Improving Diversity of Multiple Trajectory Prediction based on
Map-adaptive Lane Loss
- URL: http://arxiv.org/abs/2206.08641v1
- Date: Fri, 17 Jun 2022 09:09:51 GMT
- Title: Improving Diversity of Multiple Trajectory Prediction based on
Map-adaptive Lane Loss
- Authors: Sanmin Kim, Hyeongseok Jeon, Junwon Choi, and Dongsuk Kum
- Abstract summary: This study proposes a novel loss function, textitLane Loss, that ensures map-adaptive diversity and accommodates geometric constraints.
Experiments performed on the Argoverse dataset show that the proposed method significantly improves the diversity of the predicted trajectories.
- Score: 12.963269946571476
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Prior arts in the field of motion predictions for autonomous driving tend to
focus on finding a trajectory that is close to the ground truth trajectory.
Such problem formulations and approaches, however, frequently lead to loss of
diversity and biased trajectory predictions. Therefore, they are unsuitable for
real-world autonomous driving where diverse and road-dependent multimodal
trajectory predictions are critical for safety. To this end, this study
proposes a novel loss function, \textit{Lane Loss}, that ensures map-adaptive
diversity and accommodates geometric constraints. A two-stage trajectory
prediction architecture with a novel trajectory candidate proposal module,
\textit{Trajectory Prediction Attention (TPA)}, is trained with Lane Loss
encourages multiple trajectories to be diversely distributed, covering feasible
maneuvers in a map-aware manner. Furthermore, considering that the existing
trajectory performance metrics are focusing on evaluating the accuracy based on
the ground truth future trajectory, a quantitative evaluation metric is also
suggested to evaluate the diversity of predicted multiple trajectories. The
experiments performed on the Argoverse dataset show that the proposed method
significantly improves the diversity of the predicted trajectories without
sacrificing the prediction accuracy.
Related papers
- Certified Human Trajectory Prediction [66.1736456453465]
Tray prediction plays an essential role in autonomous vehicles.
We propose a certification approach tailored for the task of trajectory prediction.
We address the inherent challenges associated with trajectory prediction, including unbounded outputs, and mutli-modality.
arXiv Detail & Related papers (2024-03-20T17:41:35Z) - Knowledge-aware Graph Transformer for Pedestrian Trajectory Prediction [15.454206825258169]
Predicting pedestrian motion trajectories is crucial for path planning and motion control of autonomous vehicles.
Recent deep learning-based prediction approaches mainly utilize information like trajectory history and interactions between pedestrians.
This paper proposes a graph transformer structure to improve prediction performance.
arXiv Detail & Related papers (2024-01-10T01:50:29Z) - PBP: Path-based Trajectory Prediction for Autonomous Driving [3.640190809479174]
Trajectory prediction plays a crucial role in the autonomous driving stack.
Goal-based prediction models have gained traction in recent years for addressing the multimodal nature of future trajectories.
arXiv Detail & Related papers (2023-09-07T14:45:41Z) - Bridging the Gap Between Multi-Step and One-Shot Trajectory Prediction
via Self-Supervision [2.365702128814616]
Accurate vehicle trajectory prediction is an unsolved problem in autonomous driving.
We propose a middle-ground where multiple trajectory segments are chained together.
Our proposed Multi-Branch Self-Supervised Predictor receives additional training on new predictions starting at intermediate future segments.
arXiv Detail & Related papers (2023-06-06T02:46:28Z) - Graph-based Spatial Transformer with Memory Replay for Multi-future
Pedestrian Trajectory Prediction [13.466380808630188]
We propose a model to forecast multiple paths based on a historical trajectory.
Our method can exploit the spatial information as well as correct the temporally inconsistent trajectories.
Our experiments show that the proposed model achieves state-of-the-art performance on multi-future prediction and competitive results for single-future prediction.
arXiv Detail & Related papers (2022-06-12T10:25:12Z) - Adaptive Trajectory Prediction via Transferable GNN [74.09424229172781]
We propose a novel Transferable Graph Neural Network (T-GNN) framework, which jointly conducts trajectory prediction as well as domain alignment in a unified framework.
Specifically, a domain invariant GNN is proposed to explore the structural motion knowledge where the domain specific knowledge is reduced.
An attention-based adaptive knowledge learning module is further proposed to explore fine-grained individual-level feature representation for knowledge transfer.
arXiv Detail & Related papers (2022-03-09T21:08:47Z) - Trajectory Forecasting from Detection with Uncertainty-Aware Motion
Encoding [121.66374635092097]
Trajectories obtained from object detection and tracking are inevitably noisy.
We propose a trajectory predictor directly based on detection results without relying on explicitly formed trajectories.
arXiv Detail & Related papers (2022-02-03T09:09:56Z) - Divide-and-Conquer for Lane-Aware Diverse Trajectory Prediction [71.97877759413272]
Trajectory prediction is a safety-critical tool for autonomous vehicles to plan and execute actions.
Recent methods have achieved strong performances using Multi-Choice Learning objectives like winner-takes-all (WTA) or best-of-many.
Our work addresses two key challenges in trajectory prediction, learning outputs, and better predictions by imposing constraints using driving knowledge.
arXiv Detail & Related papers (2021-04-16T17:58:56Z) - Trajectory Prediction in Autonomous Driving with a Lane Heading
Auxiliary Loss [1.1470070927586014]
We propose a loss function which enhances trajectory prediction models by enforcing expected driving rules on all predicted modes.
Our contribution to trajectory prediction is twofold; we propose a new metric which addresses failure cases of the off-road rate metric.
We then use this auxiliary loss to extend the the standard multiple trajectory prediction (MTP) and MultiPath models.
arXiv Detail & Related papers (2020-11-12T22:51:25Z) - 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) - TPNet: Trajectory Proposal Network for Motion Prediction [81.28716372763128]
Trajectory Proposal Network (TPNet) is a novel two-stage motion prediction framework.
TPNet first generates a candidate set of future trajectories as hypothesis proposals, then makes the final predictions by classifying and refining the proposals.
Experiments on four large-scale trajectory prediction datasets, show that TPNet achieves the state-of-the-art results both quantitatively and qualitatively.
arXiv Detail & Related papers (2020-04-26T00:01:49Z)
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.