Autonomous mobile robots in manufacturing: Highway Code development, simulation, and testing

Abstract

A dynamic and flexible manufacturing environment presents many challenges in the movement of autonomous mobile robots (AMRs), leading to delays due to the complexity of operations while negotiating even a simple route. Therefore, an understanding of rules related to AMR movement is important both from a utility perspective as well as a safety perspective. Our survey from literature and industry has revealed a gap in methodology to test rules related to AMR movement in a factory environment. Testing purely through simulations would not able to capture the nuances of shop floor interactions whereas physical testing alone would be incredibly time-consuming and potentially hazardous. This work presents a new methodology that can make use of observations of AMR behaviour on selected cases on the shop floor and build up the fidelity of those simulations based on observations. This paper presents the development of a Highway Code for AMRs, development of simulation models for an ideal AMR (based on the rules from the Highway Code), and physical testing of real AMR in an industrial environment. Finally, a behavioural comparison of an ideal AMR and a real AMR in five scenarios (taken from the shop floor of an industrial partner) is presented. This work could enable informed decisions regarding the implementation of AMRs through identification of any adverse behaviours which could then be mitigated either through improvements on the AMR or through establishing shop floor protocols that reduce the potential impact of these behaviours.Publisher's note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.Int J Adv Manuf Technol (2019) 104:4617-4628

Reinforcement Learning for Position Control Problem of a Mobile Robot

“…As can be seen, the IPC algorithm shows the shortest trajectory (but not necessarily the fastest) to the target point. As in the previous case, table 3 shows the performance indexes obtained for the IPC algorithm and the RL algorithms. As can be seen, the performance indexes are very similar.…”

“…R OBOTICS has been very popular over the last few years. Today it is very common to find robots performing different tasks in many areas of our daily lives including social environments, agriculture [1], logistics [2], manufacturing [3], medicine [4], and education [5], just to mention a few of them.…”

Enabling Flexibility in Manufacturing by Integrating Shopfloor and Process Perception for Mobile Robot Workers

“…The introduction of these robots in assembly lines also enables reduced duration of breakdowns, lower commissioning time, minimum need for human intervention due to their autonomous behavior and higher production variability [12]. Developments of mobile robots have led to various relevant research topics, such as methodologies that can make use of observations of mobile robots on shop floors and build up the fidelity of simulations based on those shop floors [13].…”

Human–Robot Interaction in Industrial Settings: Perception of Multiple Participants at a Crossroad Intersection Scenario with Different Courtesy Cues

“…Compared to AGVs, AMRs are more flexible, collaborative, and cost-efficient [3]. This type of robot can move autonomously without the help of external workers [6] and they can detect obstacles and recalculate a new route around them [7]. The autonomy of AMRs implies continuous decision-making on how to behave according to their environment, with predefined rules and constraints [4].…”