All news
Digital Twin

Hybrid control architecture for safe vehicle lateral control

US & West ·

A hybrid architecture combining a trained Soft Actor-Critic (SAC) policy and linear MPC is presented for vehicle steering control. Using the first-step optimum of MPC as an anchor and a monotone blending coefficient allows combining the adaptability of learning with MPC's safety guarantees.

Why it matters

Important for developing reliable automated driving systems that require accuracy, low effort, and safety simultaneously.

Relevant to DT products

Original headline
A Hybrid End-to-End and Modular Control Architecture Toward Safe Vehicle Lateral Control: Combining Soft Actor-Critic with Model Predictive Control
Read the original: arXiv — Systems and Control (eess.SY)

Translation and summary are machine-generated from the source. The full article is not republished; its rights belong to the source.

Related

ModellingUS & West

Parallel branch MPC on GPUs

A GPU-based solver for trajectory planning problems using branch model predictive control is presented. The solver is based on iterative LQR, multiple-shooting formulation, and augmented Lagrangian method for constraint handling. Numerical experiments show superiority over a CPU-based solver on large-scale problems.

DT.ForecastarXiv — Systems and Control (eess.SY) ↗
ModellingUS & West

Hybrid simulation of circular supply chains in healthcare

Researchers applied a hybrid discrete-event and agent-based simulation to analyze the transition to circular economy in healthcare supply chains. Using laparoscopic scissors as a case study, they assessed the impact of introducing reusable products on individual supply chain members and the entire system. The work accounts for uncertainties in flows and actor behavior, which was not done before.

DT.BalanceDTEarXiv — Systems and Control (eess.SY) ↗