Prof. Dr.

Wrobel, Stefan

Filters
2 1
Reset filters

Settings
Now showing 1 - 3 of 3
  • Publication
    Explainable production planning under partial observability in high-precision manufacturing
    ( 2023-10)
    Weichert, Dorina
    ;
    Kister, Alexander
    ;
    Volbach, Peter
    ;
    Houben, Sebastian
    ;
    Trost, Marcus
    ;
    Wrobel, Stefan
    Conceptually, high-precision manufacturing is a sequence of production and measurement steps, where both kinds of steps require to use non-deterministic models to represent production and measurement tolerances. This paper demonstrates how to effectively represent these manufacturing processes as Partially Observable Markov Decision Processes (POMDP) and derive an offline strategy with state-of-the-art Monte Carlo Tree Search (MCTS) approaches. In doing so, we face two challenges: a continuous observation space and explainability requirements from the side of the process engineers. As a result, we find that a tradeoff between the quantitative performance of the solution and its explainability is required. In a nutshell, the paper elucidates the entire process of explainable production planning: We design and validate a white-box simulation from expert knowledge, examine state-of-the-art POMDP solvers, and discuss our results from both the perspective of machine learning research and as an illustration for high-precision manufacturing practitioners.
  • Publication
    Robustness in Fatigue Strength Estimation
    ( 2022-12-02)
    Weichert, Dorina
    ;
    Kister, Alexander
    ;
    Houben, Sebastian
    ;
    Ernis, Gunar
    ;
    Wrobel, Stefan
    Fatigue strength estimation is a costly manual material characterization process in which state-of-the-art approaches follow a standardized experiment and analysis procedure. In this paper, we examine a modular, Machine Learning-based approach for fatigue strength estimation that is likely to reduce the number of experiments and, thus, the overall experimental costs. Despite its high potential, deployment of a new approach in a real-life lab requires more than the theoretical definition and simulation. Therefore, we study the robustness of the approach against misspecification of the prior and discretization of the specified loads. We identify its applicability and its advantageous behavior over the state-of-the-art methods, potentially reducing the number of costly experiments.
  • Publication
    Multi-Agent Neural Rewriter for Vehicle Routing with Limited Disclosure of Costs
    ( 2022)
    Paul, Nathalie
    ;
    Wirtz, Tim
    ;
    Wrobel, Stefan
    ;
    Kister, Alexander
    We interpret solving the multi-vehicle routing problem as a team Markov game with partially observable costs. For a given set of customers to serve, the playing agents (vehicles) have the common goal to determine the team-optimal agent routes with minimal total cost. Each agent thereby observes only its own cost. Our multi-agent reinforcement learning approach, the so-called multi-agent Neural Rewriter, builds on the single-agent Neural Rewriter to solve the problem by iteratively rewriting solutions. Parallel agent action execution and partial observability require new rewriting rules for the game. We propose the introduction of a so-called pool in the system which serves as a collection point for unvisited nodes. It enables agents to act simultaneously and exchange nodes in a conflict-free manner. We realize limited disclosure of agent-specific costs by only sharing them during learning. During inference, each agents acts decentrally, solely based on its own cost. First empirical results on small problem sizes demonstrate that we reach a performance close to the employed OR-Tools benchmark which operates in the perfect cost information setting.