arXiv subjects

Takuya Azumi

Publications and source records attributed to Takuya Azumi.

17 recordsLinked to original sources

arXiv2026

RD-Gen: Random DAG Generator Considering Multi-rate Applications for Reproducible Scheduling Evaluation

Real-time systems have various requirements such as the deadline and resource constraints. In addition, real-time systems are becoming larger and more complex, and studies on performance analysis and efficient scheduling algorithms are becoming increasingly important. Directed acyclic graph (DAG) models, which can express task dependencies and parallelism, are used for such studies. Random DAG sets are used to demonstrate the effectiveness and objectivity of methods proposed for real-time systems. However, there is no random DAG generation tool available that can generate a DAG set that considers the latest multi-rate applications. Therefore, researchers need to generate random DAG sets on their own, leading to additional effort and reduced reliability and reproducibility. To solve this problem, we propose a random DAG generator considering multi-rate applications for reproducible scheduling evaluation (RD-Gen). RD-Gen also enables batch generation of random DAG sets with different parameters. Case studies are used to demonstrate that RD-Gen can manage various problem settings and DAG study requirements.

cs.SE↗

arXiv2026

Toward the Right Analytical Model and System Software for Autonomous Driving Systems: Open Problems and Research Directions

Autonomous driving (AD) systems continuously transform multi-rate and asynchronous sensor streams into vehicle actuation through graphs of callbacks, nodes, and middleware components. In such systems, temporal correctness cannot be characterized by the execution time or deadline of an individual task alone: localization and perception chains run in parallel, fuse data with different timestamps, converge at planning, and propagate through control to actuation. Moreover, the demand for high processing capability places AD systems on high-performance processors with multicore parallelism and GPU acceleration, where execution times vary strongly with the input scene, hardware state, and co-running work. Rare deadline misses at runtime therefore cannot be ruled out, and safety is preserved through fail-safe mechanisms such as the minimal-risk maneuver (MRM). This raises a two-sided question: what analytical models are needed to reason about timing in AD systems, and what system software is needed to realize, observe, and enforce those models on real platforms? On the analytical side, real-time research has evolved from periodic/sporadic tasks, directed acyclic graphs (DAGs), pipelines, mixed-criticality systems, and timer-/event-driven models toward end-to-end latency along cause-effect chains, data freshness, timing disparity, probabilistic timing, highest-criticality fail-safe operation, and early deadline-miss detection. On the system-software side, AD stacks and middleware, such as Autoware and ROS~2, expose both the opportunities and limitations of implementing analyzable timing behavior through executors, communication layers, tracing tools, and evaluation frameworks. This paper surveys these two lines of work and identifies the remaining gaps along five dimensions: units of timing constraints, timing metrics, resource models, execution-time variability, and safety integration...

cs.SE↗

arXiv2026

ipc_shared_ptr: A Publish/Subscribe-Aware Smart Pointer for Cross-Process Object Lifetime Management

True zero-copy Inter-Process Communication (IPC) in publish/subscribe (pub/sub) middleware such as Robot Operating System 2 (ROS 2) requires subscribers to reference message objects in publisher-owned shared memory. Objects must not be reclaimed while referenced, yet must eventually be reclaimed, with correct handling of crash recovery and Transient Local QoS retention requirements. We propose ipc_shared_ptr, a pub/sub-aware smart pointer for cross-process message lifetime management. ipc_shared_ptr exploits pub/sub structural properties to specialize Birrell's reference listing, limiting global metadata updates to per-subscriber 0<->1 transitions and achieving an order-of-magnitude reduction in global communication over general-purpose distributed reference counting. We analyze the key metadata management tradeoff: scalability versus implementation simplicity. Owner-driven reclaim offers greater scalability, but concurrent membership changes and reclamation decisions produce races that widen the correctness-verification state space. Single-writer achieves structural atomicity, eliminating this complexity at the cost of a centralized bottleneck. iceoryx2 (owner-driven reclaim) and Agnocast -- a true zero-copy ROS 2 IPC middleware sharing the publisher's heap with subscribers and adopting ipc_shared_ptr with single-writer -- embody each architecture. Comparative evaluation at the scale of Autoware -- the largest open-source ROS 2 application -- confirms that single-writer achieves sufficient scalability: at 200 topics, two subscribers per topic and 100 Hz, Agnocast's E2E p99.9 is 2.9x lower than iceoryx2's, justifying implementation simplicity over owner-driven reclaim.

cs.OS↗

arXiv2026

SC-MII: Infrastructure LiDAR-based 3D Object Detection on Edge Devices for Split Computing with Multiple Intermediate Outputs Integration

3D object detection using LiDAR-based point cloud data and deep neural networks is essential in autonomous driving technology. However, deploying state-of-the-art models on edge devices present challenges due to high computational demands and energy consumption. Additionally, single LiDAR setups suffer from blind spots. This paper proposes SC-MII, multiple infrastructure LiDAR-based 3D object detection on edge devices for Split Computing with Multiple Intermediate outputs Integration. In SC-MII, edge devices process local point clouds through the initial DNN layers and send intermediate outputs to an edge server. The server integrates these features and completes inference, reducing both latency and device load while improving privacy. Experimental results on a real-world dataset show a 2.19x speed-up and a 71.6% reduction in edge device processing time, with at most a 1.09% drop in accuracy.

cs.DC↗

arXiv2025

Model-based Development for Autonomous Driving Software Considering Parallelization

In recent years, autonomous vehicles have attracted attention as one of the solutions to various social problems. However, autonomous driving software requires real-time performance as it considers a variety of functions and complex environments. Therefore, this paper proposes a parallelization method for autonomous driving software using the Model-Based Development (MBD) process. The proposed method extends the existing Model-Based Parallelizer (MBP) method to facilitate the implementation of complex processing. As a result, execution time was reduced. The evaluation results demonstrate that the proposed method is suitable for the development of autonomous driving software, particularly in achieving real-time performance.

cs.SE↗

arXiv2025

Parallelized Code Generation from Simulink Models for Event-driven and Timer-driven ROS 2 Nodes

In recent years, the complexity and scale of embedded systems, especially in the rapidly developing field of autonomous driving systems, have increased significantly. This has led to the adoption of software and hardware approaches such as Robot Operating System (ROS) 2 and multi-core processors. Traditional manual program parallelization faces challenges, including maintaining data integrity and avoiding concurrency issues such as deadlocks. While model-based development (MBD) automates this process, it encounters difficulties with the integration of modern frameworks such as ROS 2 in multi-input scenarios. This paper proposes an MBD framework to overcome these issues, categorizing ROS 2-compatible Simulink models into event-driven and timer-driven types for targeted parallelization. As a result, it extends the conventional parallelization by MBD and supports parallelized code generation for ROS 2-based models with multiple inputs. The evaluation results show that after applying parallelization with the proposed framework, all patterns show a reduction in execution time, confirming the effectiveness of parallelization.

cs.SE↗

arXiv2025

Accelerating Probabilistic Response-Time Analysis: Revised Critical Instant and Optimized Convolution

Accurate estimation of the Worst-Case Deadline Failure Probability (WCDFP) has attracted growing attention as a means to provide safety assurances in complex systems such as robotic platforms and autonomous vehicles. WCDFP quantifies the likelihood of deadline misses under the most pessimistic operating conditions, and safe estimation is essential for dependable real-time applications. However, achieving high accuracy in WCDFP estimation often incurs significant computational cost. Recent studies have revealed that the classical assumption of the critical instant, the activation pattern traditionally considered to trigger the worst-case behavior, can lead to underestimation of WCDFP in probabilistic settings. This observation motivates the use of a revised critical instant formulation that more faithfully captures the true worst-case scenario. This paper investigates convolution-based methods for WCDFP estimation under this revised setting and proposes an optimization technique that accelerates convolution by improving the merge order. Extensive experiments with diverse execution-time distributions demonstrate that the proposed optimized Aggregate Convolution reduces computation time by up to an order of magnitude compared to Sequential Convolution, while retaining accurate and safe-sided WCDFP estimates. These results highlight the potential of the approach to provide both efficiency and reliability in probabilistic timing analysis for safety-critical real-time applications.

cs.OS↗

arXiv2025

D-AWSIM: Distributed Autonomous Driving Simulator for Dynamic Map Generation Framework

Autonomous driving systems have achieved significant advances, and full autonomy within defined operational design domains near practical deployment. Expanding these domains requires addressing safety assurance under diverse conditions. Information sharing through vehicle-to-vehicle and vehicle-to-infrastructure communication, enabled by a Dynamic Map platform built from vehicle and roadside sensor data, offers a promising solution. Real-world experiments with numerous infrastructure sensors incur high costs and regulatory challenges. Conventional single-host simulators lack the capacity for large-scale urban traffic scenarios. This paper proposes D-AWSIM, a distributed simulator that partitions its workload across multiple machines to support the simulation of extensive sensor deployment and dense traffic environments. A Dynamic Map generation framework on D-AWSIM enables researchers to explore information-sharing strategies without relying on physical testbeds. The evaluation shows that D-AWSIM increases throughput for vehicle count and LiDAR sensor processing substantially compared to a single-machine setup. Integration with Autoware demonstrates applicability for autonomous driving research.

cs.RO↗

arXiv2025

Generalized Inequality-based Approach for Probabilistic WCET Estimation

Estimating the probabilistic Worst-Case Execution Time (pWCET) is essential for ensuring the timing correctness of real-time applications, such as in robot IoT systems and autonomous driving systems. While methods based on Extreme Value Theory (EVT) can provide tight bounds, they suffer from model uncertainty due to the need to decide where the upper tail of the distribution begins. Conversely, inequality-based approaches avoid this issue but can yield pessimistic results for heavy-tailed distributions. This paper proposes a method to reduce such pessimism by incorporating saturating functions (arctangent and hyperbolic tangent) into Chebyshev's inequality, which mitigates the influence of large outliers while preserving mathematical soundness. Evaluations on synthetic and real-world data from the Autoware autonomous driving stack demonstrate that the proposed method achieves safe and tighter bounds for such distributions.

stat.ML↗

arXiv2025

AUTOSAR AP and ROS 2 Collaboration Framework

The field of autonomous vehicle research is advancing rapidly, necessitating platforms that meet real-time performance, safety, and security requirements for practical deployment. AUTOSAR Adaptive Platform (AUTOSAR AP) is widely adopted in development to meet these criteria; however, licensing constraints and tool implementation challenges limit its use in research. Conversely, Robot Operating System 2 (ROS 2) is predominantly used in research within the autonomous driving domain, leading to a disparity between research and development platforms that hinders swift commercialization. This paper proposes a collaboration framework that enables AUTOSAR AP and ROS 2 to communicate with each other using a Data Distribution Service for Real-Time Systems (DDS). In contrast, AUTOSAR AP uses Scalable service-Oriented Middleware over IP (SOME/IP) for communication. The proposed framework bridges these protocol differences, ensuring seamless interaction between the two platforms. We validate the functionality and performance of our bridge converter through empirical analysis, demonstrating its efficiency in conversion time and ease of integration with ROS 2 tools. Furthermore, the availability of the proposed collaboration framework is improved by automatically generating a configuration file for the proposed bridge converter.

cs.RO↗

arXiv2025

3D Point Cloud Object Detection on Edge Devices for Split Computing

The field of autonomous driving technology is rapidly advancing, with deep learning being a key component. Particularly in the field of sensing, 3D point cloud data collected by LiDAR is utilized to run deep neural network models for 3D object detection. However, these state-of-the-art models are complex, leading to longer processing times and increased power consumption on edge devices. The objective of this study is to address these issues by leveraging Split Computing, a distributed machine learning inference method. Split Computing aims to lessen the computational burden on edge devices, thereby reducing processing time and power consumption. Furthermore, it minimizes the risk of data breaches by only transmitting intermediate data from the deep neural network model. Experimental results show that splitting after voxelization reduces the inference time by 70.8% and the edge device execution time by 90.0%. When splitting within the network, the inference time is reduced by up to 57.1%, and the edge device execution time is reduced by up to 69.5%.

cs.DC↗

arXiv2025

TECS/Rust: Memory-safe Component Framework for Embedded Systems

As embedded systems grow in complexity and scale due to increased functional diversity, component-based development (CBD) emerges as a solution to streamline their architecture and enhance functionality reuse. CBD typically utilizes the C programming language for its direct hardware access and low-level operations, despite its susceptibility to memory-related issues. To address these concerns, this paper proposes TECS/Rust, a Rust-based framework specifically designed for TECS, which is a component framework for embedded systems. It leverages Rust's compile-time memory-safe features, such as lifetime and borrowing, to mitigate memory vulnerabilities common with C. The proposed framework not only ensures memory safety but also maintains the flexibility of CBD, automates Rust code generation for CBD components, and supports efficient integration with real-time operating systems. An evaluation of the amount of generated code indicates that the code generated by this paper framework accounts for a large percentage of the actual code. Compared to code developed without the proposed framework, the difference in execution time is minimal, indicating that the overhead introduced by the proposed framework is negligible.

cs.SE↗

arXiv2025

TECS/Rust-OE: Optimizing Exclusive Control in Rust-based Component Systems for Embedded Devices

The diversification of functionalities and the development of the IoT are making embedded systems larger and more complex in structure. Ensuring system reliability, especially in terms of security, necessitates selecting an appropriate programming language. As part of existing research, TECS/Rust has been proposed as a framework that combines Rust and component-based development (CBD) to enable scalable system design and enhanced reliability. This framework represents system structures using static mutable variables, but excessive exclusive controls applied to ensure thread safety have led to performance degradation. This paper proposes TECS/Rust-OE, a memory-safe CBD framework utilizing call flows to address these limitations. The proposed Rust code leverages real-time OS exclusive control mechanisms, optimizing performance without compromising reusability. Rust code is automatically generated based on component descriptions. Evaluations demonstrate reduced overhead due to optimized exclusion control and high reusability of the generated code.

cs.SE↗

arXiv2025

Partitioned Scheduling for DAG Tasks Considering Probabilistic Execution Time

Autonomous driving systems, critical for safety, require real-time guarantees and can be modeled as DAGs. Their acceleration features, such as caches and pipelining, often result in execution times below the worst-case. Thus, a probabilistic approach ensuring constraint satisfaction within a probability threshold is more suitable than worst-case guarantees for these systems. This paper considers probabilistic guarantees for DAG tasks by utilizing the results of probabilistic guarantees for single processors, which have been relatively more advanced than those for multi-core processors. This paper proposes a task set partitioning method that guarantees schedulability under the partitioned scheduling. The evaluation on randomly generated DAG task sets demonstrates that the proposed method schedules more task sets with a smaller mean analysis time compared to existing probabilistic schedulability analysis for DAGs. The evaluation also compares four bin-packing heuristics, revealing Item-Centric Worst-Fit-Decreasing schedules the most task sets.

eess.SY↗

arXiv2025

Work in Progress: Middleware-Transparent Callback Enforcement in Commoditized Component-Oriented Real-time Systems

Real-time scheduling in commoditized component-oriented real-time systems, such as ROS 2 systems on Linux, has been studied under nested scheduling: OS thread scheduling and middleware layer scheduling (e.g., ROS 2 Executor). However, by establishing a persistent one-to-one correspondence between callbacks and OS threads, we can ignore the middleware layer and directly apply OS scheduling parameters (e.g., scheduling policy, priority, and affinity) to individual callbacks. We propose a middleware model that enables this idea and implements CallbackIsolatedExecutor as a novel ROS 2 Executor. We demonstrate that the costs (user-kernel switches, context switches, and memory usage) of CallbackIsolatedExecutor remain lower than those of the MultiThreadedExecutor, regardless of the number of callbacks. Additionally, the cost of CallbackIsolatedExecutor relative to SingleThreadedExecutor stays within a fixed ratio (1.4x for inter-process and 5x for intra-process communication). Future ROS 2 real-time scheduling research can avoid nested scheduling, ignoring the existence of the middleware layer.

cs.OS↗

arXiv2025

Work-in-Progress: Multi-Deadline DAG Scheduling Model for Autonomous Driving Systems

Autoware is an autonomous driving system implemented on Robot Operation System (ROS) 2, where an end-to-end timing guarantee is crucial to ensure safety. However, existing ROS 2 cause-effect chain models for analyzing end-to-end latency struggle to accurately represent the complexities of Autoware, particularly regarding sync callbacks, queue consumption patterns, and feedback loops. To address these problems, we propose a new scheduling model that decomposes the end-to-end timing constraints of Autoware into local relative deadlines for each sub-DAG. This multi-deadline DAG scheduling model avoids the need for complex analysis of data flows through queues and loops, while ensuring that all callbacks receive data within correct intervals. Furthermore, we extend the Global Earliest Deadline First (GEDF) algorithm for the proposed model and evaluate its effectiveness using a synthetic workload derived from Autoware.

cs.OS↗

arXiv2017

Scheduling Parallel and Distributed Processing for Automotive Data Stream Management System

In this paper, to analyze end-to-end timing behavior in heterogeneous processor and network environments accurately, we adopt a heterogeneous selection value on communication contention (HSV_CC) algorithm, which can synchronize tasks and messages simultaneously, for stream processing distribution. In order to adapt HSV_CC to automotive data stream management system (DSMSs), one must address three issues: (i) previous task and message schedules might lead to less efficient resource usages; (ii) the conventional method to determine the task scheduling order may not be best suited to deal with stream processing graphs, and; (iii) there is a need to be able to schedule tasks with time-varying computational requirements efficiently. To address (i), we propose the heterogeneous value with load balancing and communication contention (HVLB_CC) (A) algorithm, which considers load balancing in addition to the parameters considered by the HSV_CC algorithm. We propose HVLB_CC (B) to address issue (ii). HVLB_CC (B) can deal with stream processing task graphs and more various directed acyclic graphs to prevent assigning a higher priority to successor tasks. In addition, to address issue (iii), we propose HVLB_CC_IC. To schedule tasks more efficiently with various computation times, HVLB_CC_IC utilizes schedule holes left in processors. These idle time slots can be used for the execution of an optional part to generate more precise data results by applying imprecise computation models. Experimental results demonstrate that the proposed algorithms improve minimum schedule length, accuracy, and load balancing significantly compared to the HSV_CC algorithm. In addition, the proposed HVLB_CC (B) algorithm can schedule more varied task graphs without reducing performance, and, using imprecise computation models, HVLB_CC_IC yields higher precision data than HVLB_CC without imprecise computation models.

cs.DC↗