Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Safe Human Robot Navigation in Warehouse Scenario

Seth Farrell, Chenghao Li, Hongzhan Yu, Ryo Yoshimitsu, Sicun Gao, Henrik I. Christensen

TL;DR

This work proposes a novel methodology that leverages control barrier functions (CBFs) to enhance safety in warehouse navigation by integrating learning-based CBFs with the Open Robotics Middleware Framework (OpenRMF), which achieves adaptive and safety-enhanced controls in multi-robot, multi-agent scenarios.

Abstract

The integration of autonomous mobile robots (AMRs) in industrial environments, particularly warehouses, has revolutionized logistics and operational efficiency. However, ensuring the safety of human workers in dynamic, shared spaces remains a critical challenge. This work proposes a novel methodology that leverages control barrier functions (CBFs) to enhance safety in warehouse navigation. By integrating learning-based CBFs with the Open Robotics Middleware Framework (OpenRMF), the system achieves adaptive and safety-enhanced controls in multi-robot, multi-agent scenarios. Experiments conducted using various robot platforms demonstrate the efficacy of the proposed approach in avoiding static and dynamic obstacles, including human pedestrians. Our experiments evaluate different scenarios in which the number of robots, robot platforms, speed, and number of obstacles are varied, from which we achieve promising performance.

Safe Human Robot Navigation in Warehouse Scenario

TL;DR

This work proposes a novel methodology that leverages control barrier functions (CBFs) to enhance safety in warehouse navigation by integrating learning-based CBFs with the Open Robotics Middleware Framework (OpenRMF), which achieves adaptive and safety-enhanced controls in multi-robot, multi-agent scenarios.

Abstract

The integration of autonomous mobile robots (AMRs) in industrial environments, particularly warehouses, has revolutionized logistics and operational efficiency. However, ensuring the safety of human workers in dynamic, shared spaces remains a critical challenge. This work proposes a novel methodology that leverages control barrier functions (CBFs) to enhance safety in warehouse navigation. By integrating learning-based CBFs with the Open Robotics Middleware Framework (OpenRMF), the system achieves adaptive and safety-enhanced controls in multi-robot, multi-agent scenarios. Experiments conducted using various robot platforms demonstrate the efficacy of the proposed approach in avoiding static and dynamic obstacles, including human pedestrians. Our experiments evaluate different scenarios in which the number of robots, robot platforms, speed, and number of obstacles are varied, from which we achieve promising performance.

Paper Structure

This paper contains 15 sections, 4 equations, 3 figures, 4 tables.

Table of Contents

  1. INTRODUCTION
  2. RELATED WORKS
  3. Preliminary
  4. Methodology - Safety
  5. Data Collection
  6. Dynamics Learning
  7. Neural CBF Learning
  8. Training Preparation
  9. Training Objectives
  10. Deriving Controls with Neural CBFs
  11. SYSTEM OVERVIEW
  12. EXPERIMENTS
  13. Unit Task Evaluation
  14. OpenRMF Experiments
  15. CONCLUSION

Figures (3)

  • Figure 1: Humans walk around the test area, while the robots attempt to reach their goal points without collisions. OpenRMF is used to schedule the high-level task assignment while the on-board Control Barrier Function (CBF) outputs control commands which guide the robot toward safe states.
  • Figure 2: Overview of the warehouse system: (a) Visualization of OpenRMF Map. The robots are not confined to the illustrated lanes and can freely navigate throughout the environment as needed. (b) System architecture. (c) Real-world robots, from left to right: Freight, Jackal, and two Megarovers.
  • Figure 3: Red, green, and brown trajectories represent robots operating at maximum speeds of 0.5 m/s, 1.0 m/s, and 1.5 m/s, respectively. In (a), a circular unsafe range is marked. In (b), the blue trajectory represents a pedestrian’s movement. In (c) shows a head-to-head scenario where the Freight and Jackal start from opposite ends and move toward each other’s initial positions. The timestamps indicate the moments when the robot is at the minimum distance from an obstacle.

Theorems & Definitions (1)

  • Definition 1: Control Barrier Functions c23