Heterogeneous neuromorphic processor based on RISC-V architecture for real-time robotics tasks

Zelensky, Alexander A.; Alepko, Andrey; Dubovskov, Vadim; Kuptsov, Vladimir

doi:10.1117/12.2574470

Cited by 4 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It enables a virtual connection to a digital manufacturing model over high-speed virtual industrial links that reflect the full functionality of real links. This allows further use of the developed control system elements on real objects without additional configuration, for example, sensor software components for collaborative robotics tasks [23][24].…”

Section: Simulation and Experimental Resultsmentioning

confidence: 99%

Action recognition algorithm from visual sensor data for contactless robot control systems

Voronin

Zhdanova

Khamidullin

et al. 2022

Artificial Intelligence and Machine Learning in Defense Applications IV

View full text Add to dashboard Cite

Automation of production processes using robots is a priority for the development of many industrial enterprises. Robotization is aimed at freeing a person from dangerous or routine work. At the same time, robots are able to perform tasks more efficiently than human, and the collaboration of a human and a robot allows to combine the strengths and effectiveness of robots and human cognitive ability into a single flexible system, and as a result, organize flexible methods of automation and reconfiguration of production processes. In this work, we focused on the implementation of the method of interaction between a person and a robot based on the recognition of gesture commands of a human-operator. An approach based on extraction a human skeleton and classification using a neural network is proposed as a method for recognizing actions. To test the effectiveness of the proposed algorithm, the possibility of transmitting gesture commands to the robot and organizing a contactless control method of the robot, simulation modeling was carried out in the RoboGuid environment. This environment is for industrial robots, provided by Fanuc.

show abstract

Section: Simulation and Experimental Resultsmentioning

confidence: 99%

Action recognition algorithm from visual sensor data for contactless robot control systems

Voronin

Zhdanova

Khamidullin

et al. 2022

Artificial Intelligence and Machine Learning in Defense Applications IV

View full text Add to dashboard Cite

show abstract

“…В этой области значение интенсивности центрального пикселя, взятого за порог, сравнивается со значением соседних 8 пикселей (12). Если значение пикселя превышает пороговое значение, этому пикселю присваивается 1, в противном случае -0 (13). Таким образом, результатом применения основного оператора LBP к пикселю является 8-битный двоичный код, описывающий окрестность этого пикселя [24].…”

Section: взаимоопыляемый характер информации получаемой различными сп...unclassified

Virtual Interface Technology in the Process of Simulation of Complex Functional Modules of Control Systems for Industrial Robots and Multi-Axis Mechatronic Systems

Zelensky

Zhdanova

Abdullin

et al. 2022

Proceedings of the SWSU

View full text Add to dashboard Cite

Purpose of research. Development of a tool for debugging intelligent control system algorithms, including the development of a vision system and planning a software trajectory for an industrial robot.Methods. To achieve this goal, a review of existing simulation tools was carried out. A protocol of contactless humanrobot interaction is presented. An algorithm for the recognition of gesture commands based on the difference of three-dimensional binary microblocks and the construction of the skeleton of the human body has been developed. An example of using the ROBOGuid software tool for imitating the motion of an industrial robot in the development and debugging of its own control methods focused on real objects is presented.Results. The use of digital twins of technological equipment to simulate and display real technological processes in a virtual environment, in the context of the formation of a new concept of Industry 4.0 and the sixth technological order, allows improving the main and auxiliary production processes, as well as analyzing, researching and evaluating the economic efficiency of new technological and technical solutions. Simulation allows the development of ergonomic ways of human interaction with mechatronic objects. The solution proposed in the work was tested on the example of working out a complex spatial contour that simulates the milling of a part. Experimental studies of the gesture command recognition algorithm proposed in the work were carried out on the publicly available UCF101 dataset, the results are compared with known approaches to recognizing human actions.Conclusion. The developed interface module was used on the example of working out a complex spatial contour that simulates the milling of a part, and the method of a contactless robot control system has shown its effectiveness and the need to develop this direction.

show abstract

Evaluation of HPC Workloads Running on Open-Source RISC-V Hardware

Berger-Vergiat,

Cardwell,

Feinberg

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Heterogeneous neuromorphic processor based on RISC-V architecture for real-time robotics tasks

Cited by 4 publications

References 6 publications

Action recognition algorithm from visual sensor data for contactless robot control systems

Action recognition algorithm from visual sensor data for contactless robot control systems

Virtual Interface Technology in the Process of Simulation of Complex Functional Modules of Control Systems for Industrial Robots and Multi-Axis Mechatronic Systems

Evaluation of HPC Workloads Running on Open-Source RISC-V Hardware

Contact Info

Product

Resources

About