Scalable and low-cost remote lab platforms: Teaching industrial robotics using open-source tools and understanding its social implications

TL;DR

This paper tackles the barrier of high costs and safety concerns in industrial robotics education by proposing two scalable, low-cost remote-lab platforms built on open-source tools (ROS and ROS 2) and deployed with UR5 arms and mobile rovers in greenhouse and warehouse testbeds for AAHS and AWMS. The authors implement two architectures—Stack 1 with peer-to-peer VPN and Stack 2 with VPN plus remote desktop (VNC)—to enable large numbers of students to develop and test robotics algorithms first in simulation and then on real hardware, across six months of activity in the e-Yantra Robotics Competition. Results show thousands of students being trained (1,433 for AAHS and 1,312 for AWMS) and substantial hardware interaction hours (160 and 355), with finalists achieving fully autonomous solutions, demonstrating the platforms’ potential for scalable, open-source robotics education. Limitations include host-operator workload and latency, pointing to future work on automated resets, latency reduction, and broader automation of the greenhouse and warehouse environments.

Abstract

With recent advancements in industrial robots, educating students in new technologies and preparing them for the future is imperative. However, access to industrial robots for teaching poses challenges, such as the high cost of acquiring these robots, the safety of the operator and the robot, and complicated training material. This paper proposes two low-cost platforms built using open-source tools like Robot Operating System (ROS) and its latest version ROS 2 to help students learn and test algorithms on remotely connected industrial robots. Universal Robotics (UR5) arm and a custom mobile rover were deployed in different life-size testbeds, a greenhouse, and a warehouse to create an Autonomous Agricultural Harvester System (AAHS) and an Autonomous Warehouse Management System (AWMS). These platforms were deployed for a period of 7 months and were tested for their efficacy with 1,433 and 1,312 students, respectively. The hardware used in AAHS and AWMS was controlled remotely for 160 and 355 hours, respectively, by students over a period of 3 months.

Figures (5)

• Figure 1: Set up of remote testbeds in a greenhouse (top) and a warehouse (bottom) for Autonomous Agricultural Harvester System (AAHS) and Autonomous Warehouse Management System (AWMS) using a UR5 robotic arm and a mobile rover. Students used our platforms to test their algorithms in the simulated-world (left) and real-world (right).
• Figure 2: Operational Workflow Architecture of Stacks 1 and 2 for remote lab platform: The architecture is divided into two major sections: The Student and Host Side. Stack 1 uses only a peer-to-peer VPN, whereas Stack 2 uses a combination of peer-to-peer VPN and remote desktop application.
• Figure 3: Self-reported expertise by students in both years of eYRC before the start of the competition.
• Figure 4: Performance of teams in each task during the two separate editions of eYRC. A total of 197 teams participated in eYRC 2022-23, whereas 296 teams participated in eYRC 2023-24. Teams were awarded a bonus if they completed the submission within the deadline.
• Figure 5: Total remote access slots (hours) given per hardware task vs the number of teams participating in the task. More remote access hours were provided for complex tasks.