全名ZF Friedrichshafen AG(弗里德里西港ZF股份公司),德国采埃孚(ZF)集团,简称ZF公司,是当今世界上最重要的传动系统产品专业制造厂家之一。
Accurately estimating and predicting tyre-road friction is essential for optimising safety-critical control strategies and task planning in advanced driver assistance and autonomous driving systems. Recent approaches propose the integration of camera and vehicle dynamics-based estimation methods. These hybrid approaches achieve more reliable estimation but cannot retain and recall this information for a location. They are also unable to quantify uncertainty in tyre-road friction with respect to changing road conditions. This paper proposes a novel scheme for estimating tyre-road friction under unknown road conditions. A 2D map of the environment is combined with a vehicle dynamics model to enable joint estimation of environment and vehicle state, including tyre-road friction. A tailored sequential Monte Carlo scheme enables online updating of map information and allows for recall upon revisiting a location. Results show that uncertainty in tyre-road friction can be reduced during successive trials of emergency braking. As a result, braking distance predictions become more accurate, with an RMSE reduction of 4.95 %, averaged across three road types.
Motion planning for autonomous vehicles often requires satisfying multiple conditionally conflicting specifications. In situations where not all specifications can be met simultaneously, minimum-violation motion planning maintains system operation by minimizing violations of specifications in accordance with their priorities. Signal temporal logic (STL) provides a formal language for rigorously defining these specifications and enables the quantitative evaluation of their violations. However, a total ordering of specifications yields a lexicographic optimization problem, which is typically computationally expensive to solve using standard methods. We address this problem by discretizing the multi-objective lexicographic optimization problem via non-uniform quantization and transforming it into a single-objective optimization problem using bit-shifting. Specifically, we extend a deterministic model predictive path integral (MPPI) solver to efficiently solve optimization problems without quadratic input cost. Additionally, a novel predicate robustness measure that combines spatial and temporal violations is introduced. Our results show that the proposed method offers an interpretable and scalable solution for lexicographic STL minimum-violation motion planning using a single-objective solver.
ZusammenfassungDie in Bild 9-1 zusammengefassten Megatrends der Gesellschaft bestimmen auch die Zukunftsaspekte des Fahrwerks. Diese sind die Treiber für die Anforderungen der Kunden an die Automobilhersteller. Die stark wachsende Bedeutung von Elektronik im Automobilbau wird einerseits durch die Nachhaltigkeitsdiskussion und den Trend zur Elektrifizierung des Antriebsstranges bestimmt. Andererseits wird die Weiterentwicklung von Komponenten, z. B. für das Fahrwerk maßgeblich von der Elektronik geprägt (Bild 9-2). Für die fahrwerkrelevanten Anforderungen stehen neben dem Umweltschutz die Themen Komfort, Sicherheit, Elektrifizierung und Fahrerassistenzsysteme im Vordergrund.
In times of an aging population, the implicit knowledge of specialists must be made accessible to technical systems and future employees. Currently, important decisions still require specialists, while planning software cannot be adapted according to previous results and with-it company specific attributes. This paper presents an artificial intelligence (AI) driven collaborative assistance system in production planning. The system combines ontology-based production planning with automated process planning and multi-criteria workforce allocation. It captures experiential knowledge and transforms it into ontology-based information by using AI. With the ontological database a partly automation of planning tasks is realized. For the use case of machining, the method increases the achievement of planning targets in a range of 74–87%.