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

  1. Automotive Engineering-Centric Agentic AI Workflow Framework

    Apr 9, 2026Tong Duy Son, Zhihao Liu, Piero Brigida +4Agentic WorkflowsWorkflow Automation

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

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

    Mar 20, 2026H. Sinan Bank, Daniel R. Herber, Thomas H. BradleyAgentic WorkflowsHuman-in-the-Loop AI

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

  3. Educating future engineers about LLMs: A scalable workshop

    Oct 4, 2026R. Zhang, J. C. F. de Winter, T. Dicke +2Human-AI CollaborationRobotics Education

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