Flexible Multi-Generator Model with Fused Spatiotemporal Graph for
Trajectory Prediction
- URL: http://arxiv.org/abs/2311.02835v1
- Date: Mon, 6 Nov 2023 02:46:05 GMT
- Title: Flexible Multi-Generator Model with Fused Spatiotemporal Graph for
Trajectory Prediction
- Authors: Peiyuan Zhu, Fengxia Han and Hao Deng
- Abstract summary: Trajectory prediction plays a vital role in automotive radar systems.
Generative adversarial networks with the ability to learn a distribution over future trajectories tend to predict out-of-distribution samples.
We propose a trajectory prediction framework, which can capture the social interaction and model disconnected variations of pedestrian trajectories.
- Score: 2.1638817206926855
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Trajectory prediction plays a vital role in automotive radar systems,
facilitating precise tracking and decision-making in autonomous driving.
Generative adversarial networks with the ability to learn a distribution over
future trajectories tend to predict out-of-distribution samples, which
typically occurs when the distribution of forthcoming paths comprises a blend
of various manifolds that may be disconnected. To address this issue, we
propose a trajectory prediction framework, which can capture the social
interaction variations and model disconnected manifolds of pedestrian
trajectories. Our framework is based on a fused spatiotemporal graph to better
model the complex interactions of pedestrians in a scene, and a multi-generator
architecture that incorporates a flexible generator selector network on
generated trajectories to learn a distribution over multiple generators. We
show that our framework achieves state-of-the-art performance compared with
several baselines on different challenging datasets.
Related papers
- Traj-MAE: Masked Autoencoders for Trajectory Prediction [69.7885837428344]
Trajectory prediction has been a crucial task in building a reliable autonomous driving system by anticipating possible dangers.
We propose an efficient masked autoencoder for trajectory prediction (Traj-MAE) that better represents the complicated behaviors of agents in the driving environment.
Our experimental results in both multi-agent and single-agent settings demonstrate that Traj-MAE achieves competitive results with state-of-the-art methods.
arXiv Detail & Related papers (2023-03-12T16:23:27Z) - THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling [2.424910201171407]
We present a unified model architecture for fast and simultaneous agent future heatmap estimation.
generating scene-consistent predictions goes beyond the mere generation of collision-free trajectories.
We report our results on the Interaction multi-agent prediction challenge and rank $1st$ on the online test leaderboard.
arXiv Detail & Related papers (2021-10-13T10:05:47Z) - MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples
in Pedestrian Trajectory Prediction [0.6445605125467573]
We propose a multi-generator model for pedestrian trajectory prediction.
Each generator specializes in learning a distribution over trajectories routing towards one of the primary modes in the scene.
A second network learns a categorical distribution over these generators, conditioned on the dynamics and scene input.
This architecture allows us to effectively sample from specialized generators and to significantly reduce the out-of-distribution samples compared to single generator methods.
arXiv Detail & Related papers (2021-08-20T17:10:39Z) - Haar Wavelet based Block Autoregressive Flows for Trajectories [129.37479472754083]
Prediction of trajectories such as that of pedestrians is crucial to the performance of autonomous agents.
We introduce a novel Haar wavelet based block autoregressive model leveraging split couplings.
We illustrate the advantages of our approach for generating diverse and accurate trajectories on two real-world datasets.
arXiv Detail & Related papers (2020-09-21T13:57:10Z) - DSDNet: Deep Structured self-Driving Network [92.9456652486422]
We propose the Deep Structured self-Driving Network (DSDNet), which performs object detection, motion prediction, and motion planning with a single neural network.
We develop a deep structured energy based model which considers the interactions between actors and produces socially consistent multimodal future predictions.
arXiv Detail & Related papers (2020-08-13T17:54:06Z) - SMART: Simultaneous Multi-Agent Recurrent Trajectory Prediction [72.37440317774556]
We propose advances that address two key challenges in future trajectory prediction.
multimodality in both training data and predictions and constant time inference regardless of number of agents.
arXiv Detail & Related papers (2020-07-26T08:17:10Z) - Implicit Latent Variable Model for Scene-Consistent Motion Forecasting [78.74510891099395]
In this paper, we aim to learn scene-consistent motion forecasts of complex urban traffic directly from sensor data.
We model the scene as an interaction graph and employ powerful graph neural networks to learn a distributed latent representation of the scene.
arXiv Detail & Related papers (2020-07-23T14:31:25Z) - Probabilistic Crowd GAN: Multimodal Pedestrian Trajectory Prediction
using a Graph Vehicle-Pedestrian Attention Network [12.070251470948772]
We show how Probabilistic Crowd GAN can output probabilistic multimodal predictions.
We also propose the use of Graph Vehicle-Pedestrian Attention Network (GVAT), which models social interactions.
We demonstrate improvements on the existing state of the art methods for trajectory prediction and illustrate how the true multimodal and uncertain nature of crowd interactions can be directly modelled.
arXiv Detail & Related papers (2020-06-23T11:25:16Z) - Multi-Head Attention based Probabilistic Vehicle Trajectory Prediction [10.905596145969223]
We propose a simple encoder-decoder architecture based on multi-head attention.
The proposed model generates the distribution of the predicted trajectories for multiple vehicles in parallel.
arXiv Detail & Related papers (2020-04-08T06:58:51Z) - Spatial-Temporal Transformer Networks for Traffic Flow Forecasting [74.76852538940746]
We propose a novel paradigm of Spatial-Temporal Transformer Networks (STTNs) to improve the accuracy of long-term traffic forecasting.
Specifically, we present a new variant of graph neural networks, named spatial transformer, by dynamically modeling directed spatial dependencies.
The proposed model enables fast and scalable training over a long range spatial-temporal dependencies.
arXiv Detail & Related papers (2020-01-09T10:21:04Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.