{"id":41015886,"url":"https://github.com/simon-schaefer/mantrap","last_synced_at":"2026-01-22T09:18:43.290Z","repository":{"id":41312326,"uuid":"213083933","full_name":"simon-schaefer/mantrap","owner":"simon-schaefer","description":"Leveraging Neural Network Gradients within Trajectory Optimization for Proactive Human-Robot Interactions","archived":false,"fork":false,"pushed_at":"2023-07-06T21:52:15.000Z","size":18829,"stargazers_count":13,"open_issues_count":1,"forks_count":6,"subscribers_count":4,"default_branch":"master","last_synced_at":"2024-03-19T14:00:57.222Z","etag":null,"topics":["pedestrian","trajectory-optimization","trajectron"],"latest_commit_sha":null,"homepage":"https://simon-schaefer.github.io/mantrap/","language":"Python","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/simon-schaefer.png","metadata":{"files":{"readme":"README.rst","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2019-10-05T23:19:58.000Z","updated_at":"2023-11-25T06:16:31.000Z","dependencies_parsed_at":"2022-07-31T04:37:56.869Z","dependency_job_id":null,"html_url":"https://github.com/simon-schaefer/mantrap","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/simon-schaefer/mantrap","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/simon-schaefer%2Fmantrap","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/simon-schaefer%2Fmantrap/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/simon-schaefer%2Fmantrap/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/simon-schaefer%2Fmantrap/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/simon-schaefer","download_url":"https://codeload.github.com/simon-schaefer/mantrap/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/simon-schaefer%2Fmantrap/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28660303,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-22T01:17:37.254Z","status":"online","status_checked_at":"2026-01-22T02:00:07.137Z","response_time":144,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["pedestrian","trajectory-optimization","trajectron"],"created_at":"2026-01-22T09:18:42.538Z","updated_at":"2026-01-22T09:18:43.282Z","avatar_url":"https://github.com/simon-schaefer.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":".. image:: https://travis-ci.com/simon-schaefer/mantrap.svg?branch=master\n   :target: https://travis-ci.com/simon-schaefer/mantrap\n\n.. image:: https://codecov.io/gh/simon-schaefer/mantrap/branch/master/graph/badge.svg\n  :target: https://codecov.io/gh/simon-schaefer/mantrap\n\n.. image:: https://img.shields.io/badge/docs-mantrap-blue.svg\n  :target: http://simon-schaefer.github.io/mantrap/\n\nmantrap\n=======\n\nMinimal interferring Interactive Risk-aware Planning for multimodal and time-evolving obstacle behaviour\n\nDescription\n-----------\nPlanning safe human-robot interaction is a necessary towards the widespread integration of autonomous systems in the\nsociety. However, while instinctive to humans, socially compliant navigation is still difficult to quantify due to the \nstochasticity in people’s behaviors. Previous approaches have either strongly simplified the multimodal and time-varying\nbehaviour of humans, applied hardly tractable methods lacking safety guarantees or were simply not computationally \nfeasible. Therefore the goal of this work to develop a risk-aware planning methodology with special regards on \nminimizing the interaction between human and robot and taking account the actual multi-modality and time-evolving nature\nof the humans behaviour, based on the Trajectron model (Ivanovic 19).\n\n.. code-block:: bash\n\n   Documentation: https://simon-schaefer.github.io/mantrap/\n\nInstallation\n------------\nFor installation clone the repository including it's submodules: \n\n.. code-block:: bash\n\n   git clone --recurse-submodules --remote-submodules https://github.com/simon-schaefer/mantrap.git\n\nNext create a virtual environment for Python 3 and install all package requirements by running \n\n.. code-block:: bash\n\n   conda create --name mantrap python=3.6 -y\n   source activate mantrap\n   source ops/setup.bash\n\nAfterwards install the NLP-solver `IPOPT \u003chttps://coin-or.github.io/Ipopt/\u003e`_ and it's python wrapper which is called\n`cyipopt \u003chttps://pypi.org/project/ipopt/\u003e`_:\n\n.. code-block:: bash\n\n   bash third_party/Ipopt/install.bash\n\nIn order to ensure a working Trajectron model the branch :code:`online_with_torch` has to be checkout.\n\nEvaluation\n----------\nThe evaluation of mantrap is grounded on real-world pedestrian behaviour datasets. While the  \n`ETH Pedestrian datasets \u003chttps://icu.ee.ethz.ch/research/datsets.html\u003e`_ and some custom scenarios already have\nbeen integrated, other datasets can be easily added using the mantrap_evaluation dataset API; for more information\nregarding this please read :code:`mantrap_evaluation/datasets/README`.\n\nDocumentation\n-------------\nFor code documentation the `Sphinx \u003chttps://www.sphinx-doc.org/en/master/\u003e`_ engine has been used. For building the\ndocumentation locally setup the project and run :code:`make github` in the documentation folder. Then open the\ndocumentation by opening the :code:`index.html` file in the resulting documentation build directory.\n\nRunning in optimized mode\n-------------------------\nRunning python in optimized mode let's skip all :code:`assert` statements and sets the logging level to warning\nin order to save runtime.\n\n.. code-block:: bash\n\n   python3 -O evaluation.py\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsimon-schaefer%2Fmantrap","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsimon-schaefer%2Fmantrap","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsimon-schaefer%2Fmantrap/lists"}