For the second year in a row, KI Delta Learning organized a workshop on Autonomy@Scale during the Intelligent Vehicles Symposium (IV2022). The symposium is sponsored by the IEEE Intelligent Transportation Systems Society (ITSS) and is an important industry event. It took place in Aachen between 5-9 June 2022.
The world is dynamically evolving with an "open-world" nature, creating new domains for highly/fully automated vehicles to learn. The environmental changes and developments are not only important for in time and location aspects, but also the constant developments in the field of hardware, such as sensors, software, and development states, pose great challenges.
To meet this "open-world" scenario, the autonomous driving systems must be adaptable and scalable. In this context, the workshop addressed the need for new training methods for AI systems and researches. Disruptive methods of "effective" machine learning can enable a more efficient and unrestricted use of AI and thus “scaling of autonomy” in new domains.
The workshop thus covered, among others, the topics of domain and task adaption, active learning and generative modeling. In various presentations, the progress made in the KI Delta Learning project was presented and the topic of scaling was examined from different angles. In addition, three papers were presented that were published in the course of the workshop. Thus, the workshop seamlessly followed the success of last year's workshop. More about the agenda and the speakers of the workshop can be found here: IV2022 Workshop