轨迹运动预测相关论文大盘点 | Trajectory Motion Prediction

作者 | 啊哈哈  编辑 | 汽车人

原文链接：https://zhuanlan.zhihu.com/p/480433722

点击下方卡片，关注“自动驾驶之心”公众号

ADAS巨卷干货，即可获取

点击进入→自动驾驶之心【轨迹预测】技术交流群

本文只做学术分享，如有侵权，联系删文

ICRA 2024

• MacFormer: Map-Agent Coupled Transformer for Real-time and Robust Trajectory Prediction.

ICCV 2023

• ADAPT: Efficient Multi-Agent Trajectory Prediction with Adaptation.

• BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction.

• BiFF: Bi-level Future Fusion with Polyline-based Coordinate for Interactive Trajectory Prediction.

• EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecasting.

• Fast Inference and Update of Probabilistic Density Estimation on Trajectory Prediction.

• Forecast-MAE: Self-supervised Pre-training for Motion Forecasting with Masked Autoencoders.

• GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Driving.

• HumanMAC: Masked Motion Completion for Human Motion Prediction.

• INT2: Interactive Trajectory Prediction at Intersections.

• InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion.

• Joint Metrics Matter: A Better Standard for Trajectory Forecasting.

• Learn TAROT with MENTOR: A Meta-Learned Self-Supervised Approach for Trajectory Prediction.

• R-Pred: Two-Stage Motion Prediction Via Tube-Query Attention-Based Trajectory Refinement.

• Semi-supervised Semantics-guided Adversarial Training for Robust Trajectory Prediction.

• Sparse Instance Conditioned Multimodal Trajectory Prediction.

• Traj-MAE: Masked Autoencoders for Trajectory Prediction.

• Trajectory Unified Transformer for Pedestrian Trajectory Prediction.

• TrajPAC: Towards Robustness Verification of Pedestrian Trajectory Prediction Models.

八折优惠仅限一天！扫码加入学习！

CVPR 2023

• Decompose More and Aggregate Better: Two Closer Looks at Frequency Representation Learning for Human Motion Prediction.

• DeFeeNet: Consecutive 3D Human Motion Prediction with Deviation Feedback.

• EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning.

• FEND: A Future Enhanced Distribution-Aware Contrastive Learning Framework for Long-tail Trajectory Prediction.

• FJMP: Factorized Joint Multi-Agent Motion Prediction over Learned Directed Acyclic Interaction Graphs.

• IPCC-TP: Utilizing Incremental Pearson Correlation Coefficient for Joint Multi-Agent Trajectory Prediction.

• Leapfrog Diffusion Model for Stochastic Trajectory Prediction.

• MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusion.

• Planning-oriented Autonomous Driving.

• ProphNet: Efficient Agent-Centric Motion Forecasting with Anchor-Informed Proposals.

• Query-Centric Trajectory Prediction.

• Stimulus Verification is a Universal and Effective Sampler in Multi-modal Human Trajectory Prediction.

• Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion.

• Trajectory-Aware Body Interaction Transformer for Multi-Person Pose Forecasting.

• Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Prediction.

• Unsupervised Sampling Promoting for Stochastic Human Trajectory Prediction.

• ViP3D: End-to-end Visual Trajectory Prediction via 3D Agent Queries.

• Weakly Supervised Class-agnostic Motion Prediction for Autonomous Driving.

ICLR 2023

• Learning Heterogeneous Interaction Strengths by Trajectory Prediction with Graph Neural Network.

• Stochastic Multi-Person 3D Motion Forecasting.

ICRA 2023

• Expanding the Deployment Envelope of Behavior Prediction via Adaptive Meta-Learning.

arXiv 2022

• Safety-compliant Generative Adversarial Networks for Human Trajectory Forecasting.

• Wayformer: Motion Forecasting via Simple & Efficient Attention Networks.

CoRL 2022

• SSL-Lanes: Self-Supervised Learning for Motion Forecasting in Autonomous Driving.

NeurIPS 2022

• Contact-aware Human Motion Forecasting.

• Forecasting Human Trajectory from Scene History.

• Motion Forecasting Transformer with Global Intention Localization and Local Movement Refinement.

ECCV 2022

• Action-based Contrastive Learning for Trajectory Prediction.

• AdvDO: Realistic Adversarial Attacks for Trajectory Prediction.

• Aware of the History: Trajectory Forecasting with the Local Behavior Data.

• Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors.

• D2-TPred: Discontinuous Dependency for Trajectory Prediction under Traffic Lights.

• Entry-Flipped Transformer for Inference and Prediction of Participant Behavior.

• Hierarchical Latent Structure for Multi-Modal Vehicle Trajectory Forecasting.

• Human Trajectory Prediction via Neural Social Physics.

• Learning Pedestrian Group Representations for Multi-modal Trajectory Prediction.

• Overlooked Poses Actually Make Sense: Distilling Privileged Knowledge for Human Motion Prediction. [arXiv]

• Polarimetric Pose Prediction.

• PreTraM: Self-Supervised Pre-training via Connecting Trajectory and Map.

• Skeleton-Parted Graph Scattering Networks for 3D Human Motion Prediction.

• Social-Implicit: Rethinking Trajectory Prediction Evaluation and The Effectiveness of Implicit Maximum Likelihood Estimatio.

• Social ODE: Multi-Agent Trajectory Forecasting with Neural Ordinary Differential Equations.

• SocialVAE: Human Trajectory Prediction using Timewise Latents.

• ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning.

• View Vertically: A Hierarchical Network for Trajectory Prediction via Fourier Spectrums.

CVPR 2022

• Adaptive Trajectory Prediction via Transferable GNN.

• ATPFL: Automatic Trajectory Prediction Model Design Under Federated Learning Framework.

• Convolutions for Spatial Interaction Modeling.

• End-to-End Trajectory Distribution Prediction Based on Occupancy Grid Maps.

• Forecasting from LiDAR via Future Object Detection.

• Graph-based Spatial Transformer with Memory Replay for Multi-future Pedestrian Trajectory Prediction.

• GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational Reasoning.

• LTP: Lane-Based Trajectory Prediction for Autonomous Driving.

• M2I: From Factored Marginal Trajectory Prediction to Interactive Prediction.

• Neural Prior for Trajectory Estimation.

• Non-Probability Sampling Network for Stochastic Human Trajectory Prediction.

• On Adversarial Robustness of Trajectory Prediction for Autonomous Vehicles.

• Remember Intentions: Retrospective-Memory-based Trajectory Prediction.

• ScePT: Scene-consistent, Policy-based Trajectory Predictions for Planning.

• Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion.

• Vehicle Trajectory Prediction Works, But Not Everywhere.

• Whose Track Is It Anyway? Improving Robustness to Tracking Errors With Affinity-Based Trajectory Prediction

• Goal-driven Self-Attentive Recurrent Networks for Trajectory Prediction.

• Importance Is in Your Attention: Agent Importance Prediction for Autonomous Driving.

• BE-STI: Spatial-Temporal Integrated Network for Class-Agnostic Motion Prediction With Bidirectional Enhancement.

• Forecasting Characteristic 3D Poses of Human Actions.

• HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction.

• Human Trajectory Prediction With Momentary Observation.

• MotionAug: Augmentation With Physical Correction for Human Motion Prediction.

• Motron: Multimodal Probabilistic Human Motion Forecasting.

• Multi-Objective Diverse Human Motion Prediction With Knowledge Distillation.

• Multi-Person Extreme Motion Prediction.

• Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction.

• Spatial-Temporal Gating-Adjacency GCN for Human Motion Prediction.

八折优惠仅限一天！扫码加入学习！

扫码添加助理咨询课程！

(微信：AIDriver004)

① 全网独家视频课程

BEV感知、毫米波雷达视觉融合、多传感器标定、多传感器融合、多模态3D目标检测、点云3D目标检测、目标跟踪、Occupancy、cuda与TensorRT模型部署、协同感知、语义分割、自动驾驶仿真、传感器部署、决策规划、轨迹预测等多个方向学习视频（扫码即可学习）

视频官网：www.zdjszx.com

② 国内首个自动驾驶学习社区

近2000人的交流社区，涉及30+自动驾驶技术栈学习路线，想要了解更多自动驾驶感知（2D检测、分割、2D/3D车道线、BEV感知、3D目标检测、Occupancy、多传感器融合、多传感器标定、目标跟踪、光流估计）、自动驾驶定位建图（SLAM、高精地图、局部在线地图）、自动驾驶规划控制/轨迹预测等领域技术方案、AI模型部署落地实战、行业动态、岗位发布，欢迎扫描下方二维码，加入自动驾驶之心知识星球，这是一个真正有干货的地方，与领域大佬交流入门、学习、工作、跳槽上的各类难题，日常分享论文+代码+视频，期待交流！

③【自动驾驶之心】技术交流群

自动驾驶之心是首个自动驾驶开发者社区，聚焦目标检测、语义分割、全景分割、实例分割、关键点检测、车道线、目标跟踪、3D目标检测、BEV感知、多模态感知、Occupancy、多传感器融合、transformer、大模型、点云处理、端到端自动驾驶、SLAM、光流估计、深度估计、轨迹预测、高精地图、NeRF、规划控制、模型部署落地、自动驾驶仿真测试、产品经理、硬件配置、AI求职交流等方向。扫码添加汽车人助理微信邀请入群，备注：学校/公司+方向+昵称（快速入群方式）

④【自动驾驶之心】平台矩阵，欢迎联系我们！