{"id":19526646,"url":"https://github.com/zju-fast-lab/opnet","last_synced_at":"2025-04-26T10:31:30.901Z","repository":{"id":107909359,"uuid":"309008285","full_name":"ZJU-FAST-Lab/OPNet","owner":"ZJU-FAST-Lab","description":"Learning Unknown Space for Autonomous Navigation in Clustered Environment","archived":false,"fork":false,"pushed_at":"2021-04-02T06:23:29.000Z","size":25147,"stargazers_count":62,"open_issues_count":3,"forks_count":14,"subscribers_count":5,"default_branch":"main","last_synced_at":"2025-04-04T11:46:39.000Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ZJU-FAST-Lab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2020-11-01T02:19:59.000Z","updated_at":"2025-03-07T17:24:17.000Z","dependencies_parsed_at":null,"dependency_job_id":"230bba8e-67aa-4d80-8ddf-5c486bdfb8b3","html_url":"https://github.com/ZJU-FAST-Lab/OPNet","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZJU-FAST-Lab%2FOPNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZJU-FAST-Lab%2FOPNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZJU-FAST-Lab%2FOPNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZJU-FAST-Lab%2FOPNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ZJU-FAST-Lab","download_url":"https://codeload.github.com/ZJU-FAST-Lab/OPNet/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250972820,"owners_count":21516431,"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":[],"created_at":"2024-11-11T01:11:13.152Z","updated_at":"2025-04-26T10:31:25.887Z","avatar_url":"https://github.com/ZJU-FAST-Lab.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"# OPNet \u0026 krrt-planner with map-prediction\n\nVideo at:\nhttps://www.youtube.com/watch?v=Qb3ni_j0Dic\n\nPreprint:\nLearning-based 3D Occupancy Prediction for Autonomous Navigation in Occluded Environments\n\nhttps://arxiv.org/abs/2011.03981\n\n\n#\n\nc++ realization of the paper: Kinodynamic RRT*: Asymptotically Optimal Motion Planning for Robots with Linear Dynamics\n\nBuilding:\nThe depth_sensor_simulator package in uav_simulator is alternative to build with GPU or CPU to render the depth sensor measurement. By default, it is set to build with GPU in CMakeLists:\n\nDependencies:\n\n    1. ROS (I am using Ubuntu 16.04 and ROS Kinetic, other versions maybe also usable)\n\n    2. CUDA (I am using 10.2)\n\n    3. for branch \"main\" (inference using NVIDIA TensorRT):\n        * TensorRT 7.0.0+cuda10.2 (with TensorRT ONNX  libraries)\n\nIf you want to run with only pytorch, please refer to https://gitee.com/leewlz/opnet and branch torch\n\n    4. for branch \"torch\" (inference using a Python node with Pytorch ):\n        * python \u003e 2.7\n        * numpy, Ipython, tensorboardX\n        * Pytorch (I am using 1.3.0, later versions are also usable)\n\n\nset(ENABLE_CUDA true)\n\nRemember to change the 'arch' and 'code' flags according to your graphics card devices. \nfor branch \"torch\":\n* Remember to change the model path in net_node.py -- init_param function\n\n## Run Simulation:\n\n    1. roslaunch state_machine rviz.launch  (to open rviz for visualization)\n    2. roslaunch state_machine bench_with_pred.launch    (generate environment, start simulator)\n    3. roslaunch state_machine bench_with_pred.launch  or  bench_aggres.launch    or    bench_safe.launch    (test)\n\n\n![fig1](./fig/room.png)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzju-fast-lab%2Fopnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzju-fast-lab%2Fopnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzju-fast-lab%2Fopnet/lists"}