cs.AISep 25, 2026

Toward AI-Augmented Cooperative Engineering Workflows: Requirements and Architecture the European Rover Challenge

Authors: Ahmed R. Sadik, Frank Joublin, Mariusz Bujny, Antonello Ceravola, Joan Smith

Organizations: Honda Research Institute Europe, Offenbach, 63073, Germany · NUMETO, Katowice, Poland · Honda Research Institute USA, Ohio, USA

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

The growing availability of Artificial Intelligence (AI) tools creates new opportunities to support engineering design processes, yet their current use often remains limited to isolated tasks such as coding, documentation, or information retrieval. Less attention has been given to how AI can support cooperative engineering workflows at the process level, where teams must coordinate requirements, tasks, communication, knowledge transfer, and subsystem integration. This paper investigates this challenge in the context of the European Rover Challenge (ERC), where student teams design and integrate complex rover systems within a single academic cycle under strict time constraints and high subsystem interdependence. We conducted a role adaptive 40 question survey with ERC 2025 teams, yielding 104 responses from 14 teams. The survey examined team structure, knowledge transfer, task management, integration practices, communication patterns, and current AI usage. The results reveal recurring workflow bottlenecks, including limited documentation, unclear requirements, fragmented communication, informal task monitoring, and substantial integration rework. Based on these findings, we derive requirements for AI augmented cooperative engineering work-flows and propose an initial assistant system architecture that connects user facing interfaces, credential management, service selection, specialized AI services, and external engineering tools. The proposed architecture aims to support task clarification, requirement and compliance management, communication summarization, integration risk detection, and continuous knowledge capture. In doing so, the paper contributes empirical requirements and an architectural direction for AI augmented cooperative engineering workflows in hybrid human AI team settings.

Figures & tables

Figure 1: Role-adaptive branching structure of the ERC survey.
Figure 2: Self-reported difficulty of knowledge transfer, showing that all teams rated the process as Medium, Difficult, or Very Difficult.
Figure 3: Methods used to monitor task progress, illustrating the predominance of informal updates and limited use of structured tracking tools.
Assigning Tasks - Major Problems%
Unclear task definitions/requirements23%
Ineffective or unused task mgmt tools; poor overview17%
Member availability / scheduling constraints13%
Time pressure; insufficient time or people13%
Planning, prioritization, dependencies, coordination13%
Low engagement, absenteeism, unreliable follow-through13%
Table 4
Monitoring Tasks - Major Problems%
Inconsistent/tardy progress updates; tools not adopted17%
Communication issues (absenteeism, no reporting, no help-seeking)17%
Schedule/deadline mgmt problems; interdependencies; crunch time17%
Monitoring workload/verification overhead13%
Lack of Definition of Done; unclear criteria; poor granularity13%
Delays and low commitment/accountability13%
Table 5
Figure 4: Most frequent rework loops reported by teams, highlighting instability at key transitions such as testing–integration and testing–design.
Figure 5: Primary causes of delays reported by respondents, demonstrating the impact of insufficient early testing, supplier issues, and communication gaps.
Figure 6: Most frequently reported communication problems, showing issues with misunderstandings, missing updates, and delayed responses.
Figure 7: Proposed architecture of the AI-augmented cooperative engineering assistant system.

Explore similar work

CardsList
Apr 9, 2026

Automotive Engineering-Centric Agentic AI Workflow Framework

Engineering workflows such as design optimization, simulation-based diagnosis, control tuning, and model-based systems engineering (MBSE) are iterative, constraint-driven, and shaped by prior decisions. Yet many AI methods still treat these activities as isolated tasks rather than as parts of a broader workflow. This paper presents Agentic Engineering Intelligence (AEI), an industrial vision framework that models engineering workflows as constrained, history-aware sequential decision processes in which AI agents support engineer-supervised interventions over engineering toolchains. AEI links an offline phase for engineering data processing and workflow-memory construction with an online phase for workflow-state estimation, retrieval, and decision support. A control-theoretic interpretation is also possible, in which engineering objectives act as reference signals, agents act as workflow controllers, and toolchains provide feedback for intervention selection. Representative automotive use cases in suspension design, reinforcement learning tuning, multimodal engineering knowledge reuse, aerodynamic exploration, and MBSE show how diverse workflows can be expressed within a common formulation. Overall, the paper positions engineering AI as a problem of process-level intelligence and outlines a practical roadmap for future empirical validation in industrial settings.

Tong Duy Son, Zhihao Liu, Piero Brigida +4

The authors are with Siemens Digital Industries Software, Leuven, Belgium.

Agentic WorkflowsWorkflow AutomationHuman-in-the-Loop AI
AskPDF
Mar 20, 2026

Design-OS: A Specification-Driven Framework for Engineering System Design with a Control-Systems Design Case

Engineering system design -- whether mechatronic, control, or embedded -- often proceeds in an ad hoc manner, with requirements left implicit and traceability from intent to parameters largely absent. Existing specification-driven and systematic design methods mostly target software, and AI-assisted tools tend to enter the workflow at solution generation rather than at problem framing. Human--AI collaboration in the design of physical systems remains underexplored. This paper presents Design-OS, a lightweight, specification-driven workflow for engineering system design organized in five stages: concept definition, literature survey, conceptual design, requirements definition, and design definition. Specifications serve as the shared contract between human designers and AI agents; each stage produces structured artifacts that maintain traceability and support agent-augmented execution. We position Design-OS relative to requirements-driven design, systematic design frameworks, and AI-assisted design pipelines, and demonstrate it on a control systems design case using two rotary inverted pendulum platforms -- an open-source SimpleFOC reaction wheel and a commercial Quanser Furuta pendulum -- showing how the same specification-driven workflow accommodates fundamentally different implementations. A blank template and the full design-case artifacts are shared in a public repository to support reproducibility and reuse. The workflow makes the design process visible and auditable, and extends specification-driven orchestration of AI from software to physical engineering system design.

H. Sinan Bank, Daniel R. Herber, Thomas H. Bradley

Department of Systems Engineering Colorado State University Fort Collins, CO 80523

Agentic WorkflowsHuman-in-the-Loop AI
AskPDF
Oct 4, 2026

Educating future engineers about LLMs: A scalable workshop

As large language models (LLMs) are increasingly integrated into engineering workflows, students require hands-on experience to learn how to collaborate with them critically. This paper presents a scalable gamified workshop designed for engineering Master's students to practice human-AI collaboration in navigation planning. Using a mobile web interface across 10 workshop sessions, a total of 226 students wrote prompts for a non-reasoning and a reasoning LLM to solve grid-based navigation tasks of increasing complexity. The system returned robot-executable plans, trajectory visualizations, and automated scoring, culminating in a live demonstration on a Boston Dynamics Spot robot. In a post-workshop questionnaire, 81.5% reported substantial learning and 91.0% reported high engagement. Analysis of the submitted prompts revealed that students changed their strategies from step-by-step instructions for the non-reasoning LLM toward providing higher-level guidance for complex problem-solving tasks. We conclude that such interactive simulation-to-reality environments are viable for teaching the verification and collaboration skills necessary for responsible LLM use in engineering. Code is available at: https://github.com/renchizhhhh/LLM-robotics-workshop

R. Zhang, J. C. F. de Winter, T. Dicke +2

Faculty of Mechanical Engineering, Delft University of Technology, Delft, The Netherlands

Human-AI CollaborationRobotics EducationPrompt Engineering
AskPDF