dc.contributor.author |
Van Eden, Beatrice
|
|
dc.contributor.author |
Botha, Natasha
|
|
dc.date.accessioned |
2024-01-26T10:16:52Z |
|
dc.date.available |
2024-01-26T10:16:52Z |
|
dc.date.issued |
2023-11 |
|
dc.identifier.citation |
Van Eden, B. & Botha, N. 2023. Simulating object handover between collaborative robots. http://hdl.handle.net/10204/13538 . |
en_ZA |
dc.identifier.uri |
http://hdl.handle.net/10204/13538
|
|
dc.description.abstract |
Collaborative robots are adopted in the drive towards Industry 4.0 to automate manufacturing, while retaining a human workforce. This area of research is known as human-robot collaboration (HRC) and focusses on understanding the interactions between the robot and a human. During HRC the robot is often programmed to perform a predefined task, however when working in a dynamic and unstructured environment this is not achievable. To this end, machine learning is commonly employed to train the collaborative robot to autonomously execute a collaborative task. Most of the current research is concerned with HRC, however, when considering the smart factory of the future investigating an autonomous collaborative task between two robots is pertinent. In this paper deep reinforcement learning (DRL) is considered to teach two collaborative robots to handover an object in a simulated environment. The simulation environment was developed using Pybullet and OpenAI gym. Three DRL algorithms and three different reward functions were investigated. The results clearly indicated that PPO is the best performing DRL algorithm as it provided the highest reward output, which is indicative that the robots were learning how to perform the task, even though they were not successful. A discrete reward function with reward shaping, to incentivise the cobot to perform the desired actions and incremental goals (picking up the object, lifting the object and transferring the object), provided the overall best performance. |
en_US |
dc.format |
Fulltext |
en_US |
dc.language.iso |
en |
en_US |
dc.relation.uri |
https://site.rapdasa.org/wp-content/uploads/2023/10/RAPDASA-Annual-Conference-Book-Complete.pdf |
en_US |
dc.relation.uri |
https://site.rapdasa.org/wp-content/uploads/2023/10/Draft-Programme-2023-RAPDASA-RobMech-PRASA-AMI_20231006.pdf |
en_US |
dc.source |
RAPDASA-RobMech-PRASA-AMI Conference, CSIR International Convention Centre, Pretoria, South Africa, 30 October – 2 November 2023 |
en_US |
dc.subject |
Collaborative robots |
en_US |
dc.subject |
Human-robot collaboration |
en_US |
dc.subject |
HRC |
en_US |
dc.title |
Simulating object handover between collaborative robots |
en_US |
dc.type |
Conference Presentation |
en_US |
dc.description.pages |
17 |
en_US |
dc.description.note |
© The Authors, published by EDP Sciences. This is an open access article distributed under the terms of the Creative Commons Attribution License 4.0 (https://creativecommons.org/licenses/by/4.0/). |
en_US |
dc.description.cluster |
Manufacturing |
en_US |
dc.description.impactarea |
Industrial AI |
en_US |
dc.identifier.apacitation |
Van Eden, B., & Botha, N. (2023). Simulating object handover between collaborative robots. http://hdl.handle.net/10204/13538 |
en_ZA |
dc.identifier.chicagocitation |
Van Eden, Beatrice, and Natasha Botha. "Simulating object handover between collaborative robots." <i>RAPDASA-RobMech-PRASA-AMI Conference, CSIR International Convention Centre, Pretoria, South Africa, 30 October – 2 November 2023</i> (2023): http://hdl.handle.net/10204/13538 |
en_ZA |
dc.identifier.vancouvercitation |
Van Eden B, Botha N, Simulating object handover between collaborative robots; 2023. http://hdl.handle.net/10204/13538 . |
en_ZA |
dc.identifier.ris |
TY - Conference Presentation
AU - Van Eden, Beatrice
AU - Botha, Natasha
AB - Collaborative robots are adopted in the drive towards Industry 4.0 to automate manufacturing, while retaining a human workforce. This area of research is known as human-robot collaboration (HRC) and focusses on understanding the interactions between the robot and a human. During HRC the robot is often programmed to perform a predefined task, however when working in a dynamic and unstructured environment this is not achievable. To this end, machine learning is commonly employed to train the collaborative robot to autonomously execute a collaborative task. Most of the current research is concerned with HRC, however, when considering the smart factory of the future investigating an autonomous collaborative task between two robots is pertinent. In this paper deep reinforcement learning (DRL) is considered to teach two collaborative robots to handover an object in a simulated environment. The simulation environment was developed using Pybullet and OpenAI gym. Three DRL algorithms and three different reward functions were investigated. The results clearly indicated that PPO is the best performing DRL algorithm as it provided the highest reward output, which is indicative that the robots were learning how to perform the task, even though they were not successful. A discrete reward function with reward shaping, to incentivise the cobot to perform the desired actions and incremental goals (picking up the object, lifting the object and transferring the object), provided the overall best performance.
DA - 2023-11
DB - ResearchSpace
DP - CSIR
J1 - RAPDASA-RobMech-PRASA-AMI Conference, CSIR International Convention Centre, Pretoria, South Africa, 30 October – 2 November 2023
KW - Collaborative robots
KW - Human-robot collaboration
KW - HRC
LK - https://researchspace.csir.co.za
PY - 2023
T1 - Simulating object handover between collaborative robots
TI - Simulating object handover between collaborative robots
UR - http://hdl.handle.net/10204/13538
ER -
|
en_ZA |
dc.identifier.worklist |
27453 |
en_US |