Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Infrastructure-based Autonomous Mobile Robots for Internal Logistics -- Challenges and Future Perspectives

Erik Brorsson, Kristian Ceder, Ze Zhang, Sabino Francesco Roselli, Endre Erős, Martin Dahl, Beatrice Alenljung, Jessica Lindblom, Thanh Bui, Emmanuel Dean, Lennart Svensson, Kristofer Bengtsson, Per-Lage Götvall, Knut Åkesson

TL;DR

This paper proposes RAIL, a reference architecture for infrastructure-based AMRs in internal logistics, integrating ceiling-mounted sensing, on-premise cloud computing, and onboard autonomy. It covers core technologies—localization, perception, and planning—through a detailed review and demonstrates feasibility with an industrial Volvo deployment and UX evaluation. Key contributions include the architecture, technology review, and real-world insights into deployment challenges and user experience. The work highlights the potential of infrastructure-enabled autonomy to deliver scalable, safe, and human-centered AMR solutions in dynamic industrial environments.

Abstract

The adoption of Autonomous Mobile Robots (AMRs) for internal logistics is accelerating, with most solutions emphasizing decentralized, onboard intelligence. While AMRs in indoor environments like factories can be supported by infrastructure, involving external sensors and computational resources, such systems remain underexplored in the literature. This paper presents a comprehensive overview of infrastructure-based AMR systems, outlining key opportunities and challenges. To support this, we introduce a reference architecture combining infrastructure-based sensing, on-premise cloud computing, and onboard autonomy. Based on the architecture, we review core technologies for localization, perception, and planning. We demonstrate the approach in a real-world deployment in a heavy-vehicle manufacturing environment and summarize findings from a user experience (UX) evaluation. Our aim is to provide a holistic foundation for future development of scalable, robust, and human-compatible AMR systems in complex industrial environments.

Infrastructure-based Autonomous Mobile Robots for Internal Logistics -- Challenges and Future Perspectives

TL;DR

This paper proposes RAIL, a reference architecture for infrastructure-based AMRs in internal logistics, integrating ceiling-mounted sensing, on-premise cloud computing, and onboard autonomy. It covers core technologies—localization, perception, and planning—through a detailed review and demonstrates feasibility with an industrial Volvo deployment and UX evaluation. Key contributions include the architecture, technology review, and real-world insights into deployment challenges and user experience. The work highlights the potential of infrastructure-enabled autonomy to deliver scalable, safe, and human-centered AMR solutions in dynamic industrial environments.

Abstract

The adoption of Autonomous Mobile Robots (AMRs) for internal logistics is accelerating, with most solutions emphasizing decentralized, onboard intelligence. While AMRs in indoor environments like factories can be supported by infrastructure, involving external sensors and computational resources, such systems remain underexplored in the literature. This paper presents a comprehensive overview of infrastructure-based AMR systems, outlining key opportunities and challenges. To support this, we introduce a reference architecture combining infrastructure-based sensing, on-premise cloud computing, and onboard autonomy. Based on the architecture, we review core technologies for localization, perception, and planning. We demonstrate the approach in a real-world deployment in a heavy-vehicle manufacturing environment and summarize findings from a user experience (UX) evaluation. Our aim is to provide a holistic foundation for future development of scalable, robust, and human-compatible AMR systems in complex industrial environments.

Paper Structure

This paper contains 42 sections, 7 figures.

Table of Contents

  1. Introduction
  2. Automated Transports for Internal Logistics
  3. Problem formulation
  4. Reference Architecture
  5. Key Technologies
  6. Localization
  7. Environment Perception
  8. Detection
  9. Multi-object tracking
  10. Motion prediction
  11. Fleet management and planning
  12. Scheduling and route planning
  13. Behavioral decision making
  14. Path planning
  15. Motion planning
  16. ...and 27 more sections

Figures (7)

  • Figure 1: Three of the autonomous transport robots operating inside the factory.
  • Figure 2: RAIL: a Reference Architecture for Infrastructure-based AMR Systems in Internal Logistics.
  • Figure 3: Example perception results in a factory environment. Semantic segmentation is used to find static obstacles (red) and bounding box detection is used for vehicles (blue). Object tracking estimates the past trajectory of the vehicle (blue arrow), and motion prediction creates multiple hypothesis for the future movement (red arrows).
  • Figure 4: Overview of the fleet management and planning framework. Arrows from the left correspond to output from the perception module, while arrows from the right are user specifications.
  • Figure 5: The transportation robot. The scene was reconstructed using Gaussian splatting ahmed2025realistisk.
  • ...and 2 more figures