CausalOrca: An ORCA-based Diagnostic Dataset for Causally-aware Multi-agent Trajectory Prediction
CausalOrca is a synthetic diagnostic dataset created through controlled simulations. It is designed to provide annotations of ground-truth causal effects and fine-grained agent categories for social interactions in multi-agent scenarios. The dataset is constructed using a modified RVO2 simulator and...
Main Author: | |
---|---|
Format: | Dataset |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://zenodo.org/record/7973395 https://doi.org/10.5281/zenodo.7973395 |
id |
ftzenodo:oai:zenodo.org:7973395 |
---|---|
record_format |
openpolar |
spelling |
ftzenodo:oai:zenodo.org:7973395 2023-06-11T04:15:46+02:00 CausalOrca: An ORCA-based Diagnostic Dataset for Causally-aware Multi-agent Trajectory Prediction Anonymous 2023-05-26 https://zenodo.org/record/7973395 https://doi.org/10.5281/zenodo.7973395 eng eng doi:10.5281/zenodo.7973394 https://zenodo.org/record/7973395 https://doi.org/10.5281/zenodo.7973395 oai:zenodo.org:7973395 info:eu-repo/semantics/openAccess https://creativecommons.org/licenses/by/4.0/legalcode Social Causality Multi-agent Interactions Trajectory Prediction Motion Forecasting Crowd Navigation Causal Robustness Indirect Causal Effects Low-data Regimes Distribution Shifts Ground-truth Causal Effects Simulation-based Annotations info:eu-repo/semantics/other dataset 2023 ftzenodo https://doi.org/10.5281/zenodo.797339510.5281/zenodo.7973394 2023-05-30T23:05:31Z CausalOrca is a synthetic diagnostic dataset created through controlled simulations. It is designed to provide annotations of ground-truth causal effects and fine-grained agent categories for social interactions in multi-agent scenarios. The dataset is constructed using a modified RVO2 simulator and incorporates the ORCA optimization-based collision avoidance algorithm known for crowd simulation. With full control over scene configurations, the dataset enables the collection of motion behaviors in paired scenes before and after agent removal, generating a large set of counterfactual pairs with annotations of ground-truth causal effects. CausalOrca can serve as a valuable resource for studying and developing causally-aware neural representations of social interactions and trajectory prediction models. Please see the GitHub repository for a more detailed description of the dataset, including dataset statistics and documentation on how to use, visualize, and generate the data. Dataset Orca Zenodo |
institution |
Open Polar |
collection |
Zenodo |
op_collection_id |
ftzenodo |
language |
English |
topic |
Social Causality Multi-agent Interactions Trajectory Prediction Motion Forecasting Crowd Navigation Causal Robustness Indirect Causal Effects Low-data Regimes Distribution Shifts Ground-truth Causal Effects Simulation-based Annotations |
spellingShingle |
Social Causality Multi-agent Interactions Trajectory Prediction Motion Forecasting Crowd Navigation Causal Robustness Indirect Causal Effects Low-data Regimes Distribution Shifts Ground-truth Causal Effects Simulation-based Annotations Anonymous CausalOrca: An ORCA-based Diagnostic Dataset for Causally-aware Multi-agent Trajectory Prediction |
topic_facet |
Social Causality Multi-agent Interactions Trajectory Prediction Motion Forecasting Crowd Navigation Causal Robustness Indirect Causal Effects Low-data Regimes Distribution Shifts Ground-truth Causal Effects Simulation-based Annotations |
description |
CausalOrca is a synthetic diagnostic dataset created through controlled simulations. It is designed to provide annotations of ground-truth causal effects and fine-grained agent categories for social interactions in multi-agent scenarios. The dataset is constructed using a modified RVO2 simulator and incorporates the ORCA optimization-based collision avoidance algorithm known for crowd simulation. With full control over scene configurations, the dataset enables the collection of motion behaviors in paired scenes before and after agent removal, generating a large set of counterfactual pairs with annotations of ground-truth causal effects. CausalOrca can serve as a valuable resource for studying and developing causally-aware neural representations of social interactions and trajectory prediction models. Please see the GitHub repository for a more detailed description of the dataset, including dataset statistics and documentation on how to use, visualize, and generate the data. |
format |
Dataset |
author |
Anonymous |
author_facet |
Anonymous |
author_sort |
Anonymous |
title |
CausalOrca: An ORCA-based Diagnostic Dataset for Causally-aware Multi-agent Trajectory Prediction |
title_short |
CausalOrca: An ORCA-based Diagnostic Dataset for Causally-aware Multi-agent Trajectory Prediction |
title_full |
CausalOrca: An ORCA-based Diagnostic Dataset for Causally-aware Multi-agent Trajectory Prediction |
title_fullStr |
CausalOrca: An ORCA-based Diagnostic Dataset for Causally-aware Multi-agent Trajectory Prediction |
title_full_unstemmed |
CausalOrca: An ORCA-based Diagnostic Dataset for Causally-aware Multi-agent Trajectory Prediction |
title_sort |
causalorca: an orca-based diagnostic dataset for causally-aware multi-agent trajectory prediction |
publishDate |
2023 |
url |
https://zenodo.org/record/7973395 https://doi.org/10.5281/zenodo.7973395 |
genre |
Orca |
genre_facet |
Orca |
op_relation |
doi:10.5281/zenodo.7973394 https://zenodo.org/record/7973395 https://doi.org/10.5281/zenodo.7973395 oai:zenodo.org:7973395 |
op_rights |
info:eu-repo/semantics/openAccess https://creativecommons.org/licenses/by/4.0/legalcode |
op_doi |
https://doi.org/10.5281/zenodo.797339510.5281/zenodo.7973394 |
_version_ |
1768372867437690880 |