Autonomous Driving: Motion Planner Executed on Automotive-Grade Embedded HW (TU Munich)

Researchers at TU Munich have published a technical paper titled "Towards Safe Autonomous Driving: A Real-Time Motion Planning Algorithm on Embedded Hardware." The paper focuses on the importance of motion planning modules for Autonomous Vehicles (AVs) to ensure functional safety and maintain controllability in case of system faults. They introduce an active safety extension for fail-operational Autonomous Driving by deploying a lightweight trajectory planner on automotive-grade embedded hardware with a Real-Time Operating System (RTOS). Experimental results show deterministic timing behavior, validating the feasibility of trajectory planning on safety-certifiable hardware. The study emphasizes the potential and challenges of integrating active fallback mechanisms into next-generation safeguarding frameworks.