Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representations

Abstract

Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representations","In this paper we propose a novel end-to-end learnable network that performs joint perception, prediction and motion planning for self-driving vehicles and produces interpretable intermediate representations. Unlike existing neural motion planners, our motion planning costs are consistent with our perception and prediction estimates. This is achieved by a novel differentiable semantic occupancy representation that is explicitly used as cost by the motion planning process. Our network is learned end-to-end from human demonstration. Our experiments in a large-scale manual-driving dataset and closed-loop simulation show that the proposed model significantly outperforms state-of-the-art planners in imitating the human behaviors while producing much safer trajectories.

Cite

Text

Sadat et al. "Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representations." Proceedings of the European Conference on Computer Vision (ECCV), 2020. doi:10.1007/978-3-030-58592-1_25

Markdown

[Sadat et al. "Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representations." Proceedings of the European Conference on Computer Vision (ECCV), 2020.](https://mlanthology.org/eccv/2020/sadat2020eccv-perceive/) doi:10.1007/978-3-030-58592-1_25

BibTeX

@inproceedings{sadat2020eccv-perceive,
  title     = {{Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representations}},
  author    = {Sadat, Abbas and Casas, Sergio and Ren, Mengye and Wu, Xinyu and Dhawan, Pranaab and Urtasun, Raquel},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2020},
  doi       = {10.1007/978-3-030-58592-1_25},
  url       = {https://mlanthology.org/eccv/2020/sadat2020eccv-perceive/}
}