The Israeli start-up INTSITE seeks to continue the innovation revolution in advanced driver assistance systems, started by companies such as Mobilai and Invis, and to bring the introduction of heavy mechanical-engineering equipment, with an emphasis on construction sites and mines.
The company was founded in early 2018 by the twin brothers Tzach and Moore Ram-On (36), the first a civil engineer and the second an aeronautical engineer who previously worked at Rafael. The ADAS systems developed by the company (Advanced Driver Assistance Systems) are based on image processing using artificial intelligence (AI) to analyze real-time camera data for heavy mechanical engineering equipment, ie excavators, bulldozers and various trucks.
To date, INTSITE has raised $ 2 million in a Seed round, and recently closed a similar round. Unlike companies that embark on very large rounds of fundraising, INTSITE has so far remained under the radar of capital raising thanks to a creative business model, which allows it to generate positive cash flow and thus not rely on large-scale external funding.
The company recently unveiled a fruitful collaboration with the Japanese company KOMATSU, the second largest manufacturer of heavy mechanical engineering equipment in the world (after the American Caterpillar). The collaboration is reflected in five different past and present projects and in making KOMATSU the largest customer of INTSITE.
INTSITE is also currently negotiating with KOMATSU, which is traded on the Tokyo Stock Exchange at a value of $ 23 billion, to sign a commercial agreement under which INTSITE’s systems will be integrated into KOMATSU’s heavy mechanical engineering equipment.
“We work with several types of customers,” explains Tzach. “In the first phase, the work is with end customers, those who suffer from the tool’s low productivity and safety issues, such as companies in the construction, mining and infrastructure companies that use heavy tools. We communicate business with these companies through distributors, ie we work with companies that rent them The equipment, and they offer their customers the company solution, means the computer box with all the intelligence inside and the software in the cloud.
“In the second phase, the work is with the manufacturers. Today we are already working with three of the ten largest heavy tool manufacturers in the world. The idea is to sell them our computer, and that they will integrate it into the tool production line.
There are several JVs today, consisting of the manufacturer, the communication platform and the hardware provider, for example the companies Siemens and Bush. This body chooses to implement within the autonomous platform solutions from different providers: information security provider, lidar provider, and we want to be the provider of the algorithm related to the image processing of the camera provider. The goal is to become a company that sells a license to use advanced algorithms, but at the moment our focus is on integration and growth within the construction and mining industry. “
While the company is currently advancing in real-time alerts at construction and mining sites for heavy tools, there is no doubt that there is a wide range of additional applications that can be derived from the algorithms it has developed. “Because our computer knows how to ‘talk’ to different types of cameras, and we already connect it to a camera mounted on a crane at the construction site to give top-level alerts about possible dangers, it is easy and material that the system can be installed on marine cranes. “Beyond one of the largest ports in the world. Beyond that, we are also piloting agriculture in order to show relevance in parallel markets, but there is no intention today to sell in these industries in commercial quantities – we remain focused.”
Connects to any camera
“There are two main trends in these worlds that require treatment: safety levels and very low efficiencies,” explains Tzach. “Although these industries make up only about 10% of the global workforce, their contribution to the death toll is more than 50%. This causes workers to turn their backs on these industries, especially the younger generation who prefer to work in more advanced and technological industries.”
“Also, productivity per worker in these industries has not improved over the years contrary to the growing demand for new infrastructure and construction projects,” he adds. “In fact, according to McKinsey, every five days more than a million people move from rural to urban areas, with an emphasis on Asian countries. This creates a massive demand for infrastructure, residential buildings and the like.”
Initially, INTSITE focused on developing an artificial intelligence-based system designed to make the crane, one of the most important and dangerous tools on construction sites, autonomous. But at the same time it developed ADAS systems with the second largest company in the world for the production of heavy tools KOMATSU (after Caterpillar).
About a year ago, at the end of a strategic process, the company decided to focus exclusively on ADAS systems for heavy mechanical engineering equipment, and now this choice allows it to jump a significant step in its business development. According to INTSITE, the advantage of the system it has developed is that it connects to any analog camera, and does not require the installation of lidars and other expensive sensors that constitute a significant barrier to sale.
“Heavy tools are becoming more sophisticated and more autonomous,” explains Tzach. “In the world of autonomous vehicles, the technology is classified from stage 0 to stage 5, where 0 is the issuance of alerts and 5 is full autonomy. Operate to slow down, stop or change the steering of the tool.
“The product we provide is a ‘black box’ that contains a computer with very powerful computational capabilities from NVIDIA. This computer knows how to ‘talk’ to all kinds of cameras, and they are the only sensor we use. We do not use lidars, radars or any expensive sensor. “Another thing that gives us a significant advantage, because it significantly reduces costs for our customers, and even allows us to work with new tools that are already manufactured with cameras or with old tools on which we have already installed cameras.”
in real time
As mentioned, the company takes advantage of the fact that soon half of the new and existing heavy tools already have cameras installed to which the computer it has developed can connect. The “black box” on the other hand connects to the operator’s screen, and through it visual and audible alerts are given. In addition, there is a mobile module that uploads the data to the cloud for control and monitoring of decision makers. The software and algorithms flood value in several main channels, including safety, efficiency, preventive maintenance and reduction of fuel consumption (thus also contributing to the environment).
“In terms of safety, the software provides real-time alerts to the driver and those in the vicinity of the vehicle,” notes Tzach. “The software has more than 30 different algorithms that provide alerts in a variety of situations, such as whether the tool is about to overturn or run over someone, and these are things that unfortunately happen in the field.
“Beyond that, we streamline the work process by providing simple and intuitive explanations to the operator of the tool while performing the work. Efficiency in work also leads to energy efficiency and reduced fuel consumption. These are tools that consume hundreds and thousands of liters of fuel per day.
“The last issue is preventative maintenance. By using video only we know how to detect, predict and alert before malfunctions develop that disable the tools. We do all these things in real time, and again, using only cameras.”
The company offers several services in one product and also knows how to provide detailed reports to the webmasters thanks to the connectivity of the computer in question to the cloud. “Processing is performed on the computer in a tool but also in the cloud,” Tzach emphasizes. “All issues that require real-time alerts, such as safety hazards and damage to production capacity, we provide in real time regardless of cellular reception, and anything that does not require immediate reporting is processed in the cloud and of course reflected to management. The product meets all relevant standards in information security and privacy Very, because collecting information from cameras is very sensitive, especially in Europe.
Data collections
The company has two patents: image processing and artificial intelligence. The image processing capability allows the computer to identify and track objects. Also, through artificial intelligence the software teaches itself to develop relationships, gets better and becomes better and more efficient. Tzach emphasizes: “The basis for everything we do is the data, that is, all material photographed from the relevant areas in which we operate.
“This is something that has been strategic for me and the company from day one. We have installed cameras for free at various sites around the world, so we can collect the data and develop the algorithm. It will happen and when not, and once it is accurate enough in terms of percentage accuracy, it can be released to customers. “
“Image processing technology also has a limitation,” he notes. “In extreme weather conditions, like snow or heavy fog, there is a chance that the camera will not see anything. But it affects us less, because we are not dealing with autonomous tools at this stage, and in extreme weather conditions the tools are not allowed to work anyway. Anyway, we managed to collect “Data is also in extreme weather conditions, so there is a certain ability to work in these conditions.”
The growing global need for ADAS systems for heavy mechanical engineering equipment stems from the inefficiency in operating such equipment, which becomes the bottleneck in the production floor (usually a mining or construction process). The same inefficiency is mainly due to the difficulty of monitoring these tools as well as the fact that such tools work in areas estimated over thousands of acres. “These traditional industries have undergone a process of digitization in the last two decades,” concludes Tzach. “And they need creative solutions, like ours, that will meet their specific needs at a very low and competitive cost.”