DLAD-BP 2019

Intelligent Transportation Systems (ITS) is the IEEE society for automotive broadly including autonomous driving. The Intelligent Transportation Systems Conference (ITSC'19) (link) is the annual flagship conference of the IEEE Intelligent Transportation Systems Society and this year it is the 22nd edition of the conference this year and will be held at Auckland, New Zealand. This workshop is the third edition of our workshop ‘Deep Learning for Autonomous Driving’ (DLAD) focused on deep learning applications beyond perception like fusion, mapping, planning and control. Hence it is called DLAD-BP workshop. The program of previous two editions is available here : 3D-DLAD at IV2019 Paris France, and DLAD at ITSC 2017 Yokohama, Japan.

Deep Learning has become a de-facto tool in Computer Vision and 3D processing by boosting performance and accuracy for diverse tasks such as object classification, detection, optical flow estimation, motion segmentation, mapping, etc. Deep Learning has rapidly progressed in the perception domain, tackling fields such as computer vision and lidar point-cloud processing. This workshop is an attempt to bridge the gap between in Deep Learning and machine learning methods applied to further vital tasks in the pipeline of a complete autonomous driving system. This includes sensor fusion for object detection and tracking, dynamic shared maps, trajectory optimization, path planning for real word scenarios, machine learning methods for vehicle controllers, vehicle-to-vehicle and environment communication, etc. This workshop aims to bring together the latest research of deep learning applied to various problems in Autonomous Driving beyond just perception, both from an academic research and industry in the domain of autonomous driving. We are soliciting contributions in (but not limited to) the following topics:

List of topics:

• Deep learning based sensor fusion and target tracking (camera, lidar, radar, ultrasound)

• Automatic sensor (Camera-Lidar, Lidar-Lidar, and others) calibration, End to End sensor Registration

• Dynamic Trajectory planning for real world traffic scenarios

• Deep Reinforcement learning for Motion Planning

• Shared dynamic maps for Multiagent Sensor Fusion

• Challenges of deployment in a commercial system (Functional safety & High accuracy)

• Advanced topics in Deep Learning (Meta-learning, Multi-task learning, Self-supervised, weakly-supervised, End-to-End learning)

• Other ML algorithms jointly used with Deep Learning (eg. PGMs, Probabilistic Programming)

• Vehicle-to-Vehicle and Vehicle-to-Environment communication

References:

1. Caesar, Holger, et al. "nuScenes: A multimodal dataset for autonomous driving." (2019). [Dataset]

2. Does computer vision matter for action? Brady Zhou, Philipp Krähenbühl, Vladlen Koltun Science Robotics, 4(30), 2019

3. Robust Semantic Segmentation in Adverse Weather Conditions by means of Sensor Data Fusion, A. Pfeuffer, K. Dietmayer 2019

4. Schneider, Nick, et al. "Regnet: Multimodal sensor registration using deep neural networks." 2017 IEEE intelligent vehicles symposium (IV). IEEE, 2017.

5. Feng, Di, et al. "Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges." arXiv preprint (2019).

6. LaValle, Steven M. Planning algorithms. Cambridge university press, 2006.

7. Mirowski, Piotr, et al. "Learning to navigate in cities without a map." NeurIPS 2018.

8. Subosits, John, and J. Christian Gerdes. "From the Racetrack to the Road: Real-time Trajectory Replanning for Autonomous Driving." Intelligent Vehicles (2019).

9. Sobh, Ibrahim, et al. "End-to-end multi-modal sensors fusion system for urban automated driving." (2018).

10. Devineau, Guillaume, et al. "Coupled Longitudinal and Lateral Control of a Vehicle using Deep Learning." 2018 Intelligent Transportation Systems (ITSC). IEEE, 2018.

11. Amini, Alexander, et al. "Variational autoencoder for end-to-end control of autonomous driving with novelty detection and training de-biasing." (IROS). IEEE, 2018.

12. Deep Single Image Camera Calibration with Radial Distortion CVPR 2019 [pdf]

13. Automatic Calibration of Multiple Cameras and Depth Sensors with a Spherical Target, Julius Kümmerle, Tilman Kühner, Martin Lauer, IROS, IEEE 2018

14. Iyer, Ganesh, et al. "Calibnet: Geometrically supervised extrinsic calibration using 3D spatial transformer networks." 2018 Intelligent Robots and Systems (IROS). IEEE, 2018.

15. Altché, Florent, and Arnaud de La Fortelle. "An LSTM network for highway trajectory prediction." 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC). IEEE, 2017.

Previous Editions:

• 3D-Deep Learning for Automated Driving [website] IV 2019, Paris

• Deep Learning for Automated Driving [website] ITSC 2017, Japan