梦醒时分1218
梦醒时分1218

轨迹预测论文阅读

文章目录

  • 总结
  • 2018
    • Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks
    • Motion Prediction of Traffic Actors for Autonomous Driving using Deep Convolutional Networks
  • 2019
    • Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks
    • PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settings
    • Rules of the Road: Predicting Driving Behavior with a Convolutional Model of Semantic Interactions
    • Multi-Head Attention for Multi-Modal Joint Vehicle Motion Forecasting
  • 2020
    • Learning Lane Graph Representations for Motion Forecasting
    • Implicit Latent Variable Model for Scene-Consistent Motion Forecasting
    • TNT: Target-driveN Trajectory Prediction
    • VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation
    • MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Prediction
    • CoverNet: Multimodal Behavior Prediction using Trajectory Sets
    • Trajectron++: Dynamically-Feasible Trajectory Forecasting With Heterogeneous Data
    • The Importance of Prior Knowledge in Precise Multimodal Prediction
  • 2021
    • LaneRCNN: Distributed Representations for Graph-Centric Motion Forecasting
    • Multimodal Trajectory Prediction Conditioned on Lane-Graph Traversals
    • Goal-driven Long-Term Trajectory Prediction
    • DenseTNT: Waymo Open Dataset Motion Prediction Challenge 1st Place Solution [√]
    • Scene Transformer: A unified multi-task model for behavior prediction and planning

总结

  • goal-based methods
    首先预测每个 agent 的 endpoint, 然后预测完整的轨迹

2018

Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks

  • CVPR
  • Social GAN

Motion Prediction of Traffic Actors for Autonomous Driving using Deep Convolutional Networks

  • Uber
  • paper

2019

Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks

  • ICRA
  • paper

PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settings

  • ICCV
  • PRECOG

Rules of the Road: Predicting Driving Behavior with a Convolutional Model of Semantic Interactions

  • CVPR
  • paper

Multi-Head Attention for Multi-Modal Joint Vehicle Motion Forecasting

  • paper

2020

Learning Lane Graph Representations for Motion Forecasting

  • ECCV
  • Uber
  • paper
  • code

Implicit Latent Variable Model for Scene-Consistent Motion Forecasting

  • ECCV
  • Uber
  • paper

TNT: Target-driveN Trajectory Prediction

  • Waymo
  • TNT

VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation

  • CVPR
  • Waymo
  • VectorNet

MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Prediction

  • CVPR
  • MultiPath

CoverNet: Multimodal Behavior Prediction using Trajectory Sets

  • CoverNet

Trajectron++: Dynamically-Feasible Trajectory Forecasting With Heterogeneous Data

  • ECCV
  • Trajectron++
  • code

The Importance of Prior Knowledge in Precise Multimodal Prediction

  • IROS
  • Uber
  • paper

2021

LaneRCNN: Distributed Representations for Graph-Centric Motion Forecasting

  • Uber
  • LaneRCNN

Multimodal Trajectory Prediction Conditioned on Lane-Graph Traversals

  • paper

Goal-driven Long-Term Trajectory Prediction

  • WACV
  • paper

DenseTNT: Waymo Open Dataset Motion Prediction Challenge 1st Place Solution [√]

  • CVPR WorkShop
  • DenseTNT

Scene Transformer: A unified multi-task model for behavior prediction and planning

  • paper

你可能感兴趣的:(论文阅读)

按字母分类： ABCDEFGHIJKLMNOPQRSTUVWXYZ其他