This paper discusses some of the challenges we encountered when developing Apex.OS, an automotive grade version of the Robot Operating System (ROS)2. To better understand these challenges, we look back at the best practices used for data communication and software execution in OSEK-based systems. Finally we describe the extensions made in ROS2, Apex.OS and Apex.Middleware to meet the real-time constraints of the targeted automotive systems.

Modern autonomous cars run classic AUTOSAR applications alongside advanced driving assistance systems on a single-vehicle computer. Ensuring safety and predictability in such a complex system is challenging and requires temporal isolation between the various components. A promising solution is the POSIX-compliant QNX operating system: it meets the automotive standards for functional safety at the highest level (ISO 26262 ASIL-D) and provides temporal isolation through the Adaptive Partitioning Scheduler (APS), a resource reservation algorithm that guarantees processor bandwidth to groups of threads. These guarantees make it an ideal platform for composing diverse and complex applications on centralized vehicle computers. However, so far, there is no precise description or analysis of the APS reservation mechanism in real-time literature. In this paper, we provide the first description of the behavior of the APS from a real-time point of view and validate the results by running experiments on a real QNX platform. Based on the derived scheduler rules, we develop a response-time analysis to bound the end-to-end latency of event chains under APS. Finally, we evaluate different design strategies on a case study based on a real autonomous construction vehicle.

Robotic systems are typically subject to real-time constraints. Still, the ROS ecosystem-the most popular repository of open-source robotics software-exhibits little evidence of the use of real-time theory to bound or control worst-case response times. Hurdles to adoption are the amount of expertise required to correctly use real-time scheduling mechanisms and the inherent unpredictability of typical robotics workloads, which defy static provisioning. To overcome these hurdles, ROS-Llama, an automatic latency manager for ROS2, is proposed. Crucially, use of ROS-Llama requires only little effort and knowledge of realtime concepts. Relevant properties of ROS2 and essential requirements of the robotics domain are identified, and the conceptual and practical challenges in developing such a mostly automatic tool are discussed. Experiments on a mobile robot demonstrate the viability of the approach and show that ROS-Llama reduces the maximum observed latency under load compared to the default Linux scheduler. Finally, open problems in the underlying real-time analysis and major platform limitations in Linux and ROS2 that prevent further improvements are identified.

Robots are commonly subject to real-time constraints. To ensure that such constraints are met, recent work has analyzed the response times of processing chains under ROS 2, a popular robotics framework. However, prior work supports only scalar worst-case execution time bounds and does not exploit that the ROS 2 scheduling mechanism is starvation-free.This paper proposes a novel response-time analysis for ROS 2 processing chains that accounts for both the high execution-time variance typically encountered in robotics workloads and the starvation freedom of the default ROS 2 callback scheduler. Experimental results from both synthetic callback graphs and a real ROS 2 workload empirically show the proposed analysis to be much more accurate (often by a factor of 2× or more).

Bounding the end-to-end latency of processing chains in distributed real-time systems is a well-studied problem, relevant in multiple industrial fields, such as automotive systems and robotics. Nonetheless, to date, only little attention has been given to the study of the impact that specific frameworks and implementation choices have on real-time performance. This paper proposes a scheduling model and a response-time analysis for ROS 2 (specifically, version "Crystal Clemmys" released in December 2018), a popular framework for the rapid prototyping, development, and deployment of robotics applications with thousands of professional users around the world. The purpose of this paper is threefold. Firstly, it is aimed at providing to robotic engineers a practical analysis to bound the worst-case response times of their applications. Secondly, it shines a light on current ROS 2 implementation choices from a real-time perspective. Finally, it presents a realistic real-time scheduling model, which provides an opportunity for future impact on the robotics industry.

Write-back caches are a popular choice in embedded microprocessors as they promise higher performance than write-through caches. So far, however, their use in hard real-time systems has been prohibited by the lack of adequate worst-case execution time (WCET) analysis support. In this paper, we introduce a new approach to statically analyze the behavior of write-back caches. Prior work took an "eviction-focussed perspective", answering for each potential cache miss: May this miss evict a dirty cache line and thus cause a write back? We complement this approach by exploring a "store-focussed perspective", answering for each store: May this store dirtify a clean cache line and thus cause a write back later on? Experimental evaluation demonstrates substantial precision improvements when both perspectives are combined. For most benchmarks, write-back caches are then preferable to write-through caches in terms of the computed WCET bounds.