of granularity at different spatio-temporal scales. By combining spatial and temporal downsampling, MSPred efficiently predicts abstract representations such as human poses or locations over long time horizons, while still maintaining a competitive performance for video frame prediction. In our experiments, we demonstrate that MSPred accurately predicts future video frames as well as high-level representations (e.g. keypoints or semantics) on bin-picking and action recognition datasets, while consistently outperforming popular approaches for future frame prediction. Furthermore, we ablate different modules and design choices in MSPred, experimentally validating that combining features of different spatial and temporal granularity leads to a superior performance. Code and models to reproduce our experiments can be found in https://github.com/AIS-Bonn/MSPred.

cs.CV↗

arXiv2022

Real-Time Multi-Modal Semantic Fusion on Unmanned Aerial Vehicles with Label Propagation for Cross-Domain Adaptation

Unmanned aerial vehicles (UAVs) equipped with multiple complementary sensors have tremendous potential for fast autonomous or remote-controlled semantic scene analysis, e.g., for disaster examination. Here, we propose a UAV system for real-time semantic inference and fusion of multiple sensor modalities. Semantic segmentation of LiDAR scans and RGB images, as well as object detection on RGB and thermal images, run online onboard the UAV computer using lightweight CNN architectures and embedded inference accelerators. We follow a late fusion approach where semantic information from multiple sensor modalities augments 3D point clouds and image segmentation masks while also generating an allocentric semantic map. Label propagation on the semantic map allows for sensor-specific adaptation with cross-modality and cross-domain supervision. Our system provides augmented semantic images and point clouds with $\approx$ 9 Hz. We evaluate the integrated system in real-world experiments in an urban environment and at a disaster test site.

cs.CV↗

arXiv2022

Online Marker-free Extrinsic Camera Calibration using Person Keypoint Detections

Calibration of multi-camera systems, i.e. determining the relative poses between the cameras, is a prerequisite for many tasks in computer vision and robotics. Camera calibration is typically achieved using offline methods that use checkerboard calibration targets. These methods, however, often are cumbersome and lengthy, considering that a new calibration is required each time any camera pose changes. In this work, we propose a novel, marker-free online method for the extrinsic calibration of multiple smart edge sensors, relying solely on 2D human keypoint detections that are computed locally on the sensor boards from RGB camera images. Our method assumes the intrinsic camera parameters to be known and requires priming with a rough initial estimate of the camera poses. The person keypoint detections from multiple views are received at a central backend where they are synchronized, filtered, and assigned to person hypotheses. We use these person hypotheses to repeatedly solve optimization problems in the form of factor graphs. Given suitable observations of one or multiple persons traversing the scene, the estimated camera poses converge towards a coherent extrinsic calibration within a few minutes. We evaluate our approach in real-world settings and show that the calibration with our method achieves lower reprojection errors compared to a reference calibration generated by an offline method using a traditional calibration target.

cs.CV↗

arXiv2022

Autonomous Flight in Unknown GNSS-denied Environments for Disaster Examination

Micro aerial vehicles (MAVs) have high potential for information gathering tasks to support situation awareness in search and rescue scenarios. Manually controlling MAVs in such scenarios requires experienced pilots and is error-prone, especially in stressful situations of real emergencies. The conditions of disaster scenarios are also challenging for autonomous MAV systems. The environment is usually not known in advance and GNSS might not always be available. We present a system for autonomous MAV flights in unknown environments which does not rely on global positioning systems. The method is evaluated in multiple search and rescue scenarios and allows for safe autonomous flights, even when transitioning between indoor and outdoor areas.

cs.RO↗

arXiv2022

Predictive Angular Potential Field-based Obstacle Avoidance for Dynamic UAV Flights

In recent years, unmanned aerial vehicles (UAVs) are used for numerous inspection and video capture tasks. Manually controlling UAVs in the vicinity of obstacles is challenging, however, and poses a high risk of collisions. Even for autonomous flight, global navigation planning might be too slow to react to newly perceived obstacles. Disturbances such as wind might lead to deviations from the planned trajectories. In this work, we present a fast predictive obstacle avoidance method that does not depend on higher-level localization or mapping and maintains the dynamic flight capabilities of UAVs. It directly operates on LiDAR range images in real time and adjusts the current flight direction by computing angular potential fields within the range image. The velocity magnitude is subsequently determined based on a trajectory prediction and time-to-contact estimation. Our method is evaluated using Hardware-in-the-Loop simulations. It keeps the UAV at a safe distance to obstacles, while allowing higher flight velocities than previous reactive obstacle avoidance methods that directly operate on sensor data.

cs.RO↗

arXiv2022

Direct Centroidal Control for Balanced Humanoid Locomotion

We present an integrated approach to locomotion and balancing of humanoid robots based on direct centroidal control. Our method uses a five-mass description of a humanoid. It generates whole-body motions from desired foot trajectories and centroidal parameters of the robot. A set of simplified models is used to formulate general and intuitive control laws, which are then applied in real-time for estimating and regulating the center of mass position and orientation of the multibody's principal axes of inertia. The combination of proposed algorithms produces a stretched-leg gait with naturally looking upper body motions. As only a 6-axis IMU and joint encoders are necessary for the implementation, the portability between robots is high. Our method has been experimentally verified using an igus Humanoid Open Platform, demonstrating whole-body locomotion and push rejection capabilities.

cs.RO↗

arXiv2022

Neural Strands: Learning Hair Geometry and Appearance from Multi-View Images

We present Neural Strands, a novel learning framework for modeling accurate hair geometry and appearance from multi-view image inputs. The learned hair model can be rendered in real-time from any viewpoint with high-fidelity view-dependent effects. Our model achieves intuitive shape and style control unlike volumetric counterparts. To enable these properties, we propose a novel hair representation based on a neural scalp texture that encodes the geometry and appearance of individual strands at each texel location. Furthermore, we introduce a novel neural rendering framework based on rasterization of the learned hair strands. Our neural rendering is strand-accurate and anti-aliased, making the rendering view-consistent and photorealistic. Combining appearance with a multi-view geometric prior, we enable, for the first time, the joint learning of appearance and explicit hair geometry from a multi-view setup. We demonstrate the efficacy of our approach in terms of fidelity and efficiency for various hairstyles.

cs.CV↗

arXiv2022

Synthetic-to-Real Domain Adaptation using Contrastive Unpaired Translation

The usefulness of deep learning models in robotics is largely dependent on the availability of training data. Manual annotation of training data is often infeasible. Synthetic data is a viable alternative, but suffers from domain gap. We propose a multi-step method to obtain training data without manual annotation effort: From 3D object meshes, we generate images using a modern synthesis pipeline. We utilize a state-of-the-art image-to-image translation method to adapt the synthetic images to the real domain, minimizing the domain gap in a learned manner. The translation network is trained from unpaired images, i.e. just requires an un-annotated collection of real images. The generated and refined images can then be used to train deep learning models for a particular task. We also propose and evaluate extensions to the translation method that further increase performance, such as patch-based training, which shortens training time and increases global consistency. We evaluate our method and demonstrate its effectiveness on two robotic datasets. We finally give insight into the learned refinement operations.

cs.CV↗

arXiv2022

NeuralMVS: Bridging Multi-View Stereo and Novel View Synthesis

Multi-View Stereo (MVS) is a core task in 3D computer vision. With the surge of novel deep learning methods, learned MVS has surpassed the accuracy of classical approaches, but still relies on building a memory intensive dense cost volume. Novel View Synthesis (NVS) is a parallel line of research and has recently seen an increase in popularity with Neural Radiance Field (NeRF) models, which optimize a per scene radiance field. However, NeRF methods do not generalize to novel scenes and are slow to train and test. We propose to bridge the gap between these two methodologies with a novel network that can recover 3D scene geometry as a distance function, together with high-resolution color images. Our method uses only a sparse set of images as input and can generalize well to novel scenes. Additionally, we propose a coarse-to-fine sphere tracing approach in order to significantly increase speed. We show on various datasets that our method reaches comparable accuracy to per-scene optimized methods while being able to generalize and running significantly faster. We provide the source code at https://github.com/AIS-Bonn/neural_mvs

cs.CV↗