Obstacle-Transformer: A Trajectory Prediction Network Based on Surrounding Trajectories
This work addresses trajectory prediction for autonomous systems, but it is incremental as it builds on existing transformer-based methods with a novel feature extraction approach.
The paper tackles the problem of increasing inference time in trajectory prediction models by proposing Obstacle-Transformer, which uses surrounding trajectories as obstacles instead of scene images or point clouds, achieving competitive performance on ETH and UCY datasets.
Recurrent Neural Network, Long Short-Term Memory, and Transformer have made great progress in predicting the trajectories of moving objects. Although the trajectory element with the surrounding scene features has been merged to improve performance, there still exist some problems to be solved. One is that the time series processing models will increase the inference time with the increase of the number of prediction sequences. Another lies in which the features can not be extracted from the scene's image and point cloud in some situations. Therefore, this paper proposes an Obstacle-Transformer to predict trajectory in a constant inference time. An ``obstacle'' is designed by the surrounding trajectory rather than images or point clouds, making Obstacle-Transformer more applicable in a wider range of scenarios. Experiments are conducted on ETH and UCY data sets to verify the performance of our model.