Autonomous Systems. THE NEXT BIG THING.
Kailai Li demonstrates how mobile robot systems can operate safely in dynamic environments. In particular, the use of LiDAR sensors is one of the focuses of his research, and he conducts realworld experiments using LiDARs mounted on various different platforms, helmet, backpack, handheld platform, and robot dog.
Dat je met autonome systemen zelfs de spelregels kunt veranderen, laat Frederik Nieuwenhuys (CEO, Picnic, Nederland) zien. Als online supermarkt heeft het bedrijf het traditionele distributiemodel opnieuw ontworpen: van geautomatiseerde fulfilmentcentra en datagedreven routeplanning tot fijnmazige last-mile distributie en directe digitale klantinteractie. Autonome systemen spelen daarbij een sleutelrol — zowel in het logistieke distributiekanaal als in het klantproces, en vooral in de slimme koppeling tussen beide.
Er wordt geschetst hoe autonome systemen en AI de komende jaren de zorg ingrijpend zullen veranderen — van diagnose en behandeling tot logistiek, monitoring en ondersteuning van zorgprofessionals, zowel in de cure als in de care. Klein Nagelvoort laat zien waar volgens het UMCG de grootste kansen en uitdagingen liggen, welke toepassingen zich nu al aandienen en op welke thema’s de komende jaren wordt ingezet. Tegelijk benadrukt zij dat de invoering van autonome systemen in de zorg complex is, door hoge eisen aan veiligheid, betrouwbaarheid en regelgeving.
KUKA Group is among the world’s leading players in industrial robotics, providing complete solutions for automated production, logistics, and intralogistics systems. From robotic arms and autonomous mobile robots to fully integrated factory and warehouse solutions, KUKA technology forms the backbone of modern industrial automation. In his contribution, Schwaiger outlines how the next step is being taken from traditional robotics to large-scale autonomous ecosystems.
Timo Roestenberg laat zien hoe hightech machinebouwers hun traditionele producten transformeren tot intelligente, zelfsturend opererende systemen. Hij presenteert voorbeelden uit de defensie-industrie, waar autonome toepassingen inmiddels vooroplopen en waardevolle lessen bieden voor civiele sectoren.
Ken Flemming laat vervolgens zien hoe zijn bedrijf vision-AI ontwikkelt voor zeer nauwkeurige detectie en pick-and-place van objecten in logistiek en foodprocessing. Doordat Fizyr’s technologie naadloos integreert met gangbare robotica en bestaande hardware, zijn brede toepasbaarheid en snelle opschaling mogelijk.
The role of geospatial data and precise positioning in the development of digitalisation and robotics has grown drastically. This evolution challenges the public sector to adapt their spatial data strategy to ensure accuracy, timeliness and sharing of geospatial data and positioning to meet the new needs arising from developments such as intelligent traffic, drones, digitalisation of forestry and agriculture, global trading and finance and other location-based services. Additionally, digital twins, that model real-world processes, such as climate or oceanic digital twins, need real-time accurate geospatial data. As part of these new applications, it is vital to understand how we can share geospatial data efficiently for the needs of real time decision making.
The internal reasoning of intelligent cyber-physical systems gets more complex and opaque with their increasing autonomy. This creates challenges for ensuring safety and correctness during development, diagnosis, and interaction. Collaboration between humans and machines is particularly prone to misunderstandings and false expectations, leading to poor results and even dangerous accidents. Extra effort is needed to regain transparency through explanations of internal behaviour. However, not all explanations are appropriate or useful. They must be tailored to a certain purpose, their recipient, and their situational context. Also, explanations must address the overall system behaviour, not only internal AI algorithms. This talk gives an overview of requirements for useful explanations, shows how tailored explanations can be generated autonomously, and presents challenging research questions.
Whether you are watching a launch site catching a starship booster on reentry or sitting in a self-driving car that is changing lanes, the technology behind these actions is automatic control. Control is a discipline at the intersection of engineering, math and physics that provides the tools to make machines behave the way you want.
At the core of a successful automatic control design is a good physical-mathematical description of the system you want to control. This description is usually hard to get, and even if you have it, it is unlikely that you will be able to immediately design a controller for it.
This talk will highlight recent efforts by the control systems community to automate control design using data. It will describe the fundamental principles behind an end-to-end process that, after collecting experimental data from the system to be controlled, encodes the data into an optimization program whose solution yields a provably correct control algorithm.
The talk will discuss what is left to be done and how these results fit in a world where data and machine learning are taking over.
Generative AI (GenAI) has been praised to automate and accelerate engineering processes even beyond code and test generation. The role of today’s software engineers even for embedded systems is being redefined and expertise on system architecture, orchestration, and large-scale refactoring is defining daily activities especially in the context of agentic software engineering. In this talk, the speaker is sharing selected highlights and critical reflections on the benefits and challenges of GenAI from several research projects in the area of automotive software engineering. A particular light is also shed on insights from and reflections about the Swedish research funding landscape in the context of AI, autonomous systems, and software.