Differences

This shows you the differences between two versions of the page.

Link to this comparison view

--- en:safeav:curriculum:introduction [2025/09/24 16:05] – larisas
+++ en:safeav:curriculum:introduction [2025/11/17 08:31] (current) – airi
@@ Line 1: / Line 1: @@
 ====== Introduction ======
-The document offers sample curricula for Bachelor and Master level studies (see figure below) in Safe Autonomous Vehicles (SafeAV). These examples serve as a foundational framework that educational institutions worldwide can adapt and expand upon to design their unique study modules/courses.
+The document presents a structured and adaptable curriculum for Bachelor and Master level studies in Safe Autonomous Vehicles (SafeAV), with a strong focus on Verification and Validation (V&V) of autonomous systems. The framework serves as a foundation that higher education institutions can adapt and expand when designing their own study modules or programmes related to the safety, reliability, and governance of autonomous technologies.
-<figure safeavcurriculum>
+The curriculum follows a modular structure combining theoretical foundations, applied engineering knowledge, and hands-on experimentation. It is supported by two complementary educational resources developed within the SafeAV project:
-{{:en:safeav:curriculum:SafeAV-curriculum.png?500 | SafeAV Curriculum }}
+  * **SafeAV Handbook** – provides the theoretical and methodological background, including system architectures, sensing, software, and formal V&V methods.
-<caption>Safe Autonomous Vehicles (SafeAV) curriculum </caption>
+  * **SafeAV Hands-on Guide** – offers practical laboratory and simulation exercises that allow students to perform verification and validation tasks using real and virtual autonomous platforms.
-</figure>
-The curriculum is structured to provide both comprehensive and in-depth learning at the undergraduate and postgraduate study levels. The modular design is highly flexible, enabling adaptation to the individual preferences and capabilities of students.
+**Terminology note.** In this document, the SafeAV curriculum is the unified framework that defines the overall programme architecture, the BSc/MSc progression, and the learning flow from theory to V&V practice, aligning the SafeAV Handbook and the Hands-on Guide into a coherent, modular pathway. The subsequent chapters describe the modules as syllabi course-level maps specifying aims, learning outcomes, topics, assessment, tools, and relevant standards which constitute the formal open publication.
-The undergraduate study program introduces students to the fundamental components of autonomous systems through six interrelated modules (1 ECTS each). Students gain an understanding of vehicle architectures and autonomy levels, complemented by perspectives on legal, ethical, and cybersecurity aspects. Core technical knowledge is developed through modules on sensing technologies, computing hardware, software systems, and middleware integration. Further emphasis is placed on perception, mapping, localization, and control strategies, where both classical and AI-based approaches to planning and decision-making are explored. Finally, the program addresses human–machine communication, highlighting interaction principles and interface concepts essential for safe and effective collaboration between users and autonomous technologies. The topics/modules are:
+The SafeAV curriculum architecture defines the overall structure, modular hierarchy, and learning flow that connects theoretical knowledge, simulation-based validation, and experimental practice. It ensures coherence between study levels and provides a clear path from basic understanding to advanced assurance of autonomous vehicle safety.
+Modules are organised in pairs: Part 1 (Bachelor) introduces the concepts, while Part 2 (Master) deepens the same topic through practical verification and validation methods. This two-level structure enables a stepwise learning progression across study cycles and gives universities the flexibility to adopt the curriculum or parts of it into existing educational programs.
-  * Autonomous Vehicles
+Each topic therefore exists in two complementary parts:
-  * Hardware and Sensing Technologies
+  * **Part 1 (Bachelor level)** – introduces the fundamental principles, technologies, and system interactions. Emphasis is on conceptual understanding, component function, and system-level awareness.
-  * Software Systems and Middleware
+  * **Part 2 (Master level)** – deepens the focus toward verification and validation, including analytical, experimental, and regulatory methods used to demonstrate safety, reliability, and trustworthiness.
-  * Perception, Mapping, and Localization
-  * Control, Planning, and Decision-Making
-  * Human Machine communication
-The module structure is designed to provide flexibility, enabling educational institutions to adapt its scope to their specific needs. Universities and schools may either implement the full set of topics, amounting to 6 ECTS (European Credit Transfer and Accumulation System) credits, or select a single thematic focus, such as an introductory //Autonomous vehicles//, corresponding to 1 ECTS credit. This adaptable framework allows institutions to align the content and extent of study with their curricular objectives and the learning goals of their students.
+For example, in Hardware and Sensing Technologies **Part 1**, students learn sensor types, signal processing basics, and data acquisition. In **Part 2**, they perform calibration, fault analysis, redundancy testing, and scenario-based validation using V&V tools and simulation environments.
+This two-stage progression ensures continuity between study cycles and supports lifelong learning paths in autonomous vehicle engineering.
-The Master's level study program provides an in-depth exploration of validation, safety, and governance in autonomous systems. Through six focused modules (1 ECTS each), students examine advanced challenges in hardware and software reliability, perception and control stability, human–machine interaction, and verification and validation methods, while also engaging with emerging tools, infrastructures, and research directions shaping the future of autonomy.
+{{ :en:safeav:curriculum:SafeAV-curriculum.png?500 | SafeAV Curriculum }}
-  * Hardware and Sensing Technologies
+The overall curriculum can be described as three integrated layers:
-  * Software Systems and Middleware
+  * **Conceptual layer** – theoretical foundations and system-level understanding (covered in the SafeAV Handbook)
-  * Perception, Mapping, and Localization
+  * **Practical layer** – hands-on experiments, data analysis, and verification in laboratory environments (based on the SafeAV Hands-on Guide)
-  * Control, Planning, and Decision-Making
+  * **Digital layer** – self-study materials, MOOC courses, and AI-supported assistants that guide learning and track individual progress
-  * Human Machine communication
-  * Autonomy Validation Tools
-The curriculum is organized into six modules, allowing students to complete up to 6 ECTS in total. Designed for flexibility, the program can be followed in a fully self-paced mode, enabling learners to engage with individual modules or the complete set according to their academic and professional goals.
+These layers are interconnected through shared terminology, datasets, and unified learning outcomes across all modules.
+===== Curriculum Composition =====
+The curriculum consists of six interrelated modules that together form a complete 6 ECTS study block (one for bachelor and one for masters) but can also be used independently. Each module represents approximately 25–30 hours of student work, combining lectures, laboratory tasks, and self-study.
+The modular design allows multiple implementation strategies:
+  * full six-module SafeAV course (6 ECTS)
+  * selected modules as independent 1 ECTS units
+  * integration into existing robotics, AI, or control courses
+  * use for lifelong learning or professional training
+Each module includes theoretical reading, guided experiments, simulation exercises, and assessment through a report, presentation, or quiz. The same structure is followed in all modules to maintain coherence across institutions.
+----
+===== Bachelor Level (Part 1) =====
+The undergraduate programme introduces the building blocks of autonomous systems and their relation to safety assurance. The emphasis is on understanding system components and basic verification of function. Six modules (1 ECTS each) provide foundational knowledge of vehicle architecture, autonomy levels, sensing, computing, software systems, and human–machine interaction.
+Modules – Part 1:
+  * Autonomous Vehicles
+  * Hardware and Sensing Technologies
+  * Software Systems and Middleware
+  * Perception, Mapping, and Localization
+  * Control, Planning, and Decision-Making
+  * Human–Machine Communication
+Each module combines reading assignments from the SafeAV Handbook with laboratory or simulation tasks from the Hands-on Guide, such as sensor calibration, perception benchmarking, or control-loop validation.
+The recommended full scope equals 6 ECTS, yet the modular design allows partial adoption depending on local curricula and student pathways.
+----
+===== Master Level (Part 2) =====
+The Master’s programme deepens the same thematic areas into Part 2 modules that focus on validation, verification, and system governance. Students explore how safety and reliability are demonstrated through structured testing, scenario generation, formal methods, and compliance with standards. Modules are directly linked to the advanced chapters of the SafeAV Handbook and the experimental work described in the Hands-on Guide.
+Modules – Part 2:
+  * Hardware and Sensing Technologies (Validation and Reliability)
+  * Software Systems and Middleware (Safety and Verification)
+  * Perception, Mapping, and Localization (Scenario-based Testing)
+  * Control, Planning, and Decision-Making (Formal and Simulation-backed Validation)
+  * Human–Machine Communication (HMI Safety and V&V)
+  * Autonomy Verification and Validation Tools (Integrated Frameworks and Methods)
+Students build validation pipelines from model design to field testing, using digital twins and simulation environments. The progression mirrors the V-model lifecycle introduced in the handbook — from design to verification, validation, and governance.
+It is important to note that the distinction between Bachelor (Part 1) and Master (Part 2) levels in this curriculum is conditional rather than absolute. Depending on the structure of the base study programme or the learner’s prior knowledge and competences, topics defined at the Master level in the SafeAV curriculum may also be taught within Bachelor-level courses, and vice versa. The actual implementation depends on the educational context of the university and the individual learning path of the student.
+For this reason, the SafeAV Handbook presents most topics in two levels of depth. Students who already have sufficient background or wish to advance further can continue directly to the next sub-sections, regardless of the formal level assigned to that topic in this curriculum. Conversely, in some non-technical or related engineering programmes, the same subjects might be addressed at a basic level even within Master studies, corresponding to what the SafeAV framework defines as Bachelor-level content.
+Therefore, the level designation in this curriculum should be interpreted as indicative of content depth—Basic and Advanced rather than as a strict separation between Bachelor and Master academic degrees.
+===== Learning Environments and Methods =====
+Most module supports flexible learning environments that allow both classroom and remote participation:
+  * classroom teaching for theoretical foundations
+  * access to the AI-driven hybrid laboratory environment
+  * virtual experiments linked to the MOOC platform
+  * hybrid sessions combining on-site instruction with online validation tasks
+The SafeAV Hands-on Guide defines equipment lists, hybrid lab configurations, and step-by-step procedures. Remote setups ensure that students can conduct verification and validation exercises even without physical access to hardware.
+Digital tools, Dokuwiki materials, and the MOOC environment allow integration with AI-based assistants that support self-learning, answer technical questions, and provide feedback on simulation or validation tasks.
+These learning environments are common across all modules, ensuring coherence, accessibility, and continuous feedback through AI-supported methods. The same platform is used by all modules, ensuring a consistent digital experience throughout the entire curriculum. Each course component is accessed through the same environment, which connects theoretical materials, laboratory tasks, and evaluation.
+Key features include:
+  * AI tutoring and feedback – AI assistants answer questions, explain concepts, and provide formative feedback.
+  * Accessibility and inclusion – automatic transcription, summarisation, translation, and adaptive pacing to support all learners.
+  * Integration with laboratories – seamless connection between online content and hybrid laboratory activities.
+  * Open-access collaboration – materials and results can be shared, reused, and expanded across institutions.
+The MOOC environment also functions as the central tool for monitoring student progress and competence development. It is continuously updated with new content and integrated with AI analysis to track engagement, learning efficiency, and V&V-related skills.
+===== Hybrid Laboratory Environment (AI-driven) =====
+The SafeAV curriculum builds upon the remote and virtual laboratory infrastructure previously developed within earlier Erasmus+ projects (Interstudy, SimLab, Autonomian, IoT.Open Reloaded). This existing framework enables students to perform practical experiments not only in traditional classroom settings but also remotely, even when physical equipment and autonomous platforms are involved.
+The hybrid laboratory integrates real test environments, such as sensor and control systems, with cloud-based and virtual simulation platforms. Through this setup, learners can connect to remote hardware, collect data, and carry out validation tasks in real time, regardless of their location. The same infrastructure also supports collaborative use between partner universities, allowing shared access to experiments, datasets, and learning tools.
+SafeAV enhances this environment by introducing an AI component that expands the capabilities of the virtual laboratories. AI-based modules enable advanced simulation, automated data analysis, and model validation within digital twin environments. Intelligent assistants help students interpret results, identify anomalies, and generate experiment documentation automatically.
+This AI-driven hybrid environment forms the backbone of the SafeAV practical learning concept. It bridges physical and virtual domains, connects theoretical understanding to verification and validation processes, and provides a unified experimental framework for both Bachelor and Master level studies.
+===== AI-Based Methods Supporting the Curriculum =====
+The integration of artificial intelligence (AI) tools into the SafeAV curriculum is a central element for enabling modern, personalized learning experiences. In addition to supporting individualized study paths for typical learners, it also enhances accessibility and provides improved educational opportunities for students with special needs.
+AI technologies are implemented at two levels:
+  * integration within the learning content to illustrate how AI supports autonomous vehicle V&V (e.g., AI in perception, planning, or safety analysis)
+  * integration as pedagogical tools to assist students and lecturers throughout the learning process
+The following AI-based methods are used within the SafeAV ecosystem:
+  * AI-powered virtual assistants – LLM-based agents embedded in the MOOC and Dokuwiki environment answer course-related questions, explain theoretical concepts, and provide V&V-related guidance.
+  * AI-driven interactive simulations and virtual labs – intelligent digital twins and scenario generators support sensor fusion validation, control-loop testing, and human–machine communication studies.
+  * Personalized AI tutors – adaptive learning systems analyse student progress and recommend additional materials, exercises, or simulations based on performance.
+  * AI-supported content summarization – automatic generation of concise summaries of lectures, reports, and laboratory documentation helps students prepare for assessment and supports accessibility.
+  * Automated peer review and feedback – integrated AI tools assist in assessing reports and coding exercises, providing constructive feedback and reducing lecturer workload.
+AI-based tools play a significant role in SafeAV by reducing repetitive communication tasks, offering continuous learning support, and improving the overall organization of study activities. These systems provide students with round-the-clock access to guidance and feedback, allowing instructors to focus on higher-level mentoring and project supervision.
+To ensure trustworthy and responsible use of AI in education, all implementations follow privacy-by-design principles and comply with relevant data protection regulations. Student data are processed transparently and securely, with anonymized interaction records and clear options to opt out of AI-assisted learning when preferred.
+In the long term, the SafeAV approach aims to develop a shared and open AI learning framework that promotes accessibility, multilingual support, and collaboration between partner universities, ensuring sustainable and equitable use of AI technologies in higher education.
+===== Curriculum Implementation and Adaptation =====
+The SafeAV architecture is open and adaptable. Educational institutions may:
+  * adopt the complete curriculum as a dedicated SafeAV course
+  * integrate selected modules into existing study programmes
+  * use materials in non-formal education or industrial training
+All materials are licensed under Creative Commons (CC BY-NC), allowing reuse and modification while keeping alignment with European learning standards and ECTS principles.
+This ensures consistency across partner universities while maintaining flexibility for local adaptation and future extension.
-The following section delineates the architecture of the curriculum module in detail:
-  * Study level - provides the study level for which the module is designed.
-  * ECTS credits - how many points can be obtained to complete the module.
-  * Study form - explains where the module can take place: class, online, or hybrid.
-  * Module aims - gives the overall goal(s) or purpose(s) of the module.
-  * Pre-requirements - outlines pre-requirements for the current module, which the student must meet.
-  * Learning outcomes - lists what students are expected to know, understand, and be able to do after completing the module.
-  * Topics - listed subjects taught in the module. They are based on the books that were made for the IOT-OPEN.EU Reloaded project.
-  * Type of assessment - a general description of how assessment is carried out in the module.
-  * Learning methods - describe how students are taught and how they engage with the material, ranging from traditional lectures and reading assignments to interactive, experiential, and technology-enhanced approaches.
-  * AI involvement - refers to the use of AI tools and technologies to create, adapt, and enhance the content and educational materials.
-  * References to literature - a list of books, online books, articles, etc., are given, which helps to improve knowledge in the module.
-  * Lab equipment - a list of equipment, software, etc., used in the module to perform local laboratory work(s).
-  * Virtual lab - link(s) to a virtual lab(s), which is/are used in the module to do laboratory work(s) remotely.
-  * MOOC course - provides a link to a massive open online course made for the IoT-OPEN.EU Reloaded project. Students from all over the world can attend it.

en/safeav/curriculum/introduction.1758729940.txt.gz · Last modified: 2025/09/24 16:05 by larisas