arXiv Analytics

Sign in

arXiv:2008.06041 [cs.CV]AbstractReferencesReviewsResources

DSDNet: Deep Structured self-Driving Network

Wenyuan Zeng, Shenlong Wang, Renjie Liao, Yun Chen, Bin Yang, Raquel Urtasun

Published 2020-08-13Version 1

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.

Related articles: Most relevant | Search more
arXiv:1707.08831 [cs.CV] (Published 2017-07-27)
STN-OCR: A single Neural Network for Text Detection and Text Recognition
arXiv:2003.00836 [cs.CV] (Published 2020-02-11)
Marine life through You Only Look Once's perspective
arXiv:1812.08928 [cs.CV] (Published 2018-12-21)
Slimmable Neural Networks