An AR-assisted Deep Reinforcement Learning-based approach towards mutual-cognitive safe human-robot interaction

Li, Chengxi; Zheng, Pai; Yin, Yue; Pang, Yat Ming; Huo, Shengzeng

doi:10.1016/j.rcim.2022.102471

Cited by 54 publications

(19 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Touch interfaces Tablet [55] Phone [83] Visual augmentation [55,83] Safety [55,83] HM cooperation [55] Web interfaces BLE tags [80] Indoor positioning [80] Occupational safety monitoring [80] Extended reality VR HTC Vive [50,56,65] HTC Vive Pro Eye [85] Facebook Oculus [50] Sony PlayStation VR [50] Handheld sensors [65,85] Training [65] Validation [65] Safe development [56] Data generation [85] Auto-labelling [85] Interaction with virtual environment [74] Robot operation demonstration [50] Online shopping [74] Human productivity and comfort [50] Human action recognition [85] AR HoloLens 2 [51,79,90] Tablet [55] Phone [83] Robot teleoperation [51] Visual augmentation [55,83,90] Real-time interaction [79] Human safety [55,79,83,90] Intuitive humanrobot interaction [51] Productivity [79] MR HoloLens 2 [53,…”

Section: Hmi Technology Specific Technique Task Application Problemmentioning

confidence: 99%

Towards a Human-Centric Digital Twin for Human–Machine Collaboration: A Review on Enabling Technologies and Methods

Krupas,

Kajati,

Liu

et al. 2024

Sensors

View full text Add to dashboard Cite

With the intent to further increase production efficiency while making human the centre of the processes, human-centric manufacturing focuses on concepts such as digital twins and human–machine collaboration. This paper presents enabling technologies and methods to facilitate the creation of human-centric applications powered by digital twins, also from the perspective of Industry 5.0. It analyses and reviews the state of relevant information resources about digital twins for human–machine applications with an emphasis on the human perspective, but also on their collaborated relationship and the possibilities of their applications. Finally, it presents the results of the review and expected future works of research in this area.

show abstract

Section: Hmi Technology Specific Technique Task Application Problemmentioning

confidence: 99%

Towards a Human-Centric Digital Twin for Human–Machine Collaboration: A Review on Enabling Technologies and Methods

Krupas,

Kajati,

Liu

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Xing et al [23] presented a deep learning algorithm based on a multi-agent deep deterministic policy gradient (MADDPG) that can be used to enable a multi-user wireless network by offloading the computation task to the mobile edge computing (MEC) server, reducing the latency and energy consumption of the user terminal for AR application. The study designed by Chengxi et al [12] provided a framework for safe symbiotic human-robot interaction (HRI) by integrating various features such as visual augmentation, velocity control, and collision detection. The proposed method utilizes deep RL for collision avoidance and is enabled through AR.…”

Section: The Use Of Reinforcement Learning With Extended Realitymentioning

confidence: 99%

“…In this research, we present an efficient industrial AR-assisted deep RL-based model [12] that can find a component in a system and view maintenance instructions for relevant failure modes on the operator's smartphone in a portable and real-time approach. Smartphone sensors provide user position with a certain degree of accuracy, but this accuracy does not seem to be enough to prevent errors in the localization and tracking of small objects found in devices such as the NanoDrop Spectrophotometer.…”

Section: Introductionmentioning

confidence: 99%

Augmented Reality-Assisted Deep Reinforcement Learning-Based Model towards Industrial Training and Maintenance for NanoDrop Spectrophotometer

Alatawi,

Albalawi,

Shahata

et al. 2023

Sensors

View full text Add to dashboard Cite

The use of augmented reality (AR) technology is growing in the maintenance industry because it can improve efficiency and reduce costs by providing real-time guidance and instruction to workers during repairs and maintenance tasks. AR can also assist with equipment training and visualization, allowing users to explore the equipment’s internal structure and size. The adoption of AR in maintenance is expected to increase as hardware options expand and development costs decrease. To implement AR for job aids in mobile applications, 3D spatial information and equipment details must be addressed, and calibrated using image-based or object-based tracking, which is essential for integrating 3D models with physical components. The present paper suggests a system using AR-assisted deep reinforcement learning (RL)-based model for NanoDrop Spectrophotometer training and maintenance purposes that can be used for rapid repair procedures in the Industry 4.0 (I4.0) setting. The system uses a camera to detect the target asset via feature matching, tracking techniques, and 3D modeling. Once the detection is completed, AR technologies generate clear and easily understandable instructions for the maintenance operator’s device. According to the research findings, the model’s target technique resulted in a mean reward of 1.000 and a standard deviation of 0.000. This means that all the rewards that were obtained in the given task or environment were exactly the same. The fact that the reward standard deviation is 0.000 shows that there is no variability in the outcomes.

show abstract

“…As one of the paradigms or methodologies of machine learning, reinforcement learning 38,39 has been developed to describe and solve the matter that agents learn strategies to maximize rewards or achieve specific goals in the process of interacting with the environment, which is introduced into manufacturing to provide human-level decision making. 40 As one of the important branches, DRL 41 is widely used in AGV path planning, 42 process planning, 43 human-robot collaboration, 44 et al Furthermore, a multi-agent reinforcement learning-based anti-conflict AGV path planning problem was studied to improve transportation cost and operation efficiency. 45 From the above research, the fundamental purpose of various AGV path planning algorithms is to propel separate vehicles to take the most optimal path possible toward the target point without interfering with each other.…”

Section: Path Planning For Agvs In Manufacturingmentioning

confidence: 99%

A digital twin-driven dynamic path planning approach for multiple automatic guided vehicles based on deep reinforcement learning

Bao

Zheng

Dai

2023

Proceedings of the Institution of Mechanical Engineers, Part B:

Self Cite

View full text Add to dashboard Cite

With the increasing demand for customization, the tendency of mechanical manufacturing has gradually shifted to flexible and mixed-line production, which brings new challenges to the existing scheduling pattern. As an indispensable part, logistics is responsible for establishing connections among various production equipment and processes. Meanwhile, the promotion of digital twin theory introduces an application schema for the logistics system. However, there is still a deficiency in the real-time dispatching and path planning of logistics equipment due to the uncontrollability of algorithm efficiency for complex scenes. To fill this gap, a digital twin-driven dynamic path planning approach for multiple automatic guided vehicles (AGVs) is proposed. Firstly, the AGVs are virtualized as the major component of logistics systems, while the ontology expression of logistics tasks is consistently accomplished as well. Secondly, the digital twin-driven application framework of multi-AGV dispatching is established. Moreover, a dynamic path planning method for AGVs relying on deep reinforcement learning is implemented. A segmented path planning method is illustrated considering potential route conflicts, which is regarded as the key contribution of the presented research. At last, a case study is illustrated to show the entire process of multiple vehicle path planning and conflict resolution.

show abstract

An AR-assisted Deep Reinforcement Learning-based approach towards mutual-cognitive safe human-robot interaction

Cited by 54 publications

References 22 publications

Towards a Human-Centric Digital Twin for Human–Machine Collaboration: A Review on Enabling Technologies and Methods

Towards a Human-Centric Digital Twin for Human–Machine Collaboration: A Review on Enabling Technologies and Methods

Augmented Reality-Assisted Deep Reinforcement Learning-Based Model towards Industrial Training and Maintenance for NanoDrop Spectrophotometer

A digital twin-driven dynamic path planning approach for multiple automatic guided vehicles based on deep reinforcement learning

Contact Info

Product

Resources

About