Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Safety-Critical Edge Robotics Architecture with Bounded End-to-End Latency

Gautam Gala, Tilmann Unte, Luiz Maia, Johannes Kühbacher, Isser Kadusale, Mohammad Ibrahim Alkoudsi, Gerhard Fohler, Sebastian Altmeyer

TL;DR

This work addresses the need for safe, real-time execution in robotics by moving computationally heavy, safety-critical tasks from onboard hardware to edge nodes. It proposes an edge-centric architecture built on Linux, Docker, Kubernetes, and a time-triggered TTWiFi wireless network, augmented with a Local Resource Manager to guarantee bounded end-to-end latency. Key contributions include the RT-oriented edge framework, the RMO layer with MON/LRS components, and a TTWiFi-based communication scheme to achieve predictable timing while preserving safety and security. The approach demonstrates potential to reduce robot size, weight, and power while enabling scalable, hardware-independent operation suitable for industrial robotics use cases, with future work focused on end-to-end demonstrations and validation of latency guarantees.

Abstract

Edge computing processes data near its source, reducing latency and enhancing security compared to traditional cloud computing while providing its benefits. This paper explores edge computing for migrating an existing safety-critical robotics use case from an onboard dedicated hardware solution. We propose an edge robotics architecture based on Linux, Docker containers, Kubernetes, and a local wireless area network based on the TTWiFi protocol. Inspired by previous work on real-time cloud, we complement the architecture with a resource management and orchestration layer to help Linux manage, and Kubernetes orchestrate the system-wide shared resources (e.g., caches, memory bandwidth, and network). Our architecture aims to ensure the fault-tolerant and predictable execution of robotic applications (e.g., path planning) on the edge while upper-bounding the end-to-end latency and ensuring the best possible quality of service without jeopardizing safety and security.

Safety-Critical Edge Robotics Architecture with Bounded End-to-End Latency

TL;DR

This work addresses the need for safe, real-time execution in robotics by moving computationally heavy, safety-critical tasks from onboard hardware to edge nodes. It proposes an edge-centric architecture built on Linux, Docker, Kubernetes, and a time-triggered TTWiFi wireless network, augmented with a Local Resource Manager to guarantee bounded end-to-end latency. Key contributions include the RT-oriented edge framework, the RMO layer with MON/LRS components, and a TTWiFi-based communication scheme to achieve predictable timing while preserving safety and security. The approach demonstrates potential to reduce robot size, weight, and power while enabling scalable, hardware-independent operation suitable for industrial robotics use cases, with future work focused on end-to-end demonstrations and validation of latency guarantees.

Abstract

Edge computing processes data near its source, reducing latency and enhancing security compared to traditional cloud computing while providing its benefits. This paper explores edge computing for migrating an existing safety-critical robotics use case from an onboard dedicated hardware solution. We propose an edge robotics architecture based on Linux, Docker containers, Kubernetes, and a local wireless area network based on the TTWiFi protocol. Inspired by previous work on real-time cloud, we complement the architecture with a resource management and orchestration layer to help Linux manage, and Kubernetes orchestrate the system-wide shared resources (e.g., caches, memory bandwidth, and network). Our architecture aims to ensure the fault-tolerant and predictable execution of robotic applications (e.g., path planning) on the edge while upper-bounding the end-to-end latency and ensuring the best possible quality of service without jeopardizing safety and security.
Paper Structure (28 sections, 4 equations, 5 figures, 1 table)

This paper contains 28 sections, 4 equations, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Real-time cloud computing
  4. Cloud-based robotics
  5. Existing Industrial Robotics Use Case
  6. Magni Robot
  7. OS and Middleware
  8. Top-Level Application
  9. RT-Cloud for Industrial Robotics Use Case
  10. Why use edge-cloud?
  11. What can we run in the edge?
  12. What are the requirements for running in the edge?
  13. Edge component selection
  14. Virtualization layer
  15. Fine-tuning of edge nodes
  16. ...and 13 more sections

Figures (5)

  • Figure 1: Ubiquity Robotics Magni robot with custom attachment for Slamtech RPLIDAR A1M8 sensor on its top plate
  • Figure 2: Our proposed hardware setup for a real-time capable robot controller. Below the dashed line are the proprietary components of the Magni robot. Above is our work, centered around a microcontroller running Zephyr OS.
  • Figure 3: Outline of the individual steps of the Monte-Carlo Localization (MCL) algorithm running on an edge device. The dashed arrows indicate wireless communication. The Magni diagrams shown on the left and right correspond to a single physical robot and can be seen as the start and end points of the complete control loop.
  • Figure 4: Robot and Edge Node Architecture
  • Figure 5: Observed execution time for MCL + Path Finder