In this paper, we propose the Deep Structured self-Driving Network (DSDNet), which performs object detection, motion prediction, and motion planning with a single neural network. Towards this goal, we develop a deep structured energy based model which considers the interactions between actors and produces socially consistent multimodal future predictions. Furthermore, DSDNet explicitly exploits the predicted future distributions of actors to plan a safe maneuver by using a structured planning cost. Our sample-based formulation allows us to overcome the difficulty in probabilistic inference of continuous random variables. Experiments on a number of large-scale self driving datasets demonstrate that our model significantly outperforms the state-of-the-art.
@article{arxiv.2008.06041,
title = {DSDNet: Deep Structured self-Driving Network},
author = {Wenyuan Zeng and Shenlong Wang and Renjie Liao and Yun Chen and Bin Yang and Raquel Urtasun},
journal= {arXiv preprint arXiv:2008.06041},
year = {2020}
}