Bootstrap Motion Forecasting With Self-Consistent Constraints
- URL: http://arxiv.org/abs/2204.05859v4
- Date: Sun, 26 Nov 2023 10:44:43 GMT
- Title: Bootstrap Motion Forecasting With Self-Consistent Constraints
- Authors: Maosheng Ye, Jiamiao Xu, Xunnong Xu, Tengfei Wang, Tongyi Cao, Qifeng
Chen
- Abstract summary: We present a novel framework to bootstrap Motion forecasting with Self-consistent Constraints.
The motion forecasting task aims at predicting future trajectories of vehicles by incorporating spatial and temporal information from the past.
We show that our proposed scheme consistently improves the prediction performance of several existing methods.
- Score: 52.88100002373369
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We present a novel framework to bootstrap Motion forecasting with
Self-consistent Constraints (MISC). The motion forecasting task aims at
predicting future trajectories of vehicles by incorporating spatial and
temporal information from the past. A key design of MISC is the proposed Dual
Consistency Constraints that regularize the predicted trajectories under
spatial and temporal perturbation during training. Also, to model the
multi-modality in motion forecasting, we design a novel self-ensembling scheme
to obtain accurate teacher targets to enforce the self-constraints with
multi-modality supervision. With explicit constraints from multiple teacher
targets, we observe a clear improvement in the prediction performance.
Extensive experiments on the Argoverse motion forecasting benchmark and Waymo
Open Motion dataset show that MISC significantly outperforms the
state-of-the-art methods. As the proposed strategies are general and can be
easily incorporated into other motion forecasting approaches, we also
demonstrate that our proposed scheme consistently improves the prediction
performance of several existing methods.
Related papers
- Annealed Winner-Takes-All for Motion Forecasting [48.200282332176094]
We show how an aWTA loss can be integrated with state-of-the-art motion forecasting models to enhance their performance.
Our approach can be easily incorporated into any trajectory prediction model normally trained using WTA.
arXiv Detail & Related papers (2024-09-17T13:26:17Z) - Reliable Trajectory Prediction and Uncertainty Quantification with Conditioned Diffusion Models [11.308331231957588]
This work introduces the conditioned Vehicle Motion Diffusion (cVMD) model, a novel network architecture for highway trajectory prediction using diffusion models.
Central to the architecture of cVMD is its capacity to perform uncertainty quantification, a feature that is crucial in safety-critical applications.
Experiments show that the proposed architecture achieves competitive trajectory prediction accuracy compared to state-of-the-art models.
arXiv Detail & Related papers (2024-05-23T10:01:39Z) - Self-Supervised Class-Agnostic Motion Prediction with Spatial and Temporal Consistency Regularizations [53.797896854533384]
Class-agnostic motion prediction methods directly predict the motion of the entire point cloud.
While most existing methods rely on fully-supervised learning, the manual labeling of point cloud data is laborious and time-consuming.
We introduce three simple spatial and temporal regularization losses, which facilitate the self-supervised training process effectively.
arXiv Detail & Related papers (2024-03-20T02:58:45Z) - Towards Safe and Reliable Autonomous Driving: Dynamic Occupancy Set Prediction [12.336412741837407]
This study introduces a novel method for Dynamic Occupancy Set (DOS) prediction, it effectively combines advanced trajectory prediction networks with a DOS prediction module.
The innovative contributions of this study include the development of a novel DOS prediction model specifically tailored for navigating complex scenarios.
arXiv Detail & Related papers (2024-02-29T17:36:39Z) - MTR++: Multi-Agent Motion Prediction with Symmetric Scene Modeling and
Guided Intention Querying [110.83590008788745]
Motion prediction is crucial for autonomous driving systems to understand complex driving scenarios and make informed decisions.
In this paper, we propose Motion TRansformer (MTR) frameworks to address these challenges.
The initial MTR framework utilizes a transformer encoder-decoder structure with learnable intention queries.
We introduce an advanced MTR++ framework, extending the capability of MTR to simultaneously predict multimodal motion for multiple agents.
arXiv Detail & Related papers (2023-06-30T16:23:04Z) - 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) - Raising context awareness in motion forecasting [30.86735692571529]
We introduce CAB, a motion forecasting model equipped with a training procedure designed to promote the use of semantic contextual information.
We also introduce two novel metrics -- dispersion and convergence-to-range -- to measure the temporal consistency of successive forecasts.
Our method is evaluated on the widely adopted nuScenes Prediction benchmark.
arXiv Detail & Related papers (2021-09-16T15:25:27Z) - Individual Mobility Prediction: An Interpretable Activity-based Hidden
Markov Approach [6.1938383008964495]
This study develops an activity-based modeling framework for individual mobility prediction.
We show that the proposed model can achieve similar prediction performance as the state-of-the-art long-term short-term memory (LSTM) model.
arXiv Detail & Related papers (2021-01-11T16:11:27Z) - The Importance of Prior Knowledge in Precise Multimodal Prediction [71.74884391209955]
Roads have well defined geometries, topologies, and traffic rules.
In this paper we propose to incorporate structured priors as a loss function.
We demonstrate the effectiveness of our approach on real-world self-driving datasets.
arXiv Detail & Related papers (2020-06-04T03:56:11Z)
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.