Intelligent Transportation Systems (ITS) is the IEEE society for automotive broadly including autonomous driving. The Intelligent Vehicles Symposium (IV’2021) is a premier forum sponsored by the IEEE Intelligent Transportation Systems Society (ITSS) and it is the 31st edition of the conference this year. This workshop is organized as a part of IV2021.
You can access the workshop via:
Please make sure you are registered via: Registration | IEEE IV21 (ieee-iv.org)
The registration for this workshop is free.
Aim of scope
Highly automated vehicles are an integral part of everyday traffic and will be used even more in the future with further autonomy. The world is dynamically evolving with an "open-world" nature, creating new domains for highly/fully automated vehicles to learn. Not only are the environmental changes and developments in time and place important, but also the constant developments in the field of hardware such as sensors and software such as development states pose great challenges. So far, AI modules in autonomous driving applications are scalable to a limited extent only. In fact, they only react reliably in limited scenarios. The reason lies in the training strategies applied, in which algorithms are retrained for each new domain. This results in enormous development costs.
This workshop addresses the need for a new training method for artificial intelligence (AI) and researches disruptive methods of "effective" machine learning that enable a more efficient and unrestricted use of AI and thus “scaling of autonomy” in new domains. With this approach, automated vehicles can access new market faster and respond more agilely to new demands.
The scaling of autonomy can be reached by using the already gained knowledge from known domain and focusing on learning gaps to the target domain. This is also called Delta Learning, which can be achieved by applying methods from transfer learning and incremental learning.
The focus of this workshop is on methods and approaches that contribute to the scaling of autonomy solutions (Autonomy@Scale). The goal of these methods is to reduce the dependency on high data volumes, to use different data sources and also to be able to use knowledge that has already been gained from other domains:
- Semi-Supervised, Weakly-Supervised Learning and Unsupervised Learning
- Few/Single Shot Learning
- Multi-Task Learning
- Active Learning
- Continuous Learning and Incremental Learning
- Knowledge Transfer and Knowledge Distillation
- Transfer Learning
- Domain and Task Adaptation
- Uncertainty Estimation and Out of Distribution Detection
- Generative Modelling (e.g. GANs, VAEs)
- Relational Learning (e.g. Graph Networks, Self-Attention)
The application areas for the above methods are different sources of domain shifts and changes. These changes can be caused by:
- Changes in task or label set (e.g. new classes or class imbalance)
- Changes from simulation to real environment and vice versa (sim2real)
- Cross sensor adaptation and using the knowledge from other sensors (with different technology, type, or position and orientation)
- Place and locations such as changes in road domain (e.g. highway to urban) or country (e.g. USA to china) or traffic situations (e.g roundabout to intersection)
- Changes caused by time such as seeing new classes (new mobility concepts such as escooters) or changes in weather or lighting conditions.
The application areas may be applied to different sensor technologies (e.g. camera, LiDAR, and RADAR) and also used in different functional modules such as perception, fusion, behavior and trajectory planning.
The workshop is organized by members of the German funded project of Delta Learning (www.ki-deltalearning.de/en) together with great industry partners such as Mercedes-Benz, BMW, VW, Bosch and ZF.
Call for Workshop Paper
All speakers and their colleagues are encouraged to hand in a paper corresponding to the workshop with Paper submission deadline 30. April 2021: https://its.papercept.net/conferences/scripts/start.pl. Please indicate WS52 as workshop number and x1uip as code when requested.