GroupNet: Multiscale Hypergraph Neural Networks for Trajectory
Prediction with Relational Reasoning
- URL: http://arxiv.org/abs/2204.08770v2
- Date: Wed, 20 Apr 2022 04:28:46 GMT
- Title: GroupNet: Multiscale Hypergraph Neural Networks for Trajectory
Prediction with Relational Reasoning
- Authors: Chenxin Xu, Maosen Li, Zhenyang Ni, Ya Zhang, Siheng Chen
- Abstract summary: GroupNet is a multiscale hypergraph neural network that captures both pair-wise and group-wise interactions.
We apply GroupNet into both CVAE-based prediction system and previous state-of-the-art prediction systems.
We show that with GroupNet, the CVAE-based prediction system outperforms state-of-the-art methods.
- Score: 37.64048110462638
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Demystifying the interactions among multiple agents from their past
trajectories is fundamental to precise and interpretable trajectory prediction.
However, previous works only consider pair-wise interactions with limited
relational reasoning. To promote more comprehensive interaction modeling for
relational reasoning, we propose GroupNet, a multiscale hypergraph neural
network, which is novel in terms of both interaction capturing and
representation learning. From the aspect of interaction capturing, we propose a
trainable multiscale hypergraph to capture both pair-wise and group-wise
interactions at multiple group sizes. From the aspect of interaction
representation learning, we propose a three-element format that can be learnt
end-to-end and explicitly reason some relational factors including the
interaction strength and category. We apply GroupNet into both CVAE-based
prediction system and previous state-of-the-art prediction systems for
predicting socially plausible trajectories with relational reasoning. To
validate the ability of relational reasoning, we experiment with synthetic
physics simulations to reflect the ability to capture group behaviors, reason
interaction strength and interaction category. To validate the effectiveness of
prediction, we conduct extensive experiments on three real-world trajectory
prediction datasets, including NBA, SDD and ETH-UCY; and we show that with
GroupNet, the CVAE-based prediction system outperforms state-of-the-art
methods. We also show that adding GroupNet will further improve the performance
of previous state-of-the-art prediction systems.
Related papers
- Multi-Agent Dynamic Relational Reasoning for Social Robot Navigation [50.01551945190676]
Social robot navigation can be helpful in various contexts of daily life but requires safe human-robot interactions and efficient trajectory planning.
We propose a systematic relational reasoning approach with explicit inference of the underlying dynamically evolving relational structures.
We demonstrate its effectiveness for multi-agent trajectory prediction and social robot navigation.
arXiv Detail & Related papers (2024-01-22T18:58:22Z) - SSL-Interactions: Pretext Tasks for Interactive Trajectory Prediction [4.286256266868156]
We present SSL-Interactions that proposes pretext tasks to enhance interaction modeling for trajectory prediction.
We introduce four interaction-aware pretext tasks to encapsulate various aspects of agent interactions.
We also propose an approach to curate interaction-heavy scenarios from datasets.
arXiv Detail & Related papers (2024-01-15T14:43:40Z) - Structured Radial Basis Function Network: Modelling Diversity for
Multiple Hypotheses Prediction [51.82628081279621]
Multi-modal regression is important in forecasting nonstationary processes or with a complex mixture of distributions.
A Structured Radial Basis Function Network is presented as an ensemble of multiple hypotheses predictors for regression problems.
It is proved that this structured model can efficiently interpolate this tessellation and approximate the multiple hypotheses target distribution.
arXiv Detail & Related papers (2023-09-02T01:27:53Z) - IPCC-TP: Utilizing Incremental Pearson Correlation Coefficient for Joint
Multi-Agent Trajectory Prediction [73.25645602768158]
IPCC-TP is a novel relevance-aware module based on Incremental Pearson Correlation Coefficient to improve multi-agent interaction modeling.
Our module can be conveniently embedded into existing multi-agent prediction methods to extend original motion distribution decoders.
arXiv Detail & Related papers (2023-03-01T15:16:56Z) - Parallel Reasoning Network for Human-Object Interaction Detection [53.422076419484945]
We propose a new transformer-based method named Parallel Reasoning Network(PR-Net)
PR-Net constructs two independent predictors for instance-level localization and relation-level understanding.
Our PR-Net has achieved competitive results on HICO-DET and V-COCO benchmarks.
arXiv Detail & Related papers (2023-01-09T17:00:34Z) - ProspectNet: Weighted Conditional Attention for Future Interaction
Modeling in Behavior Prediction [5.520507323174275]
We formulate the end-to-end joint prediction problem as a sequential learning process of marginal learning and joint learning of vehicle behaviors.
We propose ProspectNet, a joint learning block that adopts the weighted attention score to model the mutual influence between interactive agent pairs.
We show that ProspectNet outperforms the Cartesian product of two marginal predictions, and achieves comparable performance on the Interactive Motion Prediction benchmarks.
arXiv Detail & Related papers (2022-08-29T19:29:49Z) - Dynamic-Group-Aware Networks for Multi-Agent Trajectory Prediction with
Relational Reasoning [29.294244001911242]
We propose DynGroupNet, a dynamic-group-aware network, which can model time-varying interactions in highly dynamic scenes.
Based on DynGroupNet, we design a prediction system to forecast socially plausible trajectories with dynamic relational reasoning.
arXiv Detail & Related papers (2022-06-27T08:36:56Z) - Online Multi-Agent Forecasting with Interpretable Collaborative Graph
Neural Network [65.11999700562869]
We propose a novel collaborative prediction unit (CoPU), which aggregates predictions from multiple collaborative predictors according to a collaborative graph.
Our methods outperform state-of-the-art works on the three tasks by 28.6%, 17.4% and 21.0% on average.
arXiv Detail & Related papers (2021-07-02T08:20:06Z) - EvolveGraph: Multi-Agent Trajectory Prediction with Dynamic Relational
Reasoning [41.42230144157259]
We propose a generic trajectory forecasting framework with explicit relational structure recognition and prediction via latent interaction graphs.
Considering the uncertainty of future behaviors, the model is designed to provide multi-modal prediction hypotheses.
We introduce a double-stage training pipeline which not only improves training efficiency and accelerates convergence, but also enhances model performance.
arXiv Detail & Related papers (2020-03-31T02:49:23Z) - GAMI-Net: An Explainable Neural Network based on Generalized Additive
Models with Structured Interactions [5.8010446129208155]
An explainable neural network based on generalized additive models with structured interactions (GAMI-Net) is proposed to pursue a good balance between prediction accuracy and model interpretability.
GAMI-Net is a disentangled feedforward network with multiple additiveworks.
Numerical experiments on both synthetic functions and real-world datasets show that the proposed model enjoys superior interpretability.
arXiv Detail & Related papers (2020-03-16T11:51:38Z)
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.