Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
18
datasets available to search
ShareScore release 0.9.0
Dataset results
18 results for “Collision Avoidance”
Synthetic Collision Dataset for Spacecraft Collision Avoidance
<p>This dataset is intended to be used as a banchmark for testing collision avoidance strategies.</p> <p>It is made of 21000000 relative geometries between LEO space objects, 1000 of which are true collision (miss-distance smaller than combined hard body radius).<br>These relative geometries are expressed as target and chaser 6-dimensional state vectors (cartesian coordinates) at time of closest approach.</p> <p>The relative geometry of the encounters are statistically matched to the ESA's Kelvins dataset for the collision avoidance challenge through statistical fitting methods.</p> <p>The collision proportion is tuned to reflect a 1year mission in LEO orbit with an a-priori collision probability of 1e-3 (yearly) and a 21 collision warnings per year.</p> <p>*<em><strong> Implementation Description *</strong></em></p> <p>The dataset is made of a series of .mat files storing the following variables:</p> <div> <ul> <li>'rv_t', target's cartesian state at TCA (km, km/s, in ECI) 6xN vector</li> <li>'rv_c', chaser's cartesian state at TCA (km, km/s, in ECI) 6xN vector </li> <li>'Ct', target's position covariance matrix at TCA (km^2, in target's RTN at TCA) 3x3xN </li> <li>'Cc', chaser's position covariance matrix at TCA (km^2, in chaser's RTN at TCA) 3x3xN </li> <li>'Rc', combined hard body radius (m) 1xN</li> <li>'CollFlag', logic value of collision 1xN (0: no-collision, 1: collision)</li> <li>'missDistance', miss distance at TCA (km) Nx1</li> </ul> <p>The name of the .mat file is formatted as:</p> <p>batch_<batch start index>.mat</p> <p>Each batch file has a maximum dimension of N = 1e5.</p> </div>
iCub Joint Space Self-Collision Avoidance [Data & Code]
<p>These data files containg code sources for dataset creation & model learning (Joint-Space-SCA.zip) and collected synthetic dataset of free & collided postures for humanoid robot iCub (raw_binary_data.zip). Follow the Readme.MD files to launch the code if needed.</p><p>Corresponding Git repo: https://github.com/epfl-lasa/Joint-Space-SCA</p><p> </p>
Data and code for Zheng et al. Contrasting coloured ventral wings are a visual collision avoidance signal in birds
<p>This repository contains codes and data for Zheng et al. Contrasting coloured ventral wings are a visual collision avoidance signal in birds. We have three folders, each containing one of the three datasets of contrast scores of avian ventral wings. These include the mean manual contrast ventral wing scores for 1780 species, a subset of 1745 diurnal species, 648 species with high-resolution museum ventral images, and the mean Root-Mean-Square (RMS) contrast ventral wing scores for the same 648 species. We tested the collision avoidance hypothesis for each dataset by assessing the relationships between the contrast scores and ecological traits. We used the Bayesian Generalized Linear Mixed Models in MCMCglmm with considering the phylogenetic relatedness among species and the uncertainties of 100 phylogenetic trees (downloaded in birdtree.org). We included body mass, flock size, coloniality (colonial vs. non-colonial breeding species), activity time (nocturnal vs. diurnal), the number of sympatric predators, and the interaction between coloniality and body mass as the predictors. In each folder, we included four files, including an R source file, a dataset containing the contrast scores and the ecological traits of the corresponding species, and a tree file containing 100 randomly sampled phylogenetic trees among these species. See the Methods of the paper for detail. </p>
Dataset for "On a Collision Course: Unveiling Wireless Attacks to the Aircraft Traffic Collision Avoidance System (TCAS)"
<p>The dataset associated with "On a Collision Course: Unveiling Wireless Attacks to the Aircraft Traffic Collision Avoidance System (TCAS)"</p>
Robot trajectory data for "Biohybrid Fly-Robot Interface system performs active collision avoidance"
<p>This dataset includes the videos of the trajectories of the biohybrid robot (Fly-Robot Interface), performing collision avoidance at the patterned wall corners (90 and 60 degrees). A python script for the manual tracking is also attached, as well as the processed coordinates of each individual robot trajectory, where two tracking markers were chosen on the front-left and front-right corners of the robot.</p> <p>Serial Number <20: the videos at 90-degree wall corner</p> <p>Serial Number >20: the videos at 60-degree wall corner</p>
Vector Field Histogram (VFH) video results for vineyard navigation and collision avoidance
<p><strong>Video Results for PhD Thesis</strong>: This video demonstrates the implementation of Vector Field Histogram (VFH) navigation for collision avoidance within crop rows. The simulation is conducted in Gazebo, utilizing a Husky robot to showcase efficient path planning and obstacle avoidance in an agricultural setting.</p>
Decentralized Motion Planning with Collision Avoidance for a Team of UAVs under High Level Goals
<p>The video illustrates simulation and experimental results of a team of unmanned aerial vehicles executing Linear Temporal Logic (LTL) tasks. More specifically, given a certain LTL task over predefined regions of interest, each agent derives a high-level plan that satisfies the given task. Then, it executes the plan using a continuous controller that is based on decentralized navigation functions, which also guarantee inter-agent collision avoidance. The video shows one simulation and two experimental scenarios.</p>
NL, Advanced Driving, Cooperative Collision Avoidance
<p>Use Case Category: <strong>Advanced Driving</strong><br> User Story: <strong>Cooperative Collision Avoidance</strong><br> Location: Dutch (NL) trial site</p> <p>According to 3GPP TS 22.186 R16, Advanced Driving “enables semi-automated or fully-automated driving. Longer inter-vehicle distance is assumed. Each vehicle and/or Road Side Unit (RSU) shares data obtained from its local sensors with vehicles in proximity, thus allowing vehicles to coordinate their trajectories or manoeuvres. In addition, each vehicle shares its driving intention with vehicles in proximity. The benefits of this use case group are safer traveling, collision avoidance, and improved traffic efficiency”.</p> <p>User Story: Cooperative Collision Avoidance</p> <p>This 5G-MOBIX Service will take place at an Intelligent Intersection of the A270 Motorway - N270 Highway between Eindhoven and Helmond (NL). This site has been used for several tests and trials on Automated Driving and/or C-ITC. In 5G-Mobix the current facilities to support CCAM will be upgraded to work on a 5G mobile connectivity platform.</p> <p>Cooperative Collision Avoidance (CoCA) targets to solve a challenging traffic situation on the motorway/highway environment. The Vehicle A (‘ego vehicle’, a foreign registered vehicle driving on the Dutch motorway/highway network) will make itself ‘visible’ and known to other traffic participants and to the infrastructure for Edge Computing through C-ITS messaging via 5G networks, and Cellular V2X (C-V2X) communication i.e. either LTE-based or 5G NR-based V2X. The Vehicle B (‘alter vehicle’, a Dutch registered vehicle) will submit similar information of its presence, speed and direction of movement to ‘ego vehicle’ and infrastructure as described above. Hence the ‘Edge Cloud’ infrastructure facilities can perform calculations and offload from the vehicles to the infrastructure and then return the suggested manoeuvring messages.</p> <p>At the intersection of A270-N270 roads, the most critical path for cooperative automated driving is the left turn over the direct traffic flow that has a right-of-way for driving in highly automated mode through the intersection. The ego vehicle that is approaching the intersection must be able to clear itself safely across the motorway/highway lanes to join the main traffic flow. When deemed necessary, the ego vehicle need to safely stop autonomously before crossing the motorway/highway and start driving only when its calculated trajectory path is safe and clear for autonomous manoeuvring. For this purpose, the ego vehicle must be able to utilise both its own trajectory and timing data and information from the road side sensors as well as the alter vehicle’s precise location, intended direction and speed to avoid collision.</p> <p>The target in 5G-Mobix is time-critical message exchange between CAVs using 5G technologies. These technologies include:</p> <p>· C-V2X based on LTE or 5G NR for direct communication between vehicles and 5G networks<br> · 5G NR enabled base stations (gNB)<br> · 5G core technologies like Edge Computing (‘Edge Cloud ‘) and Slicing<br> · Ultra-Reliable Low Latency Communication (uRLLC) to support time-critical communication.</p> <p>Currently the CAVs are capable to support direct communication between vehicles via ITS-G5 based solutions and/or 4G network-based communication for C-ITS message exchange. The ultimate solution is to use hybrid in-vehicle communication units that can communicate both directly between vehicles and over the network using 5G NR-V2X.</p>
Online tree-based planning for active spacecraft fault estimation and collision avoidance
Open the record for dataset details and reuse information.
Collision Avoidance Challenge dataset
<p>The Collision Avoidance Challenge dataset is the official dataset used during the <strong>ESA's Kelvins</strong> <strong>competition for "Collision Avoidance Challenge"</strong>. The dataset is a collection of Conjunction Data Messages (CDMs) received by ESA from 2015 to 2019. The CDMs have been anonymised for distribution. The initial raw data, as well as the labels that were kept private during the competition, are also released.<br> ESA thanks the US Space Surveillance Network for the provision of surveillance data supporting safe operations of ESA’s spacecraft. In addition, we are grateful to the agreement which allows to publicly release the current dataset.</p> <p>The dataset is represented as a table, where each row corresponds to a single CDM, and each CDM contains 103 recorded characteristics/features. There are thus 103 columns, which are described in the competition pages. The dataset is made of several unique collision/close approach events, which are identified in the <code>event_id</code> column. In turn, each collision event is made of several CDMs recorded over time. Therefore, a single collision event can be thought of as a times series of CDMs. From these CDMs, for every collision event, we are interested in predicting the final risk which is computed in the last CDM of the time series (i.e. the risk value in the last row of each collision event).</p> <p>For a detailed description on the challenge and this dataset, visit <a href="https://kelvins.esa.int/collision-avoidance-challenge/data/">kelvins.esa.int/collision-avoidance-challenge/data/</a>.</p> <p>The paper describing the competition setup and result can be found at <a href="http://arxiv.org/pdf/2008.03069.pdf">arxiv.org/pdf/2008.03069.pdf</a>.</p>
Data from: Harbour seals avoid tidal turbine noise: implications for collision risk
1. Tidal stream energy converters (turbines) are currently being installed in tidally energetic coastal sites. However, there is currently a high level of uncertainty surrounding the potential environmental impacts on marine mammals. This is a key consenting risk to commercial introduction of tidal energy technology. Concerns derive primarily from the potential for injury to marine mammals through collisions with moving components of turbines. To understand the nature of this risk, information on how animals respond to tidal turbines is urgently required. 2. We measured the behaviour of harbour seals in response to acoustic playbacks of simulated tidal turbine sound within a narrow coastal channel subject to strong, tidally induced currents. This was carried out using data from animal-borne GPS tags and shore-based observations, which were analysed to quantify behavioural responses to the turbine sound. 3. Results showed that the playback state (silent control or turbine signal) was not a significant predictor of the overall number of seals sighted within the channel. 4. However, there was a localised impact of the turbine signal; tagged harbour seals exhibited significant spatial avoidance of the sound which resulted in a reduction in the usage by seals of between 11 and 41% at the playback location. The significant decline in usage extended to 500 m from the playback location at which usage decreased by between 1 and 9% during playback. 5. Synthesis and applications: This study provides important information for policy makers looking to assess the potential impacts of tidal turbines and advise on development of the tidal energy industry. Results showing that seals avoid tidal turbine sound suggest that a proportion of seals encountering tidal turbines will exhibit behavioural responses resulting in avoidance of physical injury; in practice, the empirical changes in usage can be used directly as avoidance rates when using collision risk models to predict the effects of tidal turbines on seals. There is now a clear need to measure how marine mammals behave in response to actual operating tidal turbines in the long term to learn whether marine mammals and tidal turbines can co-exist safely at the scales currently envisaged for the industry.
Pedestrian movement trajectories and collision avoidance strategies in interweaving pedestrian flow experiment
<p>The mechanisms of Collision Avoidance(CA) behaviors in interweaving pedestrian flow movements are important for pedestrian space planning and emergency management but not well understood yet. A series of controlled interweaving pedestrian flow experiments with different pedestrian flow densities are carried out to investigate the CA behaviors, especially CA strategy choices. This dataset consists the movement trajectory and the CA strategy choices information of the participants in the experiment and was provided as a supplementary material of a journal paper submitted to "Royal Society Open Science".</p> <p>All these experiments were conducted in an outdoor public square in the campus of Wuhan University of Technology. A total of 40 students aged 18-23 years participated these experiments. The experiment includes three "groups", representing low, medium and high density levels of interweaving pedestrian flow. Each group of experiment was repeated three times to increase the reliability of the observations. Therefore, there are totally 9 data files in this dataset, each file contains the data of one experiment.</p> <p>After the experiment, the PeTrack software was used to extract pedestrians' trajectories by identifying and tracking the coordinates of participants' heads in the video records. This dataset provides the extracted trajectories of all the pedestrians in each experiment. Trajectory of each RP is marked as Collision Avoidance Segment (CAS) and Normal Walking Segment (NWS). During the CAS, pedestrians have shown collision avoidance strategies. Four types of CA strategies, including "deceleration", "acceleration", "detour", and "stop" are manually identified in these experiments and marked in the dataset. More details of the data and the results of the study could be found in the associated journal paper. This dataset could be useful for researchers in this field.</p>
Pedestrian movement trajectories and collision avoidance strategies in interweaving pedestrian flow experiment
Open the record for dataset details and reuse information.
Data from: Harbour seals avoid tidal turbine noise: implications for collision risk
Open the record for dataset details and reuse information.
Video of on-ground experiments: Design and Implementation of Auto Car Driving System With Collision Avoidance
<p>The project presents designing and manufacturing the hardware and software of a low-cost robotic system, which can be installed into any petrol car with an automatic gearbox, giving the ability to a car to be driverless. <br> This video is from several on-ground experiments were performed during the last year.</p>
AgRob Collision Avoidance Simulation Trial
<p>Two videos testing<a href="https://gitlab.inesctec.pt/agrob/agrob_pp/-/tree/master/agrob_path_planning/Collision_avoidance"> AgRob Collision Avoidance</a> system on steep slope vineyard. One of the videos does not have the feature activated.</p> <p> </p> <p> </p>
A low Smc flux avoids collisions and facilitates chromosome organization in B. subtilis
GEO Series GSE163573. Bacillus subtilis. 109 samples. Type: Genome binding/occupancy profiling by high throughput sequencing; Other.
Video demonstrations of optimal collision avoidance in head-on encounter between UAV and static/dynamic intruder aircraft
<p>Video demonstrations of optimal collision avoidance in head-on encounter between UAV and static/dynamic intruder aircraft. See paper titled "Optimal Intruder Collision Avoidance for UAVs via Waypoint Tracking" in the conference proceedings of EuroGNC 2022.</p>
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.