5 results
Filters
Settings
Now showing1 - 5 of 5
- Some of the metrics are blocked by yourconsent settings
Item type:Research Data, Access status: with files , Robot Localization Failure Prediction DatasetThis repository contains a synthetic dataset designed for training and evaluating predictive localization monitoring models for autonomous mobile robots, specifically focusing on LiDAR-based particle filter localization (Adaptive Monte Carlo Localization, AMCL). The dataset is generated using NVIDIA Isaac Sim and includes 21 ROS 2 rosbags, capturing diverse scenarios with localization estimates, ground-truth poses, sensor data (LiDAR and odometry), and automatically labeled failure cases. The dataset is intended to support research in proactive fault detection for ground robots navigating in dynamic and challenging environments, as described in the paper "Synthetic Datasets for Data-Driven Localization Monitoring". The dataset comprises 417,185 labeled samples across 21 experiment runs, with a failure rate of 23.1% (96,315 failure instances and 320,870 nominal instances). Experiments were conducted in seven distinct environments: - Warehouse: A large, prebuilt environment with aisles, storage racks, and handling equipment, mimicking real-world warehouse settings. - Symmetric Maps (1–3): Three small-scale environments with symmetrical layouts to induce localization confusion due to repetitive structures. - Asymmetric Maps (1–3): Three small-scale environments with asymmetrical layouts for varied localization challenges. Each environment was tested under three obstacle configurations: - Dynamic Only: 25 spherical obstacles (representing humans, robots, or industrial trucks) with randomized trajectories. - Static Only: Manually placed static obstacles (cubes) not included in the navigational map. - Combined (Dynamic + Static): Both dynamic and static obstacles.Data Type: Simulation Data41 78 - Some of the metrics are blocked by yourconsent settings
Item type:Research Data, Access status: with files , Mobile Robot Campus Dataset (MRCD)(2025-07-28); ; ; ; The Mobile Robot Campus Dataset (MRCD) was recorded on the TU Hamburg campus using "Laura," a mobile robot platform equipped with high-end sensors including LiDAR, stereo cameras, IMU, and RTK-GNSS. The dataset captures over 1 hour of real-world driving across 2.9 km of diverse pedestrian environments featuring vegetation, cobblestones, elevation changes, and urban structures. With precise calibration, anonymized visual data, and high-frequency sensor streams, MRCD is ideal for benchmarking SLAM, navigation, and perception algorithms. Ground truth is provided through continuous-time LiDAR registration against a high-resolution 3D map of the environment.Data Type: Dataset ; Data Type: Recorded Data325 1231 - Some of the metrics are blocked by yourconsent settings
Item type:Research Data, Access status: with files , 3D Point Cloud of the Main Campus of Hamburg University of Technology (5 cm subsampled)Point cloud file (e57) of the main campus of Hamburg University of Technology containing intensity and color information for 125 separate scans.Data Type: Dataset295 153 - Some of the metrics are blocked by yourconsent settings
Item type:Research Data, Access status: with files , PalLoc6D - Estimating the Pose of a Euro Pallet with an RGB Camera based on Synthetic Training Data(2022-08-26); ; ; ; PalLoc6D contains 50 000 synthetically generated images of a photorealistic pallet in a domain-radomized environment. PalLoc6D includes annotations of the pallets' 6D pose. The data was created using the NVIDIA Dataset Synthesizer (NDDS, https://github.com/NVIDIA/Dataset_Synthesizer). Additionally, a photorealistic 3D model of a Euro pallet is provided. PalLoc6D can be used to train neural networks for RGB camera-based 6D pallet pose estimation, such as Nvidia's "Deep Object Pose Estimation" (DOPE, https://github.com/NVlabs/Deep_Object_Pose). Furthermore, the weights of the DOPE algorithm, trained with the annotated images are included in PalLoc6D to allow a quick start for experimenting with 6D pose estimation. PalLoc6D was published as part of the paper "Estimating the Pose of a Euro Pallet with an RGB Camera based on Synthetic Training Data", which was presented at the WGTL Fachkolloquium 2022 in Bremen and will be subsequently published in the Logistics Journal. The purpose, creation, and validation of the dataset are further elaborated in the publication. Paper abstract: "Estimating the pose of a pallet and other logistics objects is crucial for various use cases, such as automatized material handling or tracking. Innovations in computer vision, computing power, and machine learning open up new opportunities for device-free localization based on cameras and neural networks. Large image datasets with annotated poses are required for training the network. Manual annotation, especially of 6D poses, is an extremely labor-intensive process. Hence, newer approaches often leverage synthetic training data to automatize the process of generating annotated image datasets. In this work, the generation of synthetic training data for 6D pose estimation of pallets is presented. The data is then used to train the Deep Object Pose Estimation (DOPE) algorithm. The experimental validation of the algorithm proves that the 6D pose estimation of a standardized Euro pallet with a Red-Green-Blue (RGB) camera is feasible. The comparison of the results from three varying datasets under different lighting conditions shows the relevance of an appropriate dataset design to achieve an accurate and robust localization. The quantitative evaluation shows an average position error of less than 20 cm for the preferred dataset. The validated training dataset and a photorealistic model of a Euro pallet are publicly provided."Data Type: Dataset1348 2889 - Some of the metrics are blocked by yourconsent settings
Item type:Research Data, Access status: with files , Measured data for "A metrological and application-related comparison of six consumer grade stereo depth cameras for the use in robotics"Data measured for the paper "A metrological and application-related comparison of six consumer grade stereo depth cameras for the use in robotics" ## Structure Each directory is archived in tar archives, which are compressed with gzip. The directories / archive files contain: - 00: results in .csv and images of the first recorded frame with projected target - 01-06: measured data: depth and rgb stream as .avi, data as numpy arrays ## Data format - data files contain intrinsic and extrinsic parameters as well as depth data in 'data' array - each 'data' array in the recorded ziped numpy files has the dimension [i,j,k,3] - i: number of frames; j: x-resolution; k: y-resolution; 3: x,y,z-components; - the saved format is therefore not the usual point cloud format but the last layer [i,:,:,2] represents the depth image ## File names - recorded data is named log_<camera>_<experiment number>_<file type> - experiment numbers: - 1: rectangle target, normal light, 0 degree, 1m - 2: rectangle target, normal light, 0 degree, 2m - 3: rectangle target, normal light, 0 degree, 3m - 4: rectangle target, normal light, 0 degree, 4m - 5: rectangle target, normal light, 0 degree, 5m - 6: rectangle target, dark light, 0 degree, 2m - 7: sphere target, normal light, 0 degree, 1m - 8: sphere target, normal light, 0 degree, 2m - 9: sphere target, normal light, 0 degree, 3m - 10: sphere target, dark light, 0 degree, 2m - 11: rectangle target (shiny), normal light, 0 degree, 2m - 12: rectangle target, normal light, 20 degree, 2m - 13: rectangle target, normal light, 40 degree, 2m - 14: rectangle target, normal light, 60 degree, 2m - 15: box target, normal light, 1mData Type: Dataset360 213