Call for Papers

With the significant progress in autonomous vehicle technology, the dream of autonomous vehicles has become closer than ever. The autonomous vehicle system is expected to grow faster and various of commercial products will become available within a decade. To realize the dream, the integration of computer vision, sensing technologies, control system, signal processing, communication, hardware design, and machine learning into autonomous vehicles is evitable for correctly understanding the environments and making correct and safe decisions. For example, the core technologies include: a) positioning with high resolution maps, b) fast and reliable communications, c) energy-efficient hardware for real-time performance, c) machine learning that intelligently recognizes the related objects and environments, resists to the adversarial attacks, and makes correct control decicions, d) resilient and friendly platforms for deploying the intelligent systems, e) agile and flexible vehicle control system, f) affordable sensors that can deal with different environment conditions. The special session will cover all these topics. The topics of interest include, but are not limited to:

- Domain-adaptive object recognitiong;
- Pseudo-liDAR point cloud interpolation;
- Multi-modal learning for intelligent System;
- Reinforcement learning for autonomous driving;
- Self-supervised/unsupervised visual environment perception;
- Human-like traffic scene understanding;
- Semantic/instance driving scene segmentation and semantic mapping;
- Drivable area detection and lane segmentation;
- Car/pedestrian/object/obstacle detection/tracking and 3D localization;
- Hardware design for autonomous driving system;
- Driver status monitoring and human-car interfaces;
- Deep/machine learning and image analysis for car perception;
- Adversarial attack for car perception;


Maximum Length of a Paper


Each full paper should be limited to 6-8 pages (6 pages limit + references).

Organizers


Bing-Fei Wu
Wen-Huang Cheng
Ching-Chun Huang
Hong-Han Shuai