autonomous driving

Hardware heterogeneity across vehicle platforms introduces functional safety risks when deploying autonomous driving software. Method: This paper proposes a formal safety portability verification framework that constructs a multi-objective vehicle configuration model—abstracting sensors, actuators, and compute platforms—to automatically derive safety-critical behavior sets and perform controller realizability checks. Contribution/Results: It pioneers the application of formal portability verification to autonomous driving controller adaptation assessment, uniformly supporting safety analysis for both conventional controllers and neural network–based controllers. Evaluated on real-vehicle configurations, the framework enables minute-scale automated verification, precisely identifies adaptation bottlenecks, and generates actionable controller parameter tuning recommendations—thereby significantly accelerating software updates and integration testing.

Functional safety verification of autonomous driving motion planners faces challenges posed by complex and learning-based planners. This paper proposes a real-time runtime protection framework for trajectory safety validation, introducing— for the first time—a temporal protection module that jointly enforces geometric feasibility, dynamic feasibility, and cost rationality checks. The framework adopts a modular architecture and implements online validation of trajectory candidates on a real-time operating system, with successful deployment on embedded hardware. Experiments demonstrate that the system reliably detects unsafe trajectories under millisecond-level latency constraints. The source code is publicly available, and comprehensive fallback strategies are under integration. This work significantly enhances runtime safety assurance for black-box or learning-based planners, bridging a critical gap between planning flexibility and functional safety compliance.

This study addresses the lack of explicit behavioral specifications and validation criteria for autonomous driving systems within their Operational Design Domain (ODD). Building upon the PEGASUS six-layer model, the authors propose a comprehensive behavioral capability taxonomy encompassing 21 capabilities across three key scenarios—highway, urban, and interchange environments—structured along longitudinal and lateral control dimensions and characterized by four attributes: safety, compliance, comfort, and efficiency. The work innovatively establishes a cross-mapping between parameterized ODD definitions and behavioral specifications, thereby introducing, for the first time, a verifiable and testable behavioral specification layer. Notably, interchange scenarios are identified as a structurally distinct and underexplored domain. Leveraging a rule-driven trajectory optimization system and aligned with standards such as SAE J3016, the proposed framework enables standardized, actionable behavioral capability assessment, supports SOTIF-compliant evidence generation, and demonstrates practical efficacy as an operational specification layer in real-world deployments.

To address the stringent real-time and high-precision navigation requirements of autonomous racing on closed-circuit tracks, this paper proposes a modular autonomous driving architecture. The system decouples environment perception, SLAM-based localization and mapping, optimal trajectory generation, and model predictive control (MPC) into independent, interoperable subsystems, coordinated via a unified low-latency data pipeline—enhancing scalability and real-time performance. A key innovation lies in the fusion of multi-source visual cues with high-definition maps to achieve centimeter-level localization and millisecond-scale closed-loop control under constrained computational resources. Experimental validation on complex racetracks demonstrates robust high-speed trajectory tracking and dynamic obstacle avoidance, achieving an average lateral tracking error of <0.15 m and a control frequency of 50 Hz. These results confirm the system’s reliability and engineering practicality for competitive autonomous racing applications.

This study addresses the persistent gap between theoretical control performance and its practical realization in real-world robotic systems, often caused by inadequate discretization, insufficient real-time guarantees, and weak error handling in control software. For the first time from a software engineering perspective, the authors systematically analyze 184 open-source robotic controllers through code review, empirical analysis, and test evaluation, uncovering common deficiencies in application scenarios, implementation details, and verification practices. The findings reveal that most implementations fail to properly account for critical system constraints, and their testing strategies inadequately validate the theoretical assurances they claim. This work highlights a significant disconnect between implementation quality and theoretical promises, offering concrete directions and practical guidelines for developing reliable, verifiable robotic control software.

Current autonomous driving systems lack mechanisms to actively ensure safe operation when the primary planner fails, making it difficult to simultaneously meet functional safety and real-time requirements. This work proposes a fail-operational active safety extension architecture that, for the first time, integrates a lightweight sampling-based trajectory planner into a certifiable safety framework and implements it on automotive-grade embedded hardware using a real-time operating system. The approach enables deterministic real-time computation under stringent resource constraints. Experimental results demonstrate that the system exhibits bounded latency and extremely low timing jitter, thereby validating the feasibility of performing real-time emergency trajectory planning on a safety-certifiable platform.

This work addresses the validation gap between simulation and real-world deployment of autonomous driving algorithms, particularly the lack of efficient, high-fidelity testing platforms for safety-critical scenarios. To bridge this gap, the authors propose a mixed-reality hardware-in-the-loop testing framework that seamlessly integrates physical mobile robots with high-fidelity virtual environments, enabling multimodal sensing, vehicle-to-everything (V2X) communication, and large-scale multi-agent collaboration. A key innovation is the coexistence of physical and virtual agents within a unified architecture, coupled with an online learning controller based on control barrier functions (CBFs) that establishes an integrated perception-planning-control safety assurance mechanism. Experimental results demonstrate that the platform significantly enhances the reliability and efficiency of sim-to-real transfer and validates its effectiveness across diverse safety-critical scenarios.

This study addresses the functional safety risks of infrastructure-enabled autonomous vehicle yard systems (IX-DA) operating without human intervention by systematically applying, for the first time, the Hazard Analysis and Risk Assessment (HARA) methodology from ISO 26262 to closed-area, infrastructure-dominated scenarios. The authors identify eight categories of hazardous events and derive six corresponding safety goals, proposing a dynamic ASIL downgrade strategy based on operational speed: high-speed loss-of-control scenarios require compliance with ASIL C, whereas low-speed controlled operations may be downgraded to QM. By integrating a standards-compliant HARA process, system architecture decomposition, and multi-scenario risk evaluation, this approach offers a feasible pathway for the phased safety deployment of IX-DA systems.

This work addresses the reliability challenges inherent in deploying autonomous mobile robots from simulation to real-world environments by proposing and implementing an end-to-end development and validation framework. Building upon an existing mechatronic platform, the system integrates onboard sensing and computing units to achieve self-localization and autonomous navigation. The complete architecture is first developed and rigorously validated in a high-fidelity simulation environment before being seamlessly transferred to a physical robot. Experimental results demonstrate that the real-world system successfully replicates the performance observed in simulation, thereby confirming the effectiveness and robustness of the proposed approach. These findings substantiate the use of high-fidelity simulation as a trustworthy foundation for robotic development, significantly enhancing deployment efficiency and system credibility.

This study addresses the over-optimistic safety assessment of autonomous driving systems in conventional software-in-the-loop simulation, which typically assumes ideal perception and neglects environmental disturbances such as fog or rain that induce perceptual errors. To bridge this gap, the authors propose a perception-driven simulation framework integrating a causal probabilistic model to systematically inject physically plausible perception failures into standard scenario-based simulation pipelines. Grounded in the SOTIF (ISO 21448) validation framework, this approach effectively reproduces real-world perception failures and uncovers safety-critical risks that traditional simulations often miss. The method offers a scalable, realistic closed-loop testing pathway for verifying SOTIF compliance in advanced driver assistance and autonomous driving systems.