“If we can simulate 70% of a system before it ever hits the factory floor, that reduces time and cost for automation deployment.”

Advances in machine vision, AI-enabled software, and simulation technologies continue to reshape the way companies in manufacturing and warehousing design, deploy, and benefit from automation systems. In this episode of the Manufacturing Matters podcast, TECH B2B Marketing’s Jimmy Carroll is joined by Jim Anderson, senior business development manager for 2D and 3D vision systems at SICK, to explore where these technologies are headed next.

Anderson explains how emerging tools such as synthetic data, digital twins, and virtual sensors help companies test automation strategies in simulated environments before implementing them in the real world. The discussion also covers practical AI applications while examining how advanced machine vision technologies are enabling safer, smarter automation on factory and warehouse floors.

The conversation also hits on the future of lights-out warehousing, the growing importance of AMRs, and workforce challenges driving increased automation adoption. As experienced workers retire and U.S. reshoring accelerates, automation technologies that improve flexibility, safety, and ease of use will play a crucial role in the future of manufacturing.

Jimmy Carroll: [00:00:06] Hi everybody. My name is Jimmy Carroll. I’m the vice president of operations at Tech B2B Marketing. And welcome to this episode of the Manufacturing Matters podcast, where I have the pleasure of being joined by Jim Anderson, who is a senior business development manager for 2D and 3D vision systems at SICK. Jim, thanks so much for taking the time. I know you’ve been very busy and you’re in between some meetings here, so I very much appreciate it

Jim Anderson: [00:00:27] Good morning. Thank you for having me.

Jimmy Carroll: [00:00:28] Yeah, absolutely. My pleasure. Jimmy Carroll: So I’d like to start off by asking: What’s most exciting to you right now in the world of machine vision?

Jim Anderson: [00:00:35] Well, it’s a pretty big question. But I think overall for us at SICK is learning how we can start to work with some of these new ideas of synthetic data and how we can use that to start to manage AI in the 3D space. And that’s some of the things that we’re really excited about. We’ve been implementing a lot of deep learning and AI tools on the 2D images and now trying to figure out ways that we can make that more efficient on the 3D side.

Jimmy Carroll: [00:01:05] Yeah. So I’ve been following SICK for a while, and I don’t know much about this idea of virtual sensors. I believe it’s used in the Omniverse platform. Nvidia’s Omniverse. Can you tell me a little bit more about this? This really sounds very interesting, very exciting.

Jim Anderson: [00:01:22] Well, the idea of virtual sensors, the ability to try to kind of build and use your technology that you have in real space and be able to mimc and plan that in a virtual space, not only for machine vision but in our robot guidance tools and all that kind of thing. The idea of the Omniverse or virtual twins or industrial twins like that, we see a huge push and being able to use that because I think it reduces the time and the cost for people to be able to test things and get fairly good results. I don’t think that we’re 1/1 ratio yet of being able to do things in the Omniverse or in virtual space, but it does give us the ability to do things and get 70% down the path and say, yes, this looks like a real viable solution. Let’s go ahead and start putting boots on the ground to make this happen.

Jimmy Carroll: [00:02:22] Yeah. And you touched on it a little bit, but what other opportunities does it create? And I guess maybe not just opportunities, but for some folks maybe looking to adopt automation or expand automation, expand an existing footprint or whatever, does it lower the barrier of entry? Does it make things a little easier for the person who’s signing that check to say, “Hey, this looks good. Let’s do this now”?

Jim Anderson: [00:02:44] I think that it’s starting to get the buy-in from users on that level. I think that the people that have been already using a lot of virtual space or looking at ways to simulate items before they would buy, I think that’s increasing the speed at which they’re willing to do it. I think that they can lower the bar for new entries into the market, but I think that is one of the bars still for those people that haven’t already accepted it. It’s like, “Oh, how can I know that this is real?” And so I think that having a number of real use cases and being able to show how that resulted in, step-by-step, money savings for somebody else or how it increased the speed at which they were able to implement something, because that’s usually one of the biggest things for new people joining the market, I find, is that they’re either just nibbling at the edges or they think, “We’re behind,” and they want to take a big bite, and then when they take a big bite, they kind of start to choke a little bit.

Jim Anderson: [00:03:44] And that’s a problem that we need to . . . I think that this can kind of help break that into smaller pieces. So I don’t know if I answered the question, but in reality, I think it is in itself one of the tools that can help. But it is one of the things that for people that aren’t already involved in the market like this, it is still a little bit of a barrier because they want to see more and more real-world data. And so using that as a part of the selling process and then getting to a real-world concept for somebody and then showing that what we modeled worked. And then the next time we do the model I think can help them move faster. But on the first implementation, I don’t think that is a huge time savings because people still want to see real action. But the second time through, I think it does speed up the process quite a bit.

Jimmy Carroll: [00:04:39] Well, you did definitely answer the question. Yeah, I appreciate it. And it’s very interesting, because the whole idea of digital twins and simulation, it seems to be advancing things quickly, and it’s interesting to follow. And some of these developments, like I said, are things that I wasn’t aware of yet the concept of a digital sensor, like in the Omniverse platform. And there’s been a lot of really cool stuff in Omniverse. Anyway, I’m geeking out about it, but like I said, I’ve followed SICK for a long time. Before I was at Tech B2B Marketing, I worked for a machine vision magazine, so I’ve been familiar with your technologies for a long time. But you guys, you’re doing things like 2D and 3D and AI and obviously all the laser sensors and much more than that. But you’re kind of at the forefront of a lot of these, let’s call them hot-topic technologies, like AI. And one of the things I noticed too is that you recently won an award for an AI-driven assistant from Microsoft. So that’s a very interesting one too. Tell me a little bit about that.

Jim Anderson: [00:05:42] I’m not as familiar with what we did on that. I think that had a lot more to do with some of our safety products and some of that. So I wasn’t involved in that project. So I don’t have a whole lot of information to be able to share about that, other than there seemed to be a whole lot of people that were pretty excited about Microsoft thinking that we were doing the right thing, and working with a partner like that does open a lot of doors outside of the traditional marketplaces.

Jimmy Carroll: [00:06:12] Yeah. Fair enough. Well a question that I’m pretty sure that you would be familiar with is, when you’re talking to customers and you’re working on existing projects or new projects, how are your customers today going about AI adoption and what ways are you seeing AI add value in different ways on the factory floor?

Jim Anderson: [00:06:31] Now that’s a good one. So there’s just a lot, starting with applications seemingly as simple as counting chickens. We have an application where we’re looking at how, as chickens go through the process of going from a live bird to food for us, there are different shapes and sizes these birds take, and so they become very difficult to map and track using traditional tools. And one of the things that we did was we created a flow model based on a lot of the applications that we had already done in our work in the logistics market. So SICK has done tons and tons of AI-based solutions for package identification, package segmentation, so that you can make sure that you’re placing the right barcode and the right information onto the correct package when they come through in a jumbled mess. And so one of the techniques that we kind of expanded on, looking at more organic forms, was taking that tool and then we weren’t having to spend hours and days and months of additional data. We only needed about seven hours of total collection to get enough data to be able to totally map how chickens moved after they would come out of a wash and come down a ramp and be either 1 to 12, they could be touching, overlapping, and be able to count them with almost 100% accuracy. It’s those types of applications, in the logistics space, it’s huge for us. And the segmentation, also logistics and robotics and being able to do segmentation, finding packages on pallets, and being able to stack and depalletize and palletize product. Pallets for a long time for me seemed like the most common use tool in logistics, and nobody talked about it.

Jim Anderson: [00:08:48] We had one customer starting to say that as they were moving in more and more to automated AGVs and those kind of things, that they weren’t having the human interaction with the pallets. And so when there was a defect on a pallet, not just on the load itself but the actual wood, they were having issues in their ASRS systems. And so we came up with a solution, again using AI to do segmentation, finding boards, checking to see if the pallets were in good shape before they would go into these systems. And since that point, I don’t think I’ve had a day where I haven’t had to talk about pallets. And it seems like the most ubiquitous form of movement of any product. And once we started saying, “Do you have problems with this?” Everybody was like, “Yes. Do you have a way to fix this?” And so that’s been a really cool opportunity for what seemed to be the most boring kind of item. But then when you can fix the low-level, boring things, then you get access to a lot of other fun areas within companies. And that’s kind of when you can show that you can handle their basic needs. You get access to a lot of other fun applications, and that’s been exciting.

Jimmy Carroll: [00:10:04] Yeah. I’m glad you brought up warehouse too, because I wanted to ask about this, and we talked about it a little bit yesterday on some panel discussions that we had, and we talked about both the idea of lights-out manufacturing but also lights-out warehousing. And some of the folks I talked to said, well, I think we’re closer on lights-out manufacturing, a little farther out on lights-out warehousing, but they weren’t totally sold on the idea of complete lights-out warehousing in the sense that you’re always going to need to have at least a person in the loop, whether it’s to make sure that the truck backs up correctly to the dock or whatever. But what are your thoughts on lights-out warehousing? How close are we and what technological advancements would we need to see to get there?

Jim Anderson: [00:10:48] Wow. For me, some of the plants and locations for warehousing seem like we’re a lot closer. Because there’s so much more variety in how things get done in manufacturing, I think that the adaptability of people and all that kind of thing always is going to make that a better use case. And so I think that going complete lights-out in manufacturing actually is a little bit harder than warehousing overall. Some of the tools that we use: human in the loop, reducing people in jobs that are traditionally pretty dull, dingy, dangerous, and warehousing can be some of those. I’ve been at plants and been near toppling bottles of soda and glass and everything. And that is scary and dangerous. I’ve seen loads fall off racking systems when people are trying to pick it, a pallet or board gets stuck. And when they try to pull something off, the whole load will dump onto an AGV or onto a person. I think that the safety portions of working in the manufacturing space or into the warehousing space, I don’t think that they’re that much different in their timeline for actual lights-out. I think that sometimes that hearing both of those kind of things scares a lot of people.

Jim Anderson: [00:12:20] It’s like, where do all those jobs go? But from all the places I’ve been, it’s moving people into different locations. I don’t see it as a net loss at any one of the warehouses or manufacturing plants that we’ve implemented larger solutions. So the technological way of getting close to doing it I think is there. There are some costs that are probably still more advantageous to continue to do it with people than going complete lights-out. But I think that those things are shifting pretty quickly. And the cost over time, I think the upfront costs are what kind of hit people. And so when do they want to make that investment and when are they willing to do that. But technology-wise, we have a product called the Visionary-B Two with AI assist, and it’s a not a safety-rated product, but because right now there is no safety evaluation process that meets the standard. You know, there’s no AI included in the safety standards at this point, but it is something that is being discussed and is starting to be worked on. But basically it can identify the difference between a person moving or a person walking, a person and any other object.

Jim Anderson: [00:13:48] And it gives us a lot of ways to do safety projects in a different way, not just looking at: Is there something there, but is it a person? And do I have to make the same safety corrections in a warehouse or in a manufacturing facility if it’s an AGV moving through a zone, pulling a tug, or it’s a person driving? Those two devices might be able to talk to each other. There might be other pieces of information that can be shared. So that safety situation that used to be something like, okay, this robot needs to shut down or move at a slower pace while this object moves through. But if they’re both moving autonomously and there’s some level of network communication between them, maybe there doesn’t. It’s kind of the idea of the robot taxis or whatever as we get more and more of those devices on the road and only those devices on the road, not a human interaction, now you have a way that these things can be talking. It can be moving at a more consolidated motion, and it can probably improve a lot of traffic and might improve the throughput at warehouses where the footprint might not need to be as big as it has been in recent years.

Winn Hardin: [00:15:07] Everybody, I just want to take a quick second to thank our sponsor. Manufacturing matters is sponsored by tech B2B marketing. They’re a full service public relations and marketing agency that focuses on technology companies, especially in the energy and automation markets. They provide full service media relations, investor relations, employee relations, full end to end content development, video services, animation, full IT stack development from website, integrating with ERP systems, CRM marketing automation systems. And they bring a whole lot of knowledge and experience about technical markets since they’ve been servicing those markets for over 30 years. So if you have any questions you want to learn more, go to tech b2b.com. And now let’s get back to the show.

Jimmy Carroll: [00:15:48] True. Yeah. Less infrastructure needed. And you’re absolutely right. Obviously the safety issue is something that’s being talked about. In fact, this morning we had two different CEOs from two different companies come over and talk to us. And their companies both do safety in the warehouse and on the manufacturing floor, specifically about what you’re talking about. And that’s very interesting. And I think you’re right. Like in talking to other people, they seem to think that lights-out is mostly attainable. But maybe all that means is one person gets real-time notifications to say, all right, move this robot this way. But to your other point, and somebody else brought this up too, once these devices can start communicating with each other and there’s interoperability and some sort of standard there, then who knows.

Jim Anderson: [00:16:36] Right. And you don’t want the Skynet kind of situation. But as machines and people have the ability to communicate their information more seamlessly using AI infrastructure to be able to ask and have things be planned ahead and what to do in different situations, so it’s not just ladder logic. Planning — you can have a web or spread of different options. And if this happens, these are the workarounds to make. Those types of things are happening in real time right now, and the move towards lights-out — I don’t want to say that’s the old term, but I think that’s what the goal was — I think now it’s trying to figure out how to make it so that we don’t have to have people constantly making decisions to do certain things. People can be doing what they’re good at, like planning ahead and being creative about what the next piece of information or solution is, as opposed to trying to just move boxes.

Jimmy Carroll: [00:17:46] Or helping to control the robot fleet or overseeing it or being technicians on it. And you brought up the idea of people losing jobs, and for several years in the past five, six-ish years, there have been periods of time where there are more open jobs than there are unemployed people. And you can’t fill those jobs anyway in a lot of cases. People don’t want them. And if you’re in the warehouse and you’re having to lift 50-pound boxes all day up over your head or carry them around or whatever, then they’re hard to fill as it is.

Jim Anderson: [00:18:19] Jim Anderson: And we’ve had these discussions with different people at the Business Forum that we’re at here. There was Beaulieu and his economic speeches and that kind of talk about where we are with our population and not just in the U.S. but globally, where there’s a large number of people in the old Gen X to low baby boomer that are going to be leaving the marketplace, and we don’t have the people to replace them. And we’re already short people. And so the idea of being able to do what we want to do is going to require more efficient tools. And the fact that there’s less people doing the jobs is, well, in some ways we will have less people actively trying to do those jobs, so it’s not really that we’re losing the jobs to a machine, but we need to have those things done. Otherwise a lot of other parts of our economy start to get a little shaky.

Jimmy Carroll: [00:19:25] Jimmy Carroll: Yeah, maybe it’s a bit of an old stat now, or maybe an old sentiment not stat, but there’s a genuine fear that welders, for example, are sort of aging out and people aren’t going to these jobs even though they’re good jobs and they should be going to these jobs.

Jim Anderson: [00:19:44] Hard to be a welder influencer right now.

Jim Anderson: [00:19:47] I mean.

Jimmy Carroll: [00:19:47] Right.

Jimmy Carroll: [00:19:48] And those are jobs that automation technology systems have proven to be successful at. Not only that, there’s been a lot of investments in production facilities and manufacturing production facilities in the U.S. lately. So as part of U.S. reshoring efforts, automation technology is going to be crucial for that obviously.

Jim Anderson: [00:20:12] We’re excited about that at SICK. We definitely can say that. We have a lot of pieces that go into all the different areas, and that’s exciting for us and exciting for a lot of the customers that we support. But yeah, there is this shift that’s happening where we have to do these jobs. We don’t have people that are trained to do them, a lower and lower number of people that are trained to do those jobs, and it’s hard to make that seem sexy. I think that one of the things that we’re trying to do is, through some of the talks like this and a lot of other podcasts and webcasts that are out there, trying to talk about how manufacturing is kind of a requirement. We can’t consume things unless they’re made. And so we have to figure out a way to make that part of the process too, because I think it’s not just about: Is it fun? It can be monetarily rewarding. There’s a lot of other ways that we can make those types of jobs feel good to a new generation of students. And one of the ways that talks like this really can help is that people can see that, yes, these are needed. And it can be a niche. I’ve seen a couple of new companies start up that have taken on the goal of training and building in almost like their own welder’s union. They kind of go out and they become like a local resource. And this has been very monetarily rewarding for those groups.

Jimmy Carroll: [00:21:55] Yeah. Yeah, absolutely. SICK is a great company to ask a question like this. I wanted to ask about AMRs, but that might veer off a little bit outside of your purview, but the question is kind of still the same. For example, the development of these digital sensors or 3D or new AI-enabled tools that you guys are developing. But the original question was going to be: AMRs are obviously becoming increasingly important in factories and warehouses today as well. And I know that there’s a lot of SICK sensors in AMRs these days. And how have you guys had to adapt to changing environments and increased needs there? But that question goes beyond AMRs too. It’s for AI, it’s for 3D, it’s for vision, it’s for barcode reading.

Jim Anderson: [00:22:51] Well, going along the lines of what we just talked about with where people are putting their efforts in their training and what they have available at their facilities, I think that some of the functions that a company like SICK can provide with more of a dynamic system integrator, partnered approach, where we can go in and we can work with the AMR builder or an AGV builder, get our safety equipment on there, help do the mapping, do things at the warehouse, and make the complete risk assessment. And safety becomes a huge part of it. Beyond safety, you start to add in, we have these tools, like I mentioned, with the device called the Visionary-B Two, where it can differentiate people and objects. Like, do you have different sets of things that happen when an AMR passes through a zone or a person passes through a zone? What happens if a person is standing, so we can start to make more and smarter decisions because we have different types of data that wasn’t available. And then by having all that data, we can then start to map that back into the virtual twin.

Jim Anderson: [00:24:24] And having this ability to build this warehouse and run scenarios in a virtual space that make it so that the user becomes comfortable. And then when you show that it is implemented in real life and it works the same as it did in the model, then you start to get that buy-in that the data not only is important for them to be able to do the analytics and things that they want, but the data that we provide on the lower-end system side is important to us to be able to help them make their processes more efficient. And that is a new way of selling and talking to customers. But SICK has been trying to do that for a number of years, and we’re really starting to see a lot of traction and not just in vision. But like you mentioned, we have photoelectric sensors that have some level of AI or an FPGA that’s running inspections and can be reprogrammed on the fly to do the next inspection and to talk to its partner sensor to be able to calculate a speed or do something like that that you would have to do a lot of other work in the past. And that becomes very simple.

Jim Anderson: [00:25:32] But now you’re becoming more and more reliant on each individual product. And so it’s important to have feedback from those sensors and being able to do that to make sure that everything is working properly and not just that, okay, if it’s not working, we’re going to bypass it. No, that data now becomes inherently more important. And not just for the manufacturing process to make sure the parts are good but also to make sure that the safety of the system is right and that on the analytics side for the company that they can kind of see and manage and be prepared: Okay, this is when we’re going to have to do downtime. This is when we’re going to have to order the next batch of whatever raw materials. If we’re monitoring something with a distance measurement sensor in a bin, trying to make sure that when this gets to a certain level, just like normal loop control stuff that we’ve been doing for years and years and years, but now we might have not just a sensor that’s doing that, but when the sensor gets to a certain level, we’re taking a picture or documenting it, making sure that every step along the way becomes a more repeatable and a better process.

Jimmy Carroll: [00:26:35] Yeah. That’s a really good answer. And of course we work in a marketing agency and perhaps we’re somewhat guilty of this as well, but a term you hear a lot in automation today is “flexibility.” Systems are expected to be more flexible and less rigid than they were in the past. And you really kind of just nailed that — these sensors’ abilities to adapt and be repositioned or repurposed.

Jim Anderson: [00:27:04] And I think that’s hugely important. But it also does make things a little bit more complicated. I used to always joke, machine vision side, somebody would come to me and say, “Can you do this?” And I’d say, “Maybe.” Now the answer is, “Probably. It’s just a matter of how much time do we get? How much money do you want to put into this?” And now it’s like, “I want this machine to be more flexible.” Okay, how much flexibility do you need to add into this? Is it because you’re going to do apples and pears or is it because you’re going to build carburetors and then have some type of food product? What do we have to do here? And so looking at other things, not just the interoperability between things, but like, what is the different expectation for a flexible machine to go into different markets where now the cleaning process is completely different. So those things start to add up. So a flexible machine within a group is one thing, but having the flexibility to take the same type of machine across industries, especially AMRs and those types of things, it’s becoming important to make sure that it’s not just like the automotive standards that are driving something. It’s the food and beverage and automotive, and it’s where do those intersect and how can we make the standards also more similar so that we can say that we are working across those industries, and being more flexible becomes a little bit easier.

Jimmy Carroll: [00:28:49] To your point, I wanted to jump in and say, well, if you want flexibility in the warehouse, what does that mean? You want to be able to handle hundreds of thousands of SKUs or, like you say, an apple or a pear? How flexible do you want it? That’s a good point. And I don’t think about it from the vendor side of things. It’s like, yeah, we can make it flexible, but it’s going to be potentially more complicated on our end. But the idea is then once it gets to the end user, then it’s ready to go. It’s easier to use.

Jim Anderson: [00:29:22] And then it becomes maybe a little bit easier on our sales force. If we have one flexible machine, he’s got to learn the one machine, and then we can become experts on one thing and be able to support it. But right now we have very specific sensors that work in these areas and these areas, so having the right sales force and support staff and all that kind of stuff becomes more difficult when you try to work across multiple industries.

Jimmy Carroll: [00:29:52] On that topic of ease of use — and that’s another one that comes up a lot and for obvious reasons — you guys have a wide variety of technologies and you’ve been in this space a long time. And you’ve seen this trend over the years where we kind of talked about it earlier. It’s like you might have people that need to be able to use your technology that aren’t engineers or integrators. What are some ways that you’ve made machine vision technology a little bit more accessible to maybe a factory floor-type worker?

Jim Anderson: [00:30:25] Yeah. So specifically on the machine vision side, one of the things that we’ve done is we’ve really rolled out a new complete engineering package on our back end that allows us to have the same user interface across all of our machine vision products, 2D, 3D, and even starting to roll into our robot guidance solutions. And we call that Nova. It’s based on our app space platform, which allows us to get into the nuts and bolts and low-level stuff on all the products. But at the user level, it is a web-based solution. No software to install. Makes it so that there’s no PC. There’s no other items for the end user to have to maintain. They can program and get a working solution without having to install anything on a laptop. If they have it on a wireless network or if they have access to that same network wirelessly, they can interface with that via a tablet or a phone, make adjustments. And also from there, we can work with them to build specific user dashboards so that they can track the pieces of information that they’re working on. So those are the things that we’re really trying to do: to make the user interface across all our platforms the same and then also being able to increase the data available on a dashboard so that it’s meaningful at the user level. So if there’s a screen or something that they can see what the throughput is; not just that there was a defect but what the last defect was so that they can start to make better choices if there are things that can be impacted upstream.

Jimmy Carroll: [00:32:04] Jimmy Carroll: Just to have that peace of mind, like real-time insights or notifications if you need to make some sort of change or just to know that everything looks good. Jim, what else haven’t we talked about that you guys are so excited about these days or you are personally excited about?

Jim Anderson: [00:32:21] Well, like I mentioned, the idea of synthetic data. In my mind, it’s very interesting. And it’s sometimes a little bit odd how much improvement that actually makes in a system when the new images might not have anything to do with what the application looks like. But we learn to build in the exceptions that are sometimes very hard to find. In a good manufacturing facility, the goal is not to have errors or bad products. And so to have enough of those and the variety of them to make your AI model as robust as you’d like is sometimes hard. And so you’re starting out and you’re constantly trying to build and add. With the idea of synthetic data, and especially what’s interesting for the synthetic data for me, on the 3D side, is that for a lot of customers, getting more images on the 2D side is not so hard. They can figure out: I can take a picture with my cell phone. There’s different things I can do to gather 2D data, and even if it’s not exactly what I need it to be for, I can use that to improve my model to some level.

Jim Anderson: [00:33:41] With 3D, you need to have the right camera to start. And so if a customer doesn’t have that data or if you’re loaning a camera to somebody to capture the information that they think they’re going to need, are you there at the right time when the defects happen or can they run a product through that is defective on purpose? And so now you’re kind of impacting their production flow and that kind of thing. Is there a way to get around that? And I think that there is with the synthetic data. And I think what’s really exciting for us is that you can go in and you can capture some of the data, take that, and then start to build that out with these synthetic data models. And we’re working on our own and working with some partners to really push that forward, because I think that’s going to make the 3D adoption just a lot faster. It’s been very good for us over the years, but now the number of people that can access it and work in the model teaching as opposed to the rules-based and full-on code for 3D, this continues to expand the marketplace for 3D usage.

Jimmy Carroll: [00:34:50] Jimmy Carroll: That’s really interesting. We’ve talked about a lot of really cutting-edge — well, in a lot of ways they’re not cutting edge; these technologies have been around for a long time. But everyone keeps pushing the envelope forward, SICK included of course, you guys with your wide portfolio. And we’ve covered a lot of really cool technologies that I’m personally interested in. And for anybody out there that is trying to follow the latest trends in machine vision and AI and sensors in general, I would encourage you all to check out SICK at Sick.com and on LinkedIn obviously.

Jim Anderson: [00:35:21] And then one last thing. We’re opening up our new global office in the Twin Cities right outside the airport, one stop on the light rail. Big customer center with demos and practical use cases to come in and see. We’ve moved from our West Bloomington, Minnesota, location to a combined campus with manufacturing, where we have AMRs and all that kind of stuff as part of our solutions, and our warehousing. And then we have all of our marketing and product management and demonstrations of our technology in our new customer-facing center attached via skyway to each other, parking ramp, one stop off the light rail. Please come. You know, reach out to me and we’ll set up a visit. We can show you all the new things that we’re doing in our new facility too.

Jimmy Carroll: [00:36:14] Yeah, absolutely. It sounds exciting, and I’d love to see it someday myself. If anybody has any questions for Jim, I’d be happy to pass them along. You can reach out to us at manufacturing.matters.com. And thanks so much for joining. I really appreciate it..

Jim Anderson: [00:36:27] Thank you.