scholarly journals The Agile Robotics for Industrial Automation Competition

AI Magazine ◽  
2018 ◽  
Vol 39 (4) ◽  
pp. 73-76 ◽  
Author(s):  
William Harrison ◽  
Anthony Downs ◽  
Craig Schlenoff
Keyword(s):  
Dynamic Environment ◽  
Robotic System ◽  
System Control ◽  
Industrial Automation ◽  
Control Code ◽  
Simulation Based

The Agile Robotics for Industrial Automation Competition (ARIAC) is an annual simulation-based competition initiated in 2017. The competition challenges teams to design industrial robotic system control code to function in a dynamic environment. Each team’s system is faced with challenges such as dropped parts, and must address these challenges and continue to function without operator intervention.

An Application of a Digital Twin to Robotic System Design for an Unstructured Environment

2019 ◽  
Author(s):  
Matthew Q. Marshall ◽  
Cameron Redovian
Keyword(s):  
Life Stage ◽  
Robotic System ◽  
Ease Of Use ◽  
Design Decision ◽  
Feed System ◽  
Design Decisions ◽  
Digital Twin ◽  
Simulation Based ◽  
Unstructured Environment ◽  
Mobile Base

Abstract An experimentable digital twin is created to aid in a design decision (beginning of life stage) for a robotic system. This product is meant to automate a material-feed system. The robot comprises a six-axis manipulator mounted on a mobile base. Due to variability in the dimensions of the material-feed system and positioning error of the mobile base, the material-placement routine is considered to take place in an unstructured environment. Working therein requires exteroceptive sensors, in this instance taking the form of computer vision. Data from this subsystem are used to match the geometry of the digital twin to the physical environment. This close correspondence between physical and virtual embodiments allows for significant design decisions to be reached from simulated experiments. In this case, two motion-planning approaches are compared and it is determined that the costs associated with implementing the dynamic one in the lab for testing are merited by its ease of use and reliability, since simulation-based control employs all current information.

A Kind of Improved RED Algorithm of WSN Oriented to Self-Similar Traffic

2011 ◽  
Vol 214 ◽  
pp. 549-553
Author(s):  
Yu Jiao Wang ◽  
Hai Yun Lin
Keyword(s):  
Linear Relationship ◽  
Transmission Rate ◽  
Network Routing ◽  
Loss Probability ◽  
Wireless Sensor ◽  
System Control ◽  
Self Similarity ◽  
Management Algorithm ◽  
Simulation Based ◽  
Self Similar

Active queue management algorithm works at network routing node. It notifies terminal system control transmission rate in advance with discard or mark packet before buffer queue overflows, so as to avoid congestion. Aiming at characteristics of wireless sensor network (WSN) and based on introduction of traditional RED algorithm, the paper introduced H parameter to represent traffic similarity to original linear relationship between packet loss probability and average queue length to form the non-linear relationship related to self-similarity. Then a kind of improved RED algorithm of WSN oriented to self-similar traffic was proposed. The detail implementation flow was also provided. Simulation based on OPNET shows that the improved RED is superior to traditional RED algorithm in steady performance.

Robotic industrial automation simulation-optimization for resolving conflict and deadlock

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Hamed Fazlollahtabar ◽  
Mohammad Saidi-Mehrabad ◽  
Ellips Masehian
Keyword(s):  
Optimization Technique ◽  
Optimal Path ◽  
Advanced Technology ◽  
Design Parameters ◽  
Industrial Automation ◽  
Content Type ◽  
Simulation Based ◽  
Effective Design ◽  
Agv Systems

Purpose The purpose of this study is to investigate the benefits of the turning point layout; a simulation model being applicable for strategic level is designed that compares systems with and without turning points. Specifically, the avoidance of deadlocks and prevention of conflicts is substantial. Design/methodology/approach Optimization process for different layouts and configuration of autonomous guided vehicles (AGVs) are worked out using statistical methods for design parameters. Regression analysis is used to find effective design parameters and analysis of variance is applied for adjusting critical factors. Also, the optimal design is then implemented in a manufacturing system for an industrial automation and the results are reported. Findings The outputs imply the effectiveness of the proposed approach for real industrial cases. This research will combine both simulation-based method and optimization technique to improve the quality of solutions. Originality/value In AGV systems, the begin-end combinations are usually connected by using a fixed layout, which is not the optimal path. The capability of these configurations is limited and often the conflict of multiple AGVs and deadlock are inevitable. By appearing more flexible layouts and advanced technology, the positioning and dispatching of AGVs increased. A new concept would be to determine each path dynamically. This would use the free paths for AGVs leading to overcome the conflicts and deadlocks.

Robotic system design: A hierarchical simulation-based approach

1995 ◽  
Vol 29 (1-4) ◽  
pp. 699-703
Author(s):  
Lorace L. Massay ◽  
Silvanus J. Udoka ◽  
Bala Ram
Keyword(s):  
System Design ◽  
Robotic System ◽  
Simulation Based

Simulation on Networked Munitions System Control with Time Delay

2013 ◽  
Vol 347-350 ◽  
pp. 11-14
Author(s):  
Ping Sun ◽  
Shou Wei Hu ◽  
Wei Wang
Keyword(s):  
Wireless Networks ◽  
Time Delay ◽  
Wireless Communication ◽  
Time Delays ◽  
System Control ◽  
Weapon System ◽  
Control Performance ◽  
Electronic Technology ◽  
Simulation Based ◽  
New Generation

Networked munitions system is becoming more and more important with the development of modern electronic technology. This new generation of ground-based munitions are much more intelligent for the capability they have to trace targets, communicate with each other and order a killing node for vehicles caught in the kill-zone . It is useful to study and attempt to model through simulations the interaction between enemy targets and the whole munitions system . This paper is to propose a simulation-based model to study the performances of the weapon system. Especially, the sensors which sense the environment and the weapons which attack the targets are connected with wireless networks that will bring time delay to the system. We focus our efforts to evaluate how time delays from wireless communication affect the control performance of the weapon. This study introduces models for sensors and communication routing mechanisms , as well as the servo system and vehicle targets. A series of simulation trials to analyze and compare the effects of time delays have on the killing efficiency. The results of the study indicate in general that communication delay have the most effect on the systems.

scholarly journals Active physical inference via reinforcement learning

2019 ◽  
Author(s):  
Shuaiji Li ◽  
Yu Sun ◽  
Sijia Liu ◽  
Yu Sun ◽  
Todd Matthew Gureckis ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Physical Properties ◽  
Dynamic Environment ◽  
Human Behaviors ◽  
Simulation Based ◽  
Physical Information ◽  
Physical Objects ◽  
Similar Task

When encountering unfamiliar physical objects, children and adults often perform structured interrogatory actions such as grasping and prodding, so revealing latent physical properties such as masses and textures. However, the processes driving and supporting these curious behaviors are still largely mysterious. In this paper, we develop and train an agent able to actively uncover latent physical properties such as the mass and force of objects in a simulated physical "micro-world". Concretely, we used a simulation-based-inference framework to quantify the physical information produced by observation and interaction with the evolving dynamic environment. We used reinforcement learning to train an agent to implement general strategies for revealing latent physical properties. We compare the behaviors of this agent to the human behaviors observed in a similar task.

Sign in / Sign up

Export Citation Format

Share Document