4 papers
Zero-Shot MARL Benchmark in the Cyber-Physical Mobility Lab
Julius Beerwerth, Jianye Xu, Simon Schäfer +2
We present a reproducible benchmark for evaluating sim-to-real transfer of Multi-Agent Reinforcement Learning (MARL) policies for Connected and Automated Vehicles (CAVs). The platf…
Computation-Accuracy Trade-Off in Service-Oriented Model-Based Control
Hazem Ibrahim, Julius Beerwerth, Lorenz Dörschel +1
Representing a control system as a Service-Oriented Architecture (SOA)-referred to as Service-Oriented Model-Based Control (SOMC)-enables runtime-flexible composition of control lo…
Graph-Based Orchestration of Service-Oriented Model-Based Control Systems
Julius Beerwerth, Hazem Ibrahim, Bianca Atodiresei +2
This paper presents a novel graph-based method for adapting control system architectures at runtime. We use a service-oriented architecture as a basis for its formulation. In our m…
Synchronization-Based Cooperative Distributed Model Predictive Control
Julius Beerwerth, Maximilian Kloock, Bassam Alrifaee
Distributed control algorithms are known to reduce overall computation time compared to centralized control algorithms. However, they can result in inconsistent solutions leading t…