├── README.md └── git_op.sh /README.md: -------------------------------------------------------------------------------- 1 | # 基础知识 2 | ## 基础 3 | ### 笛卡尔坐标系&frenet坐标系: [[数学推导](https://www.jianshu.com/p/630c19f2bb9a)] 4 | 5 | ## 开源数据集 6 | ### motion forecasting dataset 7 | - [Argoverse-motion-forecasting](https://www.argoverse.org/index.html) [[Download-script](https://github.com/uber-research/LaneGCN)] 8 | - [nuscenes](https://www.nuscenes.org/) 9 | - [In-house Pedestrian-at-Intersection dataset (PAID)]() 10 | - [INTERACTION-dataset](https://github.com/interaction-dataset/interaction-dataset) 11 | - [Stanford-Drone-dataset-(SDD)](https://cvgl.stanford.edu/projects/uav_data/) 12 | - [kaggle-lyft-prediction](https://self-driving.lyft.com/level5/prediction/) 13 | 14 | ### 其他 15 | - HighD dataset "2018 21st International Conference on Intelligent Transportation Systems (ITSC)" [[link](https://www.highd-dataset.com/)] [[paper](https://ieeexplore.ieee.org/abstract/document/8569552)] [[github](https://github.com/RobertKrajewski/highD-dataset)] [[format](https://www.highd-dataset.com/format)] 16 | - inD dataset [[link](https://www.ind-dataset.com/)] [[paper](https://arxiv.org/abs/1911.07602)] 17 | - round dataset [[link](https://www.round-dataset.com/)] [[paper]()] 18 | 19 | 20 | ## 资料 21 | - [自动驾驶行为预测](https://zhuanlan.zhihu.com/p/158951141) 22 | - [行人的行为意图建模和预测](https://zhuanlan.zhihu.com/p/86184886) 23 |
24 | 25 | **** 26 | 27 | # vehicle trajectory prediction 28 | ## 关键字 29 | - Motion forecasting/prediction 30 | - Trajectory Prediction 31 | - Vehicle behavior prediction 32 | ## 其他词汇 33 | - Occupancy Grid Maps[[zhihu](https://zhuanlan.zhihu.com/p/21738718)] 34 | - BEV(Bird's eye view) 35 | - HD maps 36 | - geographic coordinate system 37 | ## Paper List 38 | - "Fast lane changing computations using polynomials" "Proceedings of the 2003 American Control Conference" (2003) [[paper](https://ieeexplore.ieee.org/abstract/document/1238912)] 39 | - "Vehicle trajectory prediction based on motion model and maneuver recognition" (2013 IROS) [[paper](https://ieeexplore.ieee.org/abstract/document/6696982)] 40 | - "A survey on motion prediction and risk assessment for intelligent vehicles"(2014) [[paper](https://hal.inria.fr/hal-01053736/document)] 41 | - "Lane Change Scheduling for Autonomous Vehicles"(2016) [[paper](https://www.sciencedirect.com/science/article/pii/S2405896316302063)] 42 | - "Lane-Change Detection Based on Vehicle-Trajectory Prediction" (IEEE Robotics and Automation Letters 2017) [[paper](https://ieeexplore.ieee.org/abstract/document/7835731)] 43 | - "Vehicle trajectory prediction by integrating physics-and maneuver-based approaches using interactive multiple models" (IEEE Transactions on Industrial Electronics 2017) [[paper](https://ieeexplore.ieee.org/abstract/document/8186191)] 44 | - "Probabilistic vehicle trajectory prediction over occupancy grid map via recurrent neural network" (ITSC 2017) [[paper](https://ieeexplore.ieee.org/abstract/document/8317943)] 45 | - "Sequence-to-Sequence Prediction of Vehicle Trajectory via LSTM Encoder-Decoder Architecture"(2018 IEEE Intelligent Vehicles Symposium (IV) 2018) [[paper](https://ieeexplore.ieee.org/abstract/document/8500658)] 46 | - "Convolutional Social Pooling for Vehicle Trajectory Prediction"(CVPR 2018) [[paper](https://openaccess.thecvf.com/content_cvpr_2018_workshops/papers/w29/Deo_Convolutional_Social_Pooling_CVPR_2018_paper.pdf)] 47 | - "Modeling Vehicle Interactions via Modified LSTM Models for Trajectory Prediction" (IEEE Access 2019) [[paper](https://ieeexplore.ieee.org/abstract/document/8672889)] 48 | - "Non-local Social Pooling for Vehicle Trajectory Prediction" (IEEE Intelligent Vehicles Symposium (IV) 2019) [[paper](https://ieeexplore.ieee.org/abstract/document/8813829)] 49 | 50 | ## Review 51 | - "Deep learning-based vehicle behavior prediction for autonomous driving applications: A review" (2020 IEEE Transactions on Intelligent Transportation Systems) [[paper](https://ieeexplore.ieee.org/abstract/document/9158529)] 52 | 53 | ## 近几年进展 54 | - "The KITTI dataset" (IJRR 2013) [[paper](http://ww.cvlibs.net/publications/Geiger2013IJRR.pdf)] [[website](http://www.cvlibs.net/datasets/kitti/)] 55 | - "DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents" (CVPR 2017) [[paper](https://arxiv.org/abs/1704.04394)] [[code](https://github.com/tdavchev/DESIRE)] 56 | - "Argoverse: 3D Tracking and Forecasting with Rich Maps" (CVPR 2019) [[paper](https://openaccess.thecvf.com/content_CVPR_2019/html/Chang_Argoverse_3D_Tracking_and_Forecasting_With_Rich_Maps_CVPR_2019_paper.html)] [[code1](https://github.com/argoai/argoverse-api)] [[code2](https://github.com/alliecc/argoverse_baselinetracker)] [[website](https://www.argoverse.org/index.html)] [[API](https://argoai.github.io/argoverse-api/)] 57 | - "INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Maps" [[paper](https://arxiv.org/abs/1910.03088)] [[website](http://interaction-dataset.com/)] [[code](https://github.com/interaction-dataset/interaction-dataset)] 58 | - "TPNet: Trajectory Proposal Network for Motion Prediction" (CVPR 2020) [[paper](https://decisionforce.github.io/TPNet/)] 59 | - "Learning Lane Graph Representations for Motion Forecasting" (ECCV 2020) [[paper](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123470528.pdf)] [[code](https://github.com/uber-research/LaneGCN)] 60 | - "TNT: Target-driveN Trajectory Prediction" (CoRL（Conference on Robot Learning）2020) [[zhihu](https://zhuanlan.zhihu.com/p/267946225)] 61 | - "VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation" (CVPR 2020) [[code](https://github.com/DQSSSSS/VectorNet)] [[zhihu](https://zhuanlan.zhihu.com/p/141665706)] 62 | - "Multi-head attention for multi-modal joint vehicle motion forecasting" (ICRA 2020) [[paper](https://arxiv.org/abs/1910.03650)]
63 | **** 64 | - "MANTRA: Memory Augmented Networks for Multiple Trajectory Prediction" (CVPR 2020) [[paper](https://openaccess.thecvf.com/content_CVPR_2020/papers/Marchetti_MANTRA_Memory_Augmented_Networks_for_Multiple_Trajectory_Prediction_CVPR_2020_paper.pdf)] 65 | - "Reciprocal Learning Networks for Human Trajectory Prediction" (CVPR 2020 human) [[paper](https://openaccess.thecvf.com/content_CVPR_2020/papers/Sun_Reciprocal_Learning_Networks_for_Human_Trajectory_Prediction_CVPR_2020_paper.pdf)] 66 | - "MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Maps" (CVPR 2020) [[paper](https://openaccess.thecvf.com/content_CVPR_2020/papers/Wu_MotionNet_Joint_Perception_and_Motion_Prediction_for_Autonomous_Driving_Based_CVPR_2020_paper.pdf)] [[code](https://github.com/pxiangwu/MotionNet)] 67 | - "STINet: Spatio-Temporal-Interactive Network for Pedestrian Detection and Trajectory Prediction" (CVPR 2020 human) [[paper](https://arxiv.org/pdf/2005.04255.pdf)] 68 | - "Recursive Social Behavior Graph for Trajectory Prediction" (CVPR 2020 human) [[paper](https://openaccess.thecvf.com/content_CVPR_2020/papers/Sun_Recursive_Social_Behavior_Graph_for_Trajectory_Prediction_CVPR_2020_paper.pdf)] 69 | - "Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction" (CVPR 2020 human) [[paper]()] 70 | - "PnPNet: End-to-End Perception and Prediction with Tracking in the Loop" (CVPR 2020) [[paper](https://arxiv.org/pdf/2005.14711.pdf)] 71 | - "The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction" (CVPR 2020 human) [[paper](https://arxiv.org/pdf/1912.06445.pdf)] [[website](https://next.cs.cmu.edu/multiverse/)] [[code](https://github.com/JunweiLiang/Multiverse)] 72 | - "Generative Hybrid Representations for Activity Forecasting with No-Regret Learning" (CVPR 2020 reasoning objects) [[paper](https://arxiv.org/pdf/1904.06250.pdf)] 73 | ## leaderboard&benchmark 74 | - [Argoverse-Motion-Forecasting-Competition](https://eval.ai/web/challenges/challenge-page/454/leaderboard/1279#leaderboardrank-10) 75 | - [Forecast-baseline](https://github.com/jagjeet-singh/argoverse-forecasting) 76 | - [baselinetracker](https://github.com/alliecc/argoverse_baselinetracker) 77 | ## Evaluation Metric 78 | - Average Displacement Error (ADE) 79 | - Final Displacement Error (FDE) 80 | - minADEk & minFDEk :For a set of K predicted trajectories 81 | - Miss Rate (MR) 82 | 83 | ## argoverse benchmark 84 | - TPNet: Trajectory Proposal Network for Motion Prediction [CVPR2020] [[paper](https://openaccess.thecvf.com/content_CVPR_2020/papers/Fang_TPNet_Trajectory_Proposal_Network_for_Motion_Prediction_CVPR_2020_paper.pdf)] 85 | - Multi-Head Attention for Multi-Modal Joint Vehicle Motion Forecasting [ICRA2020] [[paper](https://arxiv.org/pdf/1910.03650.pdf)] 86 | - LaneGCN: Learning Lane Graph Representations for Motion Forecasting [ECCV2020] [[paper](https://arxiv.org/pdf/2007.13732.pdf)] [[code](https://github.com/uber-research/LaneGCN)] 87 | - LaneRCNN: Distributed Representations for Graph-Centric Motion Forecasting [[paper](https://arxiv.org/abs/2101.06653)] 88 | - TNT [CVPR2020] 89 | - VectorNet [CVPR2020] [[zhihu](https://zhuanlan.zhihu.com/p/149799591)] [[paper](https://arxiv.org/abs/2005.04259)] [[code](https://github.com/DQSSSSS/VectorNet)] 90 | 91 | 92 |
93 | 94 | **** 95 | 96 | # Lane Change Detection/Intention prediction 97 | ## 关键字 98 | - Manoeuvre Intention 99 | - intent prediction 100 | - lane change 101 | ## paper list 102 | - "A survey on motion prediction and risk assessment for intelligent vehicles" (2014) [[paper](https://robomechjournal.springeropen.com/articles/10.1186/s40648-014-0001-z)] 103 | - "Long short term memory for driver intent prediction" (IEEE Intelligent Vehicles Symposium (IV) 2017) [[paper](https://ieeexplore.ieee.org/document/7995919)] 104 | - "Generalizable intention prediction of human drivers at intersections" (IEEE Intelligent Vehicles Symposium (IV) 2017) [[paper](https://ieeexplore.ieee.org/document/7995948)] 105 | - "Convolution neural network-based lane change intention prediction of surrounding vehicles" (ITSC 2017) [[paper](https://ywpkwon.github.io/pdf/17itsc.pdf)] 106 | - "Predicting Vehicle Behaviors Over An Extended Horizon Using Behavior Interaction Network" (ICRA 2019) [[paper](https://arxiv.org/abs/1903.00848)] 107 | - 108 | - "Continuous Control for Automated Lane Change Behavior Based on Deep Deterministic Policy Gradient Algorithm" [[paper](https://www.sci-hub.ren/https://ieeexplore.ieee.org/abstract/document/8813903/)] 109 | - "On-Road Vehicle Trajectory Collection and Scene-Based Lane Change Analysis: Part II" [[paper](https://www.sci-hub.ren/10.1109/TITS.2016.2571724]] 110 | - "An ensemble deep learning approach for driver lane change intention inference" [[paper](https://www.sci-hub.ren/10.1016/j.trc.2020.102615)] 111 | - "A data-driven lane-changing model based on deep learning" [[paper](https://www.sci-hub.ren/10.1016/j.trc.2019.07.002)] 112 | - "Simultaneous modeling of car-following and lane-changing behaviors using deep learning" [[paper](https://www.sci-hub.ren/10.1016/j.trc.2019.05.021)] 113 | ## project list 114 | - "lane-change-prediction-lstm" [[project](https://github.com/chitianhao/lane-change-prediction-lstm)] 115 | - "DQN" [[project](https://github.com/MaxPRon/DQN_lane_change)] 116 | - [LC_NGSIM](https://github.com/donnydcy/LC_NGSIM) 117 | 118 | 119 | # Human trajectory prediction 120 | ## key word 121 | ## paper list 122 | - Peeking Into the Future: Predicting Future Person Activities and Locations in Videos [CVPR2019] [[paper](https://arxiv.org/abs/1902.03748)] [[code](https://github.com/google/next-prediction)] 123 | - Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks [CVPR2018] [[paper](https://arxiv.org/abs/1803.10892)] [[code](https://github.com/agrimgupta92/sgan)] 124 | 125 | # 参考 126 | - [paper-with-code](https://paperswithcode.com/task/trajectory-prediction/latest) 127 | - [轨迹预测相关资源列表](https://bbs.cvmart.net/articles/642) 128 | - [kaggle](https://www.kaggle.com/c/lyft-motion-prediction-autonomous-vehicles/overview/evaluation) 129 | 130 | **** 131 | -------------------------------------------------------------------------------- /git_op.sh: -------------------------------------------------------------------------------- 1 | git add . 2 | git commit -m "update" 3 | git push origin master 4 | --------------------------------------------------------------------------------