2023 06 29 Telecom SIG Distributed Robotics Systems

2023 06 29 Telecom SIG Distributed Robotics Systems

Show Video

salma: Okay, thank you for inviting me for this presentation to present our research group. and I'm going to talk about the integration of hyper, ledger fabric and cross to for distributed robotic systems and some salma: results of our real work experiments in our lab. so for my presentation salma: I'm I will start with this small introduction about our research team tiers and University of Toku. Then I will give an introduction of Hyperlink and Ross to and then go over some real work, examples and scenarios, and and then finally talk about the results that we had salma: for for intelligence embedded and robotic systems, and our research where to go of can solve edge intelligence, resilience with some of the main distributed systems, like foreign intelligence and collaborative autonomy, and so on salma: and salma: In this presentation we will explore how blockchain technology can be integrated with advanced robotics to enable trustable data sharing and robot control. salma: And we will examine the real world examples of scenarios, of a scalable collaborating and reliable robotic systems and discover their potential in various industries.

salma: I know, you know. But I'm gonna give some some introduction about the fabric. Also, as you know, Hyper Ledger is one of the biggest platforms in the Permission blockchain, and it is the Open Source Project based on Linux Foundation. salma: It provides projects and frameworks to businesses and developers to build the blockchain networks and applications. And it's aims to ease the collaboration between developers, enterprises, and businesses in the field of distributed ledger technology salma: as the advantage it. It offers a robust set of features that makes it suitable for integrating blockchain into distributed robotic systems. It's permission network architecture ensures that only authorized participants can join the network and access share their data and then module. Our architecture allows for flexibility and customization, enabling developers to tailor the

salma: blockchain network to their specific requirements, and it supports smart contracts enabling the execution of automated businesses logic on the blockchain. salma: But if I want to talk about the robotic side, I'm going to talk about the Ross, which is basically it's going to be their name talk today. And what is Ross? salma: Before the introduction of Ross robotics development was often lacked a standardized framework developers had to build their own custom solutions for communication, coordination and integration of robots, components, leading lots of efforts salma: and collaboration among researchers and sharing the calls and resources over challenging the absence of a unified platform made it harder to prototype test and deploy robot applications. Increasing development time complexity. salma: Ross revolutionized robotics by providing a common framework, fostering collaboration, promoting and simplifying the development process, accelerating the investment in the field.

salma: first. salma: Ross developed. Ross oh, is also known as Ross one. It was initially released in 2,007, and has since become widely adopted in the robotics community. It provides flexible and modular framework for developing robot software. It allows developers to break down complex robot applications into smaller reusable components called packages promoting code modularity and usability salma: it uses, publish a subscribe messages system which we call them topics to enable communication between different components of the robotic systems. And it was primarily supports. It's primarily support single host systems and is mainly used for research and prototyping applications. salma: It has a large ecosystem of package and tools that, moved by the community and making it easier to leverage existing functionality and collaborate with others.

salma: if you see, I put an example of how Ross one works and how robots can communicate with each other in the presence of Ross, master, they can have publisher know the subscriber node when the where the data can be transferred to the Us. Topic, so that multiple robots can easily communicate with each other and transfer the message between each other. salma: Here you can see that Ross communication, where, for example, it is an example, camera can be as unknown which publishes its data on a topic. We can also have a node for processing the camera data and one node, for for example, recording the data salma: and processing note can subscribe to the camera topic and publish it and publish it's processing results on another topic. And, on the other hand, the recording note can subscribe to these topics and record all the data receives from the camera and all the processing salma: But, Ross, one has also limitations. It doesn't provide native support for real time systems or safety critical applications package developed for one. A specific cross distribution may not always be fully compatible, or work seamlessly with other bus distributions. So sometimes we need to change the whole codes and so call calls for other distributions.

salma: It was primarily written in Python 2, which has become an outdated version of the language, and also it was designed for research and development purposes rather than for deployment and security, sensitive and security sensitive environments. salma: it lacks of native support for external networking and distributed system. It was designed for single host systems and communication between Ross notes was primarily intended for local machine communication with the presence of these limitations was to emerge. salma: Ross to is a modern framework for building robot applications. It improves open plus one with enhanced performance, scalability and support for real time and safety salma: lost to promotes called reusability collaboration and inter operability, making it easier to develop advanced robot applications salma: with the distributed architecture of Ross to it's enabled it's communication across multiple machines. And it's modular, ourspartic or structure separates components into all for improved flexibility and message based communication in R to us as a published subscribe model model for data exchange. salma: With this architecture roast to provides a colorful platform for building advanced robot applications salma: here. if you can see, basically topics in lost to our transfer in this way, where we can have multiple properly share and subscriber notes. The biggest change that came with Ros to was this selection of the Dvs medal, where, for the communication layer which has a strength strength, the communication between robot components, units, decentralized public subscribe architecture, and we don't need any.

salma: Ross includes the mature open source libraries to be used for navigation control, motion planning, lesion and simulation purposes. The 3D visualization tool, like our ways, name, harvest, and the simulation tool gazebo, are seen as useful to for what developers, and also, apart from this, open CD. Libraries, libraries for detection purposes in those 2 which we have also used in our scenarios. salma: Now let's move to some of the real-world examples and some scenarios that we have regarding integrating Boston and fabric over the past 2 years we've been working on integrating fabric with us to using both co-language Golank, and more recently, with no Js. For Ross to both school and Js client libraries are community back and back as the main supported language or python and C, plus salma: So if I want to talk about our first scenario or real world example a hyper ledger fabric, the network is interface with for managing autonomous robotic fleets.

salma: and in this scenario we introduced the framework for integrate team, Ross to me the hyper ledge of fabric for distributed, or what it systems, and also analyze the act of integrating fabric and robotic systems with the performance and scalability of study and experimental proof of the proposed framework for an inventory management application with ground and area robots. salma: here, this diagram shows the salma: Hmm framework architecture and key components. The fabric network is hosted in a cloud with the Go-based Web interface for visualizing the roasting data stored in the different channels, and the command interface for including the instructions salma: fabric is hosted by a second or a set of organizations contain peers, certificate authorities to verify their membership. It more like existing of the private data channel is one of the key components differentiating fabric from other blockchain solutions. Here salma: in this framework robots are members of the fabric network and also shared Austin network. You can also see the important applications of smart contracts for industrial robots like later, it can be used to record sensor data, rosy data type or so on, and web application can be used for visualizing data, sending comments to the robots and so on.

salma: if I want to, you give a algorithm example of an application for such purpose. You can see this algorithm and other benefits of the Lt. In addition to the mutable in a digital record, as you as you know, in the building security features and identity management which can be exploits, for instance, in in interfaces for users for control in their individual. salma: Any collaborative decision making process can be implemented through a smart contract which we are basically using to ensure that all robots obtain the same result. This is applicable to all location or resource, distributed problems. salma: for the experimental part of our scenario. You can see the implementation diagram of the different software models running in different notes. Here we have use the ground robots, the AI dashboard platform and the Ui one Uav, It's 500 cartoon, 4 frame embedded with pixel, 5 x one controller running with the pixel framework.

salma: For this experiment we use 6 optic track cameras for navigation and the robots in our arena salma: robots. They're running. Ross and I take under 180 but the localization of object detection we're all running in Ros to proxy. And we have used Russ one breach to for our data from to foxy, from restaurant to salma: fabric applications. We're running on board the robots, but connect to the peers running on the separate computer in the network with the same Intel, 4, 7 processor. salma: And for the object detection we use your looks and fabric has been built up for secure data management and robot control. We have, we use 2 smart contracts, one for storing, past tracking and one for storing the location of the detective objects in the asset, and for each robot one application with different functions for controlling the assets has been used. salma: and we have used a series of shells set up in the room of 40 m², containing different objects from the cocoa data sets categories. salma: And for this, for this scenario, we have checked and analyze the Cp. One memory usage during the experiments, and to see if using an integrating topic in our system would affect the system or not.

salma: and we have also checked the yours and The the CPU usage is in blue, and memories in ping. So, as you can see, having fabric for secure data, sharing is negligible. And so the proposed framework can be adopted in a wide variety of what these platforms. salma: and we have also measured the salma: latency of the data storing in the blockchain. When the application notes is running in the robots connected to the computers running in the order and the peers not via Wi-fi. And here you can see the distribution of the latency of the name for settings. salma: the data from 15 s. It's accumulated. And over 200 hertz of Ross to data being pushed into the smart contract. We were trying to try this with different cash amount and maximum message to see the difference latencies. Also salma: as a second scenario. you can see here the blockchain is used for high level mission commands, predefined robot past for triggering multiple of cooperative actions based on chain recorded robot states like docking and landing the zoom and switching operation modes for active and deactivating the ultra wide band. Bacon detect that. Objects are also stored in the blockchain salma: with the ultraviolet. And I need to give an introduction about that. Also. What is it? Ultra-wide by technology? merged as a robust new solution for localization and robotics systems, especially for Gn Ss denied environments. It can provide centimeter levels of a curious C at low cost. It also has the advantage that it doesn't depend on environmental conditions, such as light, or salma: there is a dust like what would happen with the cameras and lighters. It is also more accurate than Wi-fi or blue to some less

salma: here, you can see. also, Wideband is a radio frequency technology that it's used for indoor organizations. Since these devices are more affordable than other indoor localization. Solutions like of the track camera that we use for previous scenarios salma: is attracting increasing attention. Anchors and tags or 2 types of nodes, using also wipe and localization to obtain the positions of the tabs in most on purpose scenarios. The locations of the anchors must be known. So if we salma: the coordinations of the fixed anchors and those are assumed to be normal by the system or for our calculation, and if we have enough fixed, and also the location of that coordination of them depending on the ranging methods implement implemented, the tags can be estimated, their distance from each anchor and calculate their only location using different algorithms like to us, kind of flight, which in our case is that salma: so for this scenario, we, we, we, we, we plan to. We plan the past for our telephone and dash, go to inspect a warehouse like environments, and store the information they get about the objects salma: store them in the blockchain. We we utilize the fabric, smart contract for logging historical data and collaborating collaborative decision making for salma: landing. And we also utilize virtual Wi-fi localization for following predefined trajectory. Why, the docking is smart contract triggers. The activation of the anchors in the ground. So what for more accurate relative localization by talking?

salma: the experimental platform of this scenario is consist of the commercially Tello, and maybe and salma: and ground robot. As you can see, the drone is equipped with the ultraviolet band module for localization. We also utilize the drone camera for object detections with the camera of it being available to that's so that's connected to a controller computer. salma: The ground robots. Yeah, I, Dashco is equipped with the some source and camera, and also vs, t, 2, 6, 5. Real sense camera for that. ecomotion estimation salma: for the experiments we have for ultraviolet modules with custom firmware. They have been deployed for robust localization, and also we have 5 extra provider notes which has been on the dashboard platform for more accurate docking of the telo. For this experiments, like like the previous one, we have the objects from the salma: so on the software side, the Dashco robot phones and the main driver. Localization and object detections are all running Ros to the fabric application running on board. The robots are connected to peers running on a separate computer and network salma: to forward the data we have used breach like us, one, and to obtain the camera image on the dashboard at the frequency of 30 Hertz. Even though they are forwarded to the object detectors. At 5 hertz the USB. Package has been used which is available in both melodic and foxy. So

salma: to implement the different parts of the system we have you for prop, go programming language for like whenever possible, has been used to increase the potential for integrate change between the different parts of the system. salma: we have 5 smart contracts implemented in the system, 2 for restoring each robust pass history, and 2 for storing the location, some of theected objects by each robot, and one for updating the battery of the cello and also landing decision making for both robots salma: one application containing different functions, such as creating access and read and updating and changing the assets as they use for each robot also. This figure shows the trajectories of the robots during the experiment and towards the mission ends, as it can be seen. After more than 3 min the positions converge when the telephone lands on the dash call salma: and the the bottom figures show the distribution in the time of the object detection detected by the.

salma: and we have also analyzed the memory and Cp usage by fabric and your looks, and we got the same results which a usage of fabric is negatable, and we have also analyzed the latency and this figure of the latency distribution of 5 smart contracts where we had over 200 hertz of Austin data stored in the average. salma: And if I want to show it so it' be more visualized for you. So the idea is that those salma: tello and Dash will start to explore that in place, and whenever they are exploring whenever the battery level of the cello goes beyond the threshold. Then the talking command is sent to Dashco and telo. So they both go to the landing position, and why they will survive to that position. salma: The anchors on the dashboard activates So the tele use zooms also wide panel on the dashboard to land. So we have more accurate landing. salma: so salma: this is another scenario with the same idea. But it's using the Africa smart contracts as running the role allocation to determine the corresponding role for each notes from here. we have for ultra-widebound localization of the system. We use both time of life and TV to minimize the disadvantages and the hyper ledger fabric aim to secure and data management and robot control. The implementation has 2 smart contracts. salma: one new contract to store the past history of 6 mobile and the second one that implements the rule allocation algorithm and saves the roles in the network.

salma: So the core idea for the role. Allocation is to keep that to keep the passive nodes toward the centroid of the system inside, the convex in below, and the active modes towards the outside. So the idea is that I I don't want to go inside this, but using that smart contract for all location, that's basically for this idea salma: and for the hardware it we we utilize the 6 jets. So Nano's jet zones. sorry, Jason's. we just a lot of modules and we have ultra-wide bands develop modules with custom firmware to enable time of flight, and T do A and transmission scheduling. And salma: the backbone wireless network is also implemented. And we have also use 6 of the track channels for motion capture system. We're use and one global controller with right 7 processor for robot co coordination and to run the localization algorithm salma: on the software side, digest ones are running ros melodic, you know, one at one computer to serve as a coordinator and wrong location. Also a Ross, one to us to reach is implemented before and last one for Jetson, and also for the Hypervisor public application and the role allocation algorithm is implemented in 3 different ways salma: one way it was in lost one python. Note one way it was in 2 with our. and another way was in fabric as not contract in salma: with the aim of comparing the performances. Later on, all 3 methods are implemented with the frequency of 5 hertz. And after comparing this

salma: different methods we analyze the impact of the integrating hyper Ledger smart contracts for the roll allocation also, and as a distributed and corporate decision making process. salma: Ross to go. Implementation is naturally faster than the interpreted lost one python note. However, most implementations are fast enough for meeting the frequency to find for the roller location the addition of hyper, ledger fabric interface to the baseline go implementation salma: it. It's late and see. However, it still remains fast enough to meet the 5 Hertz requirements for the system. salma: and as the last scenario that we have recently worked on. a hyper ledger fabric network region robots. With the removal operation application.

salma: the fabric network is able to transport data with low latencies in the range of hundreds of milliseconds, real time data stream can be confirmed. So hashes in the blockchain. The fabric network allows for control access management and a disability of the salma: celebration. So we proposed a fabric as bridging, they interfacing Ros to system salma: so using the fabric as a bridge. we draw the system through an event space design and parameters valuable data transport setting. And also we introduce the design implementation and evaluation of a pro pro proof of concept for near real time. Robot celebration so fabric from single to multiple systems. salma: comparing to previous experiments and scenarios. These, a experiments is toward near real turning. Really, television and control. It's more lively and computationally efficient fabric for us to breach and the ported from go to Nodejs. So Despite a go it should required the predefined bus to access. No, Js doesn't require this.

salma: and it's in general it's a more generalized up and performance to interface. salma: So this is a system, architecture, overview and illustration of the Us. To and from with blockchain interfaces. salma: The fabric network effectively acts as a data transport layer between individual lost to soft systems. A fabric network is optimized for cross-organizational data exchange and secure temper proof data, storage and sharing even driven architecture is the key feature of this paper. salma: research over to the fabric applications execute call guys from both the Ross and the salma: fabric networks. they are interfacing lost to events. Events occur whenever, for example, new message arrives

salma: or new messes are published to a given topic. This approach significantly reduces data transport latency as high network capacity salma: and as a hardware set up. We utilize For this experiment we utilize the the ji teller drawn, and also the mock up system in there, and about 8 to 9 to 5 meters for the localization. salma: So here you can see them. salma: software architecture. This system, was implemented based on the Roster Galactic framework on April 20 salma: and robot control and organizations. We're running in host. One data from Oki track Moca system camera is received with the V Rpm client and use for accurate position and attitude of the robot and the teleportation application and the basic motion controller. We're running in host to 2 fabric applications are then deployed in each cost to interface with the system.

salma: and the latency is also calculated, since automatic messages generated in one host until the matching Velocity Control message for controlling the to to go to the identifying path arise from another host, including both the physical network and the fabric network agencies which you can see is more or less around 0 point 5 salma: as a conclusion, we leverage blockchain technology for multi robot systems in various industrial applications for purpose of identity management data sharing security, monitoring and multi robot inventory management and consensus we showed that using proper ledger fabric and robotic systems provides a significant amount of built in security by salma: having a minimal impact on the utilization of the computational resources, and in overall the integration of hyper ledger fabric and rose to be powers, distributed robotic systems with enhanced capabilities and trustworthiness. salma: of course we are a team, and I haven't worked alone, and I couldn't do this without the help of my friends and colleagues. salma: and so thank you for your patience and listening. Thank you so much. Vipin Rathi: Thanks, so thanks so much. And participants can ask questions directly, or or they can write in the chat. So we have some questions on my in the chat. So first question is about Vipin Rathi: Lidar and the machine which vision can be used to complement each other. Is there any focus with the lost to R&D to march the 2 technologies.

salma: basically, I haven't worked on Lidar. And so salma: maybe I am. I cannot help you with that. But salma: we, we, I haven't worked with that, so I cannot say exactly, but I can search and I can. I can reply you later. I can ask, because some of our colleagues are specifically working on liders. And we have other colleagues working on machine machine learning and visions aside. So I can ask them. And later, answer your question. salma: is there mesh technology used for solutions? salma: No, we haven't using mass mesh technology.

salma: We haven't used for our use for our solutions. Vipin Rathi: some of you mentioned one one thing like identity management. So how you you how you are using this? with respect to blockchain. salma: So the the basic idea is that salma: all the robots that are in the system are defined before. So we know the identity of them. So they are kind of members of the network, so that other robots do not come, and via like. By some time the system salma: currently we are working on the scenario now that we have a Vice-presidentine robot. So we are more focusing on the identity management part. And we are using the ABC smart contract of the fabric which is gonna be published later. So you can see the result. But basically the idea until now was that so we all the identities were defined in the system. Vipin Rathi: and one more question on ultra wide band. So what are the use case and other use cases like what what kind of devices we can connect with this. And if you can tell us the frequency as well, that's really helpful.

salma: basically my colleague is working on also wipe and but The main users that I have used for all this experiments is only for the localization and salma: it is. The thing is most mostly we use mockup systems, but as also right there salma: more affordable and easy to use. We have. I have used them in some of my experiments to see the results also. But for the other systems they can be. I think they can be portable. They can be connected to the different robots also. But if you have any questions about ultraviolet, you can connect my colleague Paul. salma: A, specialized person for the the ultimate part Vipin Rathi: thanks and about the standards. So do you stand on this right now, or which which is a standard body for this, particularly salma: what I didn't get.

salma: Yes. salma: so is there any standard body who made all these standards? Or is it? What is it like? Is it open source? Or it? Yeah, it is open source. So we have currently, we are working with Ross to galactic. So it's easily use and open source. And it can be used for different robots, and it's easy to use. Also, we have all the package and things in our Github Repository. If you want. for salma: example, the ones that the smart contracts and applications that we have used for our scenarios are. I can send you later on in the Github, so it can be used and compatible to other robots, and you can, you can easily use them.

salma: Yeah, that will be great if you can share the Github Repository in this slide. And then later, when I send the slides, you when you are sharing that you can go on check. Vipin Rathi: Oh, David, could you check any questions for me, too. Nima Afraz: I've got. I've got a Nima Afraz: but if any comments to say so, thanks, Samuel, for for accepting invitation, and for a great presentation, you've done quite a bit of work here here, and it's Nima Afraz: and it seems that you haven't really stopped that trying to integrate the the the fabric with Ross, too. So you've actually

Nima Afraz: done some analytics work on on kind of how Nima Afraz: Hyper Ledger on the fabric would would actually work in these environments. Nima Afraz: So the Nima Afraz: and I and I particularly like the way that you've used smart contract. It seems to kind of support the event driven or or enabled the event-driven Nima Afraz: kind of nature, of of the work. So you're you're, I think, triggering these smart contracts based on the events that happen Nima Afraz: on the on the Us. To side, right? So that that's probably Nima Afraz: would save lots of resources in Nima Afraz: the smart contracts just being triggered when they are needed, rather than constantly being kind of monitoring the system right? And so the the part with the smart contracts, which is kind of the the most interesting part for us in this group Nima Afraz: kind of trying to see how people are using fabric and and chain codes, and so on.

Nima Afraz: So 1 one of them particularly was interesting to me which was the decision making contract based on the battery level. I think you can go back to that to the slide, because Nima Afraz: so some of the or small apologies are are, are essentially about writing kind of data on the ledger right? But this particular one was about actually kind of making a decision. Nima Afraz: And so, W. One thing that I that I'm a bit confused about is that so? So this is a decision making that's supposed to be taken in a distributed matter. So there should be some

Nima Afraz: essentially entities that don't trust each other right. And now they want to make this decision together without trusting each other. So can you just elaborate on that scenario like? Why wouldn't they trust each other? And what are these parties? salma: Why wouldn't they trust each other. So the thing is, we are okay. For example, here Nashville and Tel are not connected to each other. salma: You are not aware of each other's salma: condition. So a smart contract only checks the topics that is getting from the cello, which is the battery, and whenever it gets the topic that the battery is lower and a specific. It just published the topic. So the Ross so on the other side, in the dashboard salma: which the we have the small contract. Also, when it gets that topic, it's go to that task, I mean, goes to that position. So basically they they do not. Both of them are from parts of the network, but they are not aware of each other. salma: They just get like, publish and subscribe. They just subscribe to topics and publish, and the they just communicate. I don't know if I get your question by it or not. Yeah, yeah, no, no. So yeah, maybe maybe I'm I. I misunderstood the the point here. So

Nima Afraz: So what you're saying is that Nima Afraz: there is a server server and and kind of note relationship here. So the the idea here is not get achieving trust using the smart contract. It's more about. salma: yeah. Trust side is for trusting the robots. Because, you know, for example, we are. Our scenario was using them in the warehouse environment. If another robots try to make a false in the system, or try to. for example, get the drone for landing, or do some false in the system. salma: That's that's what we cannot see any topic, because those topics are going through the blockchain. So it's not available outside that. So only these 2 can can communicate and can see the topics.

salma: Another thing which which which which we are currently using also is that there is another thing like beside what's in S. Ross has been developed recently, which is secure. R, 2 With that case, if we implemented that also each. the each robot would have some cheese, and with those keys salma: no, no, nothing out of those robots would see those topics. So basically, it's like that. But we have, we, we are using it. Currently, we are trying to use the Srus to with the aviation smart contract this time for this identity and trust things. But basically, okay. So now, so Nima Afraz: if you want to talk about the kind of the the setup of fabric that you have. Right? So do you have multiple organizations? Do you have like Nima Afraz: so because these so these are our contracts are essentially probably you don't need a Nima Afraz: very complicated endorsement policy for them, right? So Nima Afraz: to to to everyone in the network have to endorse these spot contracts, or salma: only the robots which are which are which are going to involve in this. So nothing else, this smart only, and by this robust. So no, no one else. I mean you can. If you're in a system, you can see the topics, but you don't need to endorse the smart contract

Nima Afraz: right? So I can. Nima Afraz: I can see, like in in more sophisticated scenarios, like, let's say in a factory of future sorry over you might have. let's say. Nima Afraz: machines from different Nima Afraz: let's say, sections of the factory trying to work together. So so maybe in those cases you might, you might need Nima Afraz: and kind of smart contracts that are. they're essentially gonna bring in more more of that. Nima Afraz: the collaborative decision making a kind of side of things to the smart contract.

Nima Afraz: Because then then you have the problem with trust. Right? So because now you have external sources Nima Afraz: of of of trust. And and how do you. How do you trust people coming in and out? I know that you're you're planning to use our contracts for identity management as well. But what I'm what I'm talking about here is more or more from the view of more complicated decisions that have to be taken. And more people have to give an input. So here, your input comes directly from the drone. And the drone makes a decision based on its battery level. Nima Afraz: And okay, okay, yeah, yeah. So there's there's quite a bit of things to be to be done here in in more complicated scenarios. salma: Yeah, of course, I mean, we are just trying starting this. I I'm I'm I I I I I I just started working on fabric from my Phd, I mean, it's been one year and a half. So I'm just trying to. Yeah, integrate. I I was not specializing. Yeah. Yeah. And and then one last question. So if you go to the

Nima Afraz: and latency Nima Afraz: figures that you had but actually like both latency and and CPU utilization. So what is the transaction to put here? What numbers are you looking at the the the the the the thing is, we had another on a leases also, but I didn't put because the slides were too much salma: for checking the throughputs to see that is changing. having different through puts. Hmm would affect this or not. We had some test tests with different dash, time out and maximum message salma: that's beside that we got the frequency of I mean, with the frequency of around 50 hertz was the thing that we got the optimal one. But we had some stress test to check the different frequencies and different utilization. But I don't put it here.

salma: So with that optimal frequency that we got, we got this minimum resources. Utilization. Nima Afraz: Yeah. But sometimes that's really out of your control, right? Because transactions Nima Afraz: that come through your your your, your, your, your fabric Nima Afraz: will depend on the number of drones you have. so I I assume these are all scenarios with one drone and one dash right? Not only for our case. I mean, it's not yeah. So I mean, obviously, for this case, this is a good analysis. But I wonder if this would still

Nima Afraz: apply. If you have, let's say 100 machines that are quiet latency sensitive. So you want to process their transactions very, very quickly. And so, yeah, what I'm saying is that this might not be very generalizable. because, like I I did lots of Nima Afraz: kind of these kind of Nima Afraz: analysis on on better if Nima Afraz: my fabric. That fork is going to kind of be able to meet the the, the latency requirement that I have in my used cases, which is telecom, use cases, and they're very late as it's sensitive, and once you reach them a couple of 100 transactions Nima Afraz: per second. It things start to to kind of

salma: change quite rapidly with the with the latency and CPU usage as well. Yeah. Also, when after recently, because with our new scenario that we are using the one problem is that as it is accumulating the data after, if if we leave the data to be transferred as it is salma: sometimes the latency increases, even even though it needs, for example, after 3 min or 4 min after to accumulating the message, it starts to. salma: yeah. And there's also. So one thing is actually like just writing things on the blocks. And the other thing is that if you have, like a Nima Afraz: kind of a more sophisticated.

Nima Afraz: a smart contract that are making a decision based on particular algorithm. Then if you have to wait for all the notes to endorse your your your smart contracts outcome, then you end up sometimes Nima Afraz: waiting for quite a while to for everyone to Nima Afraz: a smart contract, and so on. So yeah, yeah, like, lots of space for you to to work on if if you want to continue working with type of ledger. So of course, there are lots of parameters that we have to take into account, and if you want to, if we want to generalize it. Of course we have to use more than 2 robots. We have to take into account both of things. Of course you're right Nima Afraz: perfect. Thank you very much. Vipin Rathi: Anyone else. Any questions.

Vipin Rathi: I have a question. Bret Michael Carpenter: So very wonderful presentation. Thank you so much for your time. My question is, are you able to bring the electromagnetic computation Bret Michael Carpenter: into fabric? salma: I salma: for now I have to search for that because I don't know if I can. Bret Michael Carpenter: I I don't know. I have to. What's the frequent like the frequencies. Are you able to bring, like the Rf. And all of these things into fabric.

salma: Yeah, that's why I'm saying salma: I mean, like checking them or anything. I mean, it's I mean, you're on the you're on the cutting edge. So I'm just wondering if you were able to bring electromagnetic computation into fabric. salma: actually, we haven't tried. No, so I can. I cannot give you another. I I we haven't tried. So maybe if you try it, I can give you the Vipin Rathi: anyone else any questions. Vipin Rathi: if not So thank you. Thank you so much for accepting our invitation. And this very good presentation. And

Vipin Rathi: thank you. Everyone for joining today. And Vipin Rathi: thank you so much. Thanks. Everyone Nima Afraz: thanks everyone. Bye, bye. Vipin Rathi: right.

2023-07-04 19:40

Show Video

Other news