The development of Cyber-Physical Systems, particularly inthe field of autonomous mobile robotics, often relies onproprietary environments, which limit flexibility andinteroperability. This paper proposes a modular andopen-source methodology that enables the modeling andsimulation of such systems using non-proprietary tools. Themethodology integrates Functional Mock-up Interfacestandard for model exchange, Open Neural Network Exchangestandard for Convolutional Neuronal Networks algorithmsintegration, ROS2 as robotic middleware, and Gazebo as thesimulation environment. To validate the approach, weapplied it in the development of a mobile robot thatnavigates autonomously by following traffic signals. Thisimplementation demonstrates that these open technologiescan be effectively combined, overcoming common integrationbarriers among proprietary tools. The proposed workflowprovides a practical alternative to proprietary solutionsand demonstrates the feasibility of integrating openstandards for the development of autonomous robotic systems.
30 July 2026 in Mathematical and Computer Modelling of Dynamical Systems
1. Model-Based Engineering (MBE) has transformed the way engineers and researchers design and develop complex systems (Holtmann et al. 2024). By promoting the reuse of models, tests, and validation...
This paper presents a proof-of-concept for a natural-language-based closed-loop controller that regulates the temperature of a simple single-input single-output (SISO) thermal process. The key idea is to express a relay-with-hysteresis policy in plain English and let a local large language model (LLM) interpret sensor readings and output a binary actuation command at each sampling step. Beyond interface convenience, we demonstrate that natural language can serve as a valid medium for modeling physical reality and executing deterministic reasoning in control loops. We implement a compact plant model and compare two controllers: a conventional coded relay and an LLM-driven controller prompted with the same logic and constrained to a single-token output. The workflow integrates schema validation, retries, and a safe fallback, while a stepwise evaluator checks agreement with the baseline. In a long-horizon (1000-step) simulation, the language controller reproduces the hysteresis behavior with matching switching patterns. Furthermore, sensitivity and ablation studies demonstrate the system’s robustness to measurement noise and the LLM’s ability to correctly execute the hysteresis policy, thereby preserving the theoretical robustness inherent to this control law. This work demonstrates that, for slow thermal dynamics, natural-language policies can achieve comparable performance to classical relay systems while providing a transparent, human-readable interface and facilitating rapid iteration.
Large Language Models are increasingly used for high-level robotic reasoning, yet their latency and stochasticity complicate their direct use in low-level control. Moreover, extracting actionable navigation cues from multimodal context incurs inference costs that are challenging for embedded platforms. We present a plug-and-play framework that augments a finite-state machine with asynchronous velocity suggestions generated by a Large Language Model, using an off-the-shelf DistilGPT-2 model running on-device on a Jetson AGX Orin. The system extracts task-relevant cues from the current context and integrates them only if they satisfy deadline, schema, and kinematic validation, thereby preserving a deterministic 50 Hz control loop with a <5 ms fallback path. We compare multiple Large Language Models for embedded robot control and quantify trade-offs among model size, inference time, and output validity. To assess whether the Large Language Models add value beyond signal processing, we include an ablation against a standard smoothing baseline; the results indicate that the Large Language Models contribute anticipatory, context-dependent adjustments that are not captured by filtering alone. Experiments in Gazebo and on a real TurtleBot3 reduce the final position error from 0.246 m to 0.159 m and improve trajectory efficiency from 0.821 to 0.901 without increasing control-loop latency. Approximately 80% of the Large Language Models’ outputs pass validation and are applied. Overall, the framework reduces developer effort by enabling behavioral changes at the prompt level while maintaining interpretable, robust edge-based navigation.