Stepwise Goal-Driven Networks for Trajectory Prediction

03/25/2021
by   W, et al.
0

We propose to predict the future trajectories of observed agents (e.g., pedestrians or vehicles) by estimating and using their goals at multiple time scales. We argue that the goal of a moving agent may change over time, and modeling goals continuously provides more accurate and detailed information for future trajectory estimation. In this paper, we present a novel recurrent network for trajectory prediction, called Stepwise Goal-Driven Network (SGNet). Unlike prior work that models only a single, long-term goal, SGNet estimates and uses goals at multiple temporal scales. In particular, the framework incorporates an encoder module that captures historical information, a stepwise goal estimator that predicts successive goals into the future, and a decoder module that predicts future trajectory. We evaluate our model on three first-person traffic datasets (HEV-I, JAAD, and PIE) as well as on two bird's eye view datasets (ETH and UCY), and show that our model outperforms the state-of-the-art methods in terms of both average and final displacement errors on all datasets. Code has been made available at: https://github.com/ChuhuaW/SGNet.pytorch.

READ FULL TEXT

Authors

page 1

page 8

11/05/2020

Goal-driven Long-Term Trajectory Prediction

The prediction of humans' short-term trajectories has advanced significa...
08/10/2021

Multi-Camera Trajectory Forecasting with Trajectory Tensors

We introduce the problem of multi-camera trajectory forecasting (MCTF), ...
04/21/2021

FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras

Driving requires interacting with road agents and predicting their futur...
05/08/2022

Mutual Distillation Learning Network for Trajectory-User Linking

Trajectory-User Linking (TUL), which links trajectories to users who gen...
06/08/2020

Multimodal Future Localization and Emergence Prediction for Objects in Egocentric View with a Reachability Prior

In this paper, we investigate the problem of anticipating future dynamic...
12/18/2020

A Graph Attention Based Approach for Trajectory Prediction in Multi-agent Sports Games

This work investigates the problem of multi-agents trajectory prediction...
12/22/2016

First-Person Activity Forecasting with Online Inverse Reinforcement Learning

We address the problem of incrementally modeling and forecasting long-te...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.