RAIN: Reinforced Hybrid Attention Inference Network for Motion
Forecasting
- URL: http://arxiv.org/abs/2108.01316v1
- Date: Tue, 3 Aug 2021 06:30:30 GMT
- Title: RAIN: Reinforced Hybrid Attention Inference Network for Motion
Forecasting
- Authors: Jiachen Li and Fan Yang and Hengbo Ma and Srikanth Malla and Masayoshi
Tomizuka and Chiho Choi
- Abstract summary: We propose a generic motion forecasting framework with dynamic key information selection and ranking based on a hybrid attention mechanism.
The framework is instantiated to handle multi-agent trajectory prediction and human motion forecasting tasks.
We validate the framework on both synthetic simulations and motion forecasting benchmarks in different domains.
- Score: 34.54878390622877
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Motion forecasting plays a significant role in various domains (e.g.,
autonomous driving, human-robot interaction), which aims to predict future
motion sequences given a set of historical observations. However, the observed
elements may be of different levels of importance. Some information may be
irrelevant or even distracting to the forecasting in certain situations. To
address this issue, we propose a generic motion forecasting framework (named
RAIN) with dynamic key information selection and ranking based on a hybrid
attention mechanism. The general framework is instantiated to handle
multi-agent trajectory prediction and human motion forecasting tasks,
respectively. In the former task, the model learns to recognize the relations
between agents with a graph representation and to determine their relative
significance. In the latter task, the model learns to capture the temporal
proximity and dependency in long-term human motions. We also propose an
effective double-stage training pipeline with an alternating training strategy
to optimize the parameters in different modules of the framework. We validate
the framework on both synthetic simulations and motion forecasting benchmarks
in different domains, demonstrating that our method not only achieves
state-of-the-art forecasting performance, but also provides interpretable and
reasonable hybrid attention weights.
Related papers
- AMP: Autoregressive Motion Prediction Revisited with Next Token Prediction for Autonomous Driving [59.94343412438211]
We introduce the GPT style next token motion prediction into motion prediction.
Different from language data which is composed of homogeneous units -words, the elements in the driving scene could have complex spatial-temporal and semantic relations.
We propose to adopt three factorized attention modules with different neighbors for information aggregation and different position encoding styles to capture their relations.
arXiv Detail & Related papers (2024-03-20T06:22:37Z) - Disentangled Neural Relational Inference for Interpretable Motion
Prediction [38.40799770648501]
We develop a variational auto-encoder framework that integrates graph-based representations and timesequence models.
Our model infers dynamic interaction graphs augmented with interpretable edge features that characterize the interactions.
We validate our approach through extensive experiments on both simulated and real-world datasets.
arXiv Detail & Related papers (2024-01-07T22:49:24Z) - FFINet: Future Feedback Interaction Network for Motion Forecasting [46.247396728154904]
We propose a novel Future Feedback Interaction Network (FFINet) to aggregate features the current observations and potential future interactions for trajectory prediction.
Our FFINet achieves the state-of-the-art performance on Argoverse 1 and Argoverse 2 motion forecasting benchmarks.
arXiv Detail & Related papers (2023-11-08T07:57:29Z) - Motion-Scenario Decoupling for Rat-Aware Video Position Prediction:
Strategy and Benchmark [49.58762201363483]
We introduce RatPose, a bio-robot motion prediction dataset constructed by considering the influence factors of individuals and environments.
We propose a Dual-stream Motion-Scenario Decoupling framework that effectively separates scenario-oriented and motion-oriented features.
We demonstrate significant performance improvements of the proposed textitDMSD framework on different difficulty-level tasks.
arXiv Detail & Related papers (2023-05-17T14:14:31Z) - Joint Forecasting of Panoptic Segmentations with Difference Attention [72.03470153917189]
We study a new panoptic segmentation forecasting model that jointly forecasts all object instances in a scene.
We evaluate the proposed model on the Cityscapes and AIODrive datasets.
arXiv Detail & Related papers (2022-04-14T17:59:32Z) - Leveraging Smooth Attention Prior for Multi-Agent Trajectory Prediction [32.970169015894705]
We formulate an attention model for multi-agent interactions based on a total variation temporal smoothness prior.
We show its advantages in terms of prediction accuracy by comparing it with the state-of-the-art approaches on both synthetic and naturalistic driving data.
arXiv Detail & Related papers (2022-03-08T21:54:28Z) - Investigating Pose Representations and Motion Contexts Modeling for 3D
Motion Prediction [63.62263239934777]
We conduct an indepth study on various pose representations with a focus on their effects on the motion prediction task.
We propose a novel RNN architecture termed AHMR (Attentive Hierarchical Motion Recurrent network) for motion prediction.
Our approach outperforms the state-of-the-art methods in short-term prediction and achieves much enhanced long-term prediction proficiency.
arXiv Detail & Related papers (2021-12-30T10:45:22Z) - Dyadic Human Motion Prediction [119.3376964777803]
We introduce a motion prediction framework that explicitly reasons about the interactions of two observed subjects.
Specifically, we achieve this by introducing a pairwise attention mechanism that models the mutual dependencies in the motion history of the two subjects.
This allows us to preserve the long-term motion dynamics in a more realistic way and more robustly predict unusual and fast-paced movements.
arXiv Detail & Related papers (2021-12-01T10:30:40Z) - Panoptic Segmentation Forecasting [71.75275164959953]
Our goal is to forecast the near future given a set of recent observations.
We think this ability to forecast, i.e., to anticipate, is integral for the success of autonomous agents.
We develop a two-component model: one component learns the dynamics of the background stuff by anticipating odometry, the other one anticipates the dynamics of detected things.
arXiv Detail & Related papers (2021-04-08T17:59:16Z) - Social-WaGDAT: Interaction-aware Trajectory Prediction via Wasserstein
Graph Double-Attention Network [29.289670231364788]
In this paper, we propose a generic generative neural system for multi-agent trajectory prediction.
We also employ an efficient kinematic constraint layer applied to vehicle trajectory prediction.
The proposed system is evaluated on three public benchmark datasets for trajectory prediction.
arXiv Detail & Related papers (2020-02-14T20:11:13Z)
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.