Wayformer: Motion Forecasting via Simple &amp; Efficient Attention Networks

Nayakanti, Nigamaa; Al‐Rfou, Rami; Zhou, Aurick; Goel, Kratarth; Refaat, Khaled S.; Sapp, Benjamin

doi:10.1109/icra48891.2023.10160609

Cited by 86 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Trajectory forecasts must include precisely 16 position samples, each corresponding to the next 8 seconds and sampled at a rate of 2 Hz. Wayformer's attention-based scene encoder/decoder is modest [16]. Nigamaa Nayakanti and all study scene encoder early, late, and hierarchical input fusion [16].…”

Section: Leaderboard Best Solutionsmentioning

confidence: 99%

See 1 more Smart Citation

An Empirical Analysis of Trajectory Prediction Techniques for Motion Prediction in Waymo Dataset

Arora,

Wason

2023

3C Tecnología

View full text Add to dashboard Cite

The Waymo is the prime and most varied autonomous driving dataset that improves and enhances itself every year. Motion Prediction is a considerable challenge in 2023. This manuscript analyses five considerable methods namely MTR-A, Wayformer, DenseTNT, Golfer and MultiPath++ for their technology applied. The analysis revealed that the Transformer network could achieve a state of the art trajectory prediction as well as scale to many workloads.

show abstract

Section: Leaderboard Best Solutionsmentioning

confidence: 99%

“…Wayformer's attention-based scene encoder/decoder is modest [16]. Nigamaa Nayakanti and all study scene encoder early, late, and hierarchical input fusion [16]. Factorized or latent query attention balances efficiency and quality for each fusion type.…”

Section: Leaderboard Best Solutionsmentioning

confidence: 99%

An Empirical Analysis of Trajectory Prediction Techniques for Motion Prediction in Waymo Dataset

Arora,

Wason

2023

3C Tecnología

View full text Add to dashboard Cite

show abstract

“…Given past observations of objects in a dynamic scene, motion forecasting aims to predict future trajectories of the objects. Current state-of-the-art methods [12,22,25,27,42,56,60] learn the complex and nuanced interactions from data through deep neural networks. Some other methods study joint 3D object detection and motion forecasting [1,4,5,20,23,28,48,61], where detection can be an intermediate task.…”

Section: Related Workmentioning

confidence: 99%

Offboard 3D Object Detection from Point Cloud Sequences

Zhou

Najibi

et al. 2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

129

View full text Add to dashboard Cite

Occluded and long-range objects are ubiquitous and challenging for 3D object detection. Point cloud sequence data provide unique opportunities to improve such cases, as an occluded or distant object can be observed from different viewpoints or gets better visibility over time. However, the efficiency and effectiveness in encoding long-term sequence data can still be improved. In this work, we propose MoDAR, using motion forecasting outputs as a type of virtual modality, to augment LiDAR point clouds. The MoDAR modality propagates object information from temporal contexts to a target frame, represented as a set of virtual points, one for each object from a waypoint on a forecasted trajectory. A fused point cloud of both raw sensor points and the virtual points can then be fed to any off-the-shelf pointcloud based 3D object detector. Evaluated on the Waymo Open Dataset, our method significantly improves prior art detectors by using motion forecasting from extra-long sequences (e.g. 18 seconds), achieving new state of the arts, while not adding much computation overhead.

show abstract

“…In existing works, researchers have primarily focused on the construction of encoders and decoders. For encoders, the emphasis is on how to better aggregate HD map features [5,6]. As for decoders, the focus is on whether to use regression-based methods [2,7] or target-based methods [8,9], and how to construct trajectory optimization modules [10].…”

Section: Introductionmentioning

confidence: 99%

Q‐EANet: Implicit social modeling for trajectory prediction via experience‐anchored queries

Chen,

Wang,

Wang

et al. 2023

IET Intelligent Trans Sys

View full text Add to dashboard Cite

Accurately predicting the future trajectory and behavior of traffic participants is crucial for the maneuvers of self‐driving vehicles. Many existing works employed a learning‐based “encoder‐interactor‐decoder” structure, but they often fail to clearly articulate the relationship between module selections and real‐world interactions. As a result, these approaches tend to rely on a simplistic stacking of attention modules. To address this issue, a trajectory prediction network (Q‐EANet) is presented in this study, which integrates GRU encoders, MLPs and attention modules. By introducing a new explanatory rule, it makes a contribution to interpretable modeling, models the entire trajectory prediction process via an implicit social modeling formula. Inspired by the anchoring effect in decision psychology, the prediction task is formulated as an information query process that occurs before traffic participants make decisions. Specifically, Q‐EANet uses GRUs to encode features and utilizes attention modules to aggregates interaction information for generating the target trajectory anchors. Then, queries are introduced for further interaction. These queries, along with the trajectory anchors with added Gaussian noise, are then processed by a GRU‐based decoder. The final prediction results are obtained through a Laplace MDN. Experimental results on the several benchmarks demonstrate the effectiveness of Q‐EANet in trajectory prediction tasks. Compared to the existing works, the proposed method achieves state‐of‐the‐art performance with only simple module design. The code for this work is publicly available at https://github.com/Jctrp/socialea.

show abstract

Wayformer: Motion Forecasting via Simple & Efficient Attention Networks

Cited by 86 publications

References 21 publications

An Empirical Analysis of Trajectory Prediction Techniques for Motion Prediction in Waymo Dataset

An Empirical Analysis of Trajectory Prediction Techniques for Motion Prediction in Waymo Dataset

Offboard 3D Object Detection from Point Cloud Sequences

Q‐EANet: Implicit social modeling for trajectory prediction via experience‐anchored queries

Contact Info

Product

Resources

About