{"id":13701724,"url":"https://github.com/svenkreiss/socialforce","last_synced_at":"2025-04-07T08:26:34.220Z","repository":{"id":35190053,"uuid":"144574786","full_name":"svenkreiss/socialforce","owner":"svenkreiss","description":"Differentiable Social Force simulation with universal interaction potentials.","archived":false,"fork":false,"pushed_at":"2024-09-03T22:20:56.000Z","size":71925,"stargazers_count":124,"open_issues_count":3,"forks_count":42,"subscribers_count":4,"default_branch":"main","last_synced_at":"2024-10-13T00:10:16.465Z","etag":null,"topics":["differentiable-simulations","social-force-model"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/svenkreiss.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"citation.bib","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2018-08-13T12:10:04.000Z","updated_at":"2024-10-11T09:14:33.000Z","dependencies_parsed_at":"2022-08-08T06:00:56.757Z","dependency_job_id":"7ade3c35-d4a9-469b-9f50-878b67a07b5c","html_url":"https://github.com/svenkreiss/socialforce","commit_stats":{"total_commits":24,"total_committers":3,"mean_commits":8.0,"dds":0.08333333333333337,"last_synced_commit":"8d1fba69667f949175dc8575857fb4780afedb9a"},"previous_names":[],"tags_count":3,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/svenkreiss%2Fsocialforce","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/svenkreiss%2Fsocialforce/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/svenkreiss%2Fsocialforce/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/svenkreiss%2Fsocialforce/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/svenkreiss","download_url":"https://codeload.github.com/svenkreiss/socialforce/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247617388,"owners_count":20967598,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["differentiable-simulations","social-force-model"],"created_at":"2024-08-02T20:01:55.822Z","updated_at":"2025-04-07T08:26:34.200Z","avatar_url":"https://github.com/svenkreiss.png","language":"Jupyter Notebook","funding_links":[],"categories":["Jupyter Notebook","Tools"],"sub_categories":[],"readme":"[![Tests](https://github.com/svenkreiss/socialforce/actions/workflows/tests.yml/badge.svg)](https://github.com/svenkreiss/socialforce/actions/workflows/tests.yml)\u003cbr /\u003e\n[Executable Book documentation](https://www.svenkreiss.com/socialforce/).\u003cbr /\u003e\n[Deep Social Force (arXiv:2109.12081)](https://arxiv.org/abs/2109.12081).\n\n# Deep Social Force\n\n\u003e [__Deep Social Force__](https://arxiv.org/abs/2109.12081)\u003cbr /\u003e\n\u003e _[Sven Kreiss](https://www.svenkreiss.com)_, 2021.\n\u003e\n\u003e The Social Force model introduced by Helbing and Molnar in 1995\n\u003e is a cornerstone of pedestrian simulation. This paper\n\u003e introduces a differentiable simulation of the Social Force model\n\u003e where the assumptions on the shapes of interaction potentials are relaxed\n\u003e with the use of universal function approximators in the form of neural\n\u003e networks.\n\u003e Classical force-based pedestrian simulations suffer from unnatural\n\u003e locking behavior on head-on collision paths. In addition, they cannot\n\u003e model the bias\n\u003e of pedestrians to avoid each other on the right or left depending on\n\u003e the geographic region.\n\u003e My experiments with more general interaction potentials show that\n\u003e potentials with a sharp tip in the front avoid\n\u003e locking. In addition, asymmetric interaction potentials lead to a left or right\n\u003e bias when pedestrians avoid each other.\n\n\n# Install and Run\n\n```sh\n# install from PyPI\npip install 'socialforce[dev,plot]'\n\n# or install from source\npip install -e '.[dev,plot]'\n\n# run linting and tests\npylint socialforce\npycodestyle socialforce\npytest tests/*.py\n```\n\n\n# Ped-Ped-Space Scenarios\n\n\u003cimg src=\"docs/separator.gif\" height=200 /\u003e\n\u003cimg src=\"docs/gate.gif\" height=200 /\u003e\n\nEmergent lane forming behavior with 30 and 60 pedestrians:\n\n\u003cimg src=\"docs/walkway_30.gif\" height=200 /\u003e\n\u003cimg src=\"docs/walkway_60.gif\" height=200 /\u003e\n\n\n# Download TrajNet++ Data\n\nThe [Executable Book](https://www.svenkreiss.com/socialforce/)\nrequires some real-world data for the TrajNet++ section.\nThis is how to download and unzip it to the right folder:\n\n```\nwget -q https://github.com/vita-epfl/trajnetplusplusdata/releases/download/v4.0/train.zip\nmkdir data-trajnet\nunzip train.zip -d data-trajnet\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsvenkreiss%2Fsocialforce","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsvenkreiss%2Fsocialforce","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsvenkreiss%2Fsocialforce/lists"}