Dragonfly is now available with direct ROS integration.
Our team has recently released the first entirely working ROS integration for Dragonfly, making Dragonfly the first commercial visual SLAM technology for ROS.
What is ROS?
ROS stands for Robot Operating System.
ROS is an open-source, meta-operating system for robots. It is not a “real” operating system but it provides the services you would expect from an operating system, including hardware abstraction, low-level device control, implementation of commonly-used functionality, message-passing between processes, and package management. It also provides tools and libraries for obtaining, building, writing, and running code across multiple computers. ROS is similar in some respects to ‘robot frameworks’.
ROS is not a real operating system since it goes on top of Linux Ubuntu. ROS is a framework on top of the O.S. that allows it to abstract the hardware from the software. This means you can think in terms of software for all the hardware of the robot. And that’s good news for you because this implies that you can actually create programs for robots without having to deal with the hardware.
At Accuware we created Dragonfly, our unique Visual SLAM (vSLAM) technology. It allows robots, drones, machines, vehicles, AGV and mobile devices to get their real time precise location in GPS-denied environments, by just using an on-board camera. No hardware deployed on-site, no expensive LiDAR, no “sensor fusion” required.
So far in order to interact with the Dragonfly engine it was possible to use the Dragonfly JAVA application for Linux and MacOS and the Dragonfly API.
In order to be integrated with ROS we have created “nodes” that are directly interfaced with the Dragonfly engine to Start and Stop the positioning and to automatically Get the real-time location data stream. Accuware’s R&D team is able to deliver custom ROS nodes to be integrated in your projects so that our visual SLAM solution can be seamlessly integrated in robots and other devices based on ROS.
So, whether you need to integrate Dragonfly on a vehicle operating inside a warehouse or on a robot for personal assistance in healthcare, our team can provide the right integration tools.
ROS integration is just the last of the developments and services that we have rolled out in order to ease the deployment and installation of Dragonfly, and we are open to listen to your requirements: contact us and share your project, we will be glad to help!
Forklift Tracking with a RTLS System lets you understand how Forklifts are used.
Understanding how Forklifts move throughout a warehouse has always been a need: knowing how forklifts move, how operators use them, can significantly improve the operations management and the productivity.
Having an overview of the movements and utilization patterns of forklifts can let you cut the business expenses by optimizing the operations.
Forklifts and Lifting Trucks are a necessary part of the manufacturing, transportation, and warehousing industries. Yet, many businesses only use them to a fraction of their maximum potential.
Knowing the location of forklifts and being able to track this data over time can lead to great improvements.
How can you track forklifts?
Multiple technologies, hard to decide…
There are several technologies that promise to track forklifts in real time, claiming Real-Time updates with Active RTLS/RFID systems. Bluetooth/BLE, WiFi, Ultra Wide Band (UWB) and RFID have been used to track moving assets and people, but when it comes to forklifts tracking they are not the best options to choose from.
These technologies, based on radio frequency (RF), require the deployment and maintenance of an on-site infrastructure (“antennas”, “nodes”, “receivers”) throughout the warehouse that detect the presence of “Tags”, attached to the forklifts.
Not only the deployment is time consuming and expensive, but the final results are not even satisfactory. The average accuracy of BLE Tracking inside a warehouse, considering the open space and the amount of metallic surfaces creating interference, ranges between 5 and 8 meters: definitely not accurate enough for a Real-Time Locating System solution. Likewise, the other RF based technologies have significant accuracy and latency issues that cannot be overcome.
Real Innovation is here.
At Accuware we have a lot of experience with RF based location technologies: we developed WiFi and Bluetooth based tracking systems almost 10 years ago. We decided then, back in 2015, to focus our efforts on the development of a new technology able to address use cases that could not take advantage of radio frequency based systems.
In this context we created Dragonfly, our unique Visual SLAM (vSLAM) technology.
Dragonfly can provide centimeter accuracy using just an on-board camera. This technology does not require the deployment of “receivers” throughout the site, nor the installation of “antennas” or other fixed equipment. In addition, the precision is extremely high and the location is computed in real time, with a refresh rate up to 60 Hz (60 location updates per second).
A forklift location overview is important. The amount of data that you can collect from forklift tracking is tremendous and has a crucial importance for business analysis:
How long does an operator take to get a pallet?
What are the most used routes?
What are the most congested areas?
Where and when do the most of the accidents happen?
Dragonfly is used to collect data inside the warehouse and can be used to collect data outside the warehouse (sometimes in combination with a GPS unit). The possibilities of data collection related to forklifts are many:
Precise Indoor location
Custom sensors (Temperature, Humidity, Other sensors…)
Alerts in real time
Alarms Inside/Outside predefined area
Driving speed over a certain limit
Analytics and Reports
Most active warehouse areas
Average time to pick a palletet
We can also create custom analysis and reports, to let you analyze which operators finish the most orders and which operators get speed or pedestrian warnings, you can compare charts across the vehicle fleet (utilization, efficiency, accidents, average speed, average daily distance, etc.)
Reducing the costs
Speaking of cost, a large warehouse can have dozens of forklifts and similar vehicles operating at the same time on the floor.
A big fleet can have a significant impact on your budget: purchase or leasing of vehicles, maintenance, electricity for recharging, and the expense of extra workers to operate those vehicles are costs that businesses are constantly facing.
Implementing a Forklifts Tracking solution can help you control and reduce these costs:
Increasing Forklift Utilization
Dragonfly allows managers to analyze vehicle usage with an aim towards improving efficiency. When you are better able to use your existing equipment, you may be able to reduce the amount of vehicles on the floor.
With a smart combination of hardware and software, Dragonfly provides the manager the ability to keep their fleet at high efficiency levels and save money.
Without a proper procedure in place, operators are forced to figure out the best routes to take across the floor on their own. This can lead to errors and accidents. Sometimes operators need to backtrack because of other vehicles, pedestrians, or even pallets that were in the way. This wasted time could be used to fill other orders.
With Dragonfly you can understand which are the most crowded routes, where operators have to backtrack often, where the most of the accidents happen, and plan the best routing model for the future.
Dragonfly is able to detect forklift and lifting truck speed and acceleration. This enables the possibility of configuring speed limits throughout the warehouse or inside specific areas and geo-fences. The operator can receive an alert when the speed is over the limit. In some cases it is also possible to configure the forklifts to limit their speed automatically and Accuware’s engineering team can design and develop the on-board controlling system.
Dragonfly also keeps a record of all the events and activities so that they can be reviewed and analyzed to improve operator efficiency and overall safety.
Real-Time Forklift Tracking Systems are Crucial for the Modern Warehouse Managers
It is fundamental nowadays to stay updates and take advantage of technical innovations: technology is progressing faster than ever, bringing new possibilities to businesses to improve their operations and reduce the costs. Lacking or staying behind in technology can create competitive disadvantages and can lead to losses of contracts when clients prefer to assign their contracts to more advanced companies. Dragonfly is a RTLS that allows businesses to remain at the cutting edge of technology when it comes to forklifts tracking: it makes it possible to have:
Real-time location display and recording
Data analytics (that leads to operation and route optimization)
Do not let your competitors stay ahead of you!
Forklift tracking solutions can improve your business and significantly reduce the operational costs. Reduced accidents less wasted hours, and less unused vehicles mean more productivity and lower costs for maintenance and operations.
Dragonfly lets you be competitive in a sector that is continuously evolving and adopting new technologies and solutions for better operations.
Dragonfly for your Project
If you want an advanced indoor location technology for your warehouse and if you would like the advice of our experts, do not hesitate to contact us.
At Accuware we can deliver the right technology for your requirements and we provide consulting services as well, for complete custom projects. Our team will be delighted to speak with you.
A new technology trend is emerging in the retail industry: robots and autonomous machines are being introduced to perform many tasks. The robots will substitute lower-level jobs, both in maintenance functions and basic inventory functions, in order to manage rising costs.
The world’s largest retailer, Walmart, is carrying thousands of robots on board in nearly 5,000 of its 11,348 stores. According to CNN Business, these robots will wash floors, scan boxes, unload trucks and track shelf inventory, primarily at domestic locations in the United States.
A new unloading robot has already been used at the docks of hundreds of stores, extracting boxes from delivery trucks while automatically scanning and sorting goods. The unloader will be used at more than 1,100 points of sale in the near future.
“Automating certain tasks,” according to Walmart CEO Doug McMillon “gives employees more time to do the work that satisfies them and to interact with customers. Following this logic, the retailer points to robots as a source of increased efficiency, increased sales and reduced employee turnover.
Tests in dozens of markets and hundreds of stores have shown the effectiveness of robots, but how can replacing people with machines really reduce employee turnover?
This statement remains to be seen, but there seems to be strong support for greater profitability through robotics.
Are robots a threat for workers?
“As we evolve, there are some jobs that will disappear,” said Michael Dastugue, Chief Financial Officer of Walmart in the United States. The message is clear: robots remain a valuable resource to replace low-level jobs. The company says that this investment will allow human workers to perform more varied tasks, as robots take jobs that humans don’t want to do anyway.
Profit vs. People
In 2018 more than a dozen large retailers filed for bankruptcy. Sears, Diesel, Beauty Brands, Mattress Firm and many others are restructuring – or disappearing – due to bankruptcy.
Walmart’s obligation to its people remains strong – if by “people” we mean “shareholders“.
Business considerations are at the center of the transition to the use of new technologies and employees will have to adapt. Consider these statistics in a recent study commissioned by Bossa Nova Robotics. (Full disclosure: Bossa Nova is the manufacturer of inventory evaluation robots at Walmart, and others. With more than $70 million in capital raised, this Carnegie-Mellon-driven venture is revolutionizing retail sales with robots, according to CNBC sources.)
Inventory problems in Retail
Based on responses from 100 retail executives from companies with revenues over $500 million, 99% reported inventory problems. In addition, this survey showed that
87% said an inaccurate inventory was responsible for more loss of revenue than theft.
92% said that stores spend more time identifying inventory problems than implementing innovative solutions.
81% claimed they believe their stores are only maintained or even falling behind, despite the availability of new technologies.
76% said the introduction of robots in stores will improve employee productivity.
Indoor Location: the new challenge
Providing indoor location to robots is crucial when they need to autonomously move throughout a complex space. It is even more important if customers are walking throughout a supermarket while the robots move around the aisles.
Precise indoor location becomes a key component for robots: in GPS-denied environments, such as supermarkets and stores, it is necessary to consider alternative technologies for positioning.
Dragonfly, the solution to indoor location problems
At Accuware we have developed Dragonfly, a technology for robots and autonomous vehicles able to provide precise location using just computer vision. Our team has been working with several customers in retail to implement indoor location technologies, and Dragonfly is the state of the art system for similar applications.
Dragonfly is a Visual SLAM technology: unlike other systems, such as LiDARs, it does not require the installation and calibration on board of expensive hardware, nor the presence of multiple sensors for “sensor fusion” computations. Dragonfly simply requires a camera on board and uses the video stream to compute the real time location of the robot: this data can be fed it to the navigation and piloting system.
Dragonfly for your Project
If you need an advanced indoor location technology for your project, or if you would like the advice of our experts, do not hesitate to contact us.
At Accuware we can deliver the right technology for your requirements and we provide consulting services as well, for completely custom projects. Our team will be delighted to speak with you.
Sentinel is a computer vision technology that uses Artificial Intelligence to process videos from existing Video Cameras (CCTV cameras) installed in the venue. Sentinel is able to detect and identify people: it can be used to track the presence of people, analyze footfall, and collect the precise location of each customer.
One of our clients, Modani, in Miami, Florida, has been one of the first customers to use Sentinel to monitor the location and presence of customers, and track their behavior inside the store.
Modani has installed multiple cameras throughout the store to measure the traffic and analyze the movements of customers.
Modani, modern and contemporary furniture
Modani Furniture is a worldwide famous brand for high-end modern and contemporary furniture. Modani focuses on simple geometric shapes rather than the heavy ornamentation typically found in traditional or contemporary furnishings.
Each piece of furniture is designed to be personal: Modani sources beautiful materials from around the world, such as raw-edge acacia wood, stainless steel, nickel or aluminum, velvet, suede, and silk to create furniture profiles that are transitional.
Modani has several stores across the United States and their Miami retail space has been equipped with Sentinel video tracking for several years.
Tracking customers inside the store brought several benefits
Customer behavior insights
The first and main advantage of using retail analytics is that they provide tangible and actionable insights about customers’ behavior.
Handling the aspects of a business becomes way easier when one knows how to measure the return on investment. Retail analytics makes it possible. Retail analytics gives a highly accurate picture to retailers of what works and what doesn’t: this becomes crucial when trying to understand the customers’ response to a product or to a marketing campaign.
Improving Marketing ROI
As mentioned above, retail analytics helps in measuring the return on investment (ROI) across various aspects of business management.
Therefore, Analytics can have a deep impact on enhancing the ROI from marketing endeavors. A store manager can measure the effect of in-store influences and modifications on purchase patterns, so he can alter future campaigns accordingly.
He can focus on effective campaigns and plan marketing initiatives based on what triggers specific customers’ actions.
Optimizing In-Store Operations
In-store analytics offer a strong understanding of the consumer behavior. Tracking the shopping patterns and analyzing dwell times can reveal several opportunities for all types of retail operations, from individual stores to large shopping malls. Managers can change the layout to be more attractive, can plan the service delivery quality that customers like the most and the product placements that draw maximum attention.
With these KPI at hand, retailers can manage the best staffing options, the most attractive design techniques and the best selling tactics, based on real data.
Retail analytics helps in understanding the relationship between a store and its visitors, by giving useful insights into customer behavior.
It helps the retailer to get the right information across to the desired recipient and ensure a nice shopping experience for the buyer. By personalizing marketing content based on the customers’ response, retailers are able to showcase the relevant products and offers to the most responsive audience, therefore increasing the propensity in them to buy.
This also increases the brand perception with the customers who feel valued. As a consequence, this positively affects the loyalty that they feel towards the brand.
Managing the Basics
Retail analytics plays a crucial role in improving the efficiencies in daily business management.
Predictions based on analytics let the retailer take immediate actions for decision-making on stocking, tracking, and restocking SKUs on a convenient and regular basis. Keeping a track of how often a particular product is sold, sellers can predict and analyze the trends that are dominant in the current market. This insight can help identify the most popular items, concentrating on these and similar products to improve the lateral sales.
Sentinel Video Tracking Technology
Modani has installed several CCTV cameras to use Accuware Sentinel: Sentinel is an intelligent video tracking system that enables all kinds of retail analytics.
Sentinel makes it possible to build solutions and software to analyze visitors’ behavior by following the movements of people inside venues and stores, identifying and tracking them by their visual appearance.
Sentinel provides API and raw CSV files that can be integrated into analytic systems, and Accuware’s partners can also deliver an end-user application for retail analytics, if required.
Accuware Dragonfly, a visual SLAM technology based on computer vision, provides accurate location to robots, drones, machines and vehicles. But, what is SLAM? How does it work?
This article wants to give a brief introduction to what SLAM is, how it works, what it’s for (and what it’s not for), and why it is important for the new industry revolution.
The importance of Simultaneous Localization and Mapping (SLAM) is constantly increasing, not only among the computer vision community, but across multiple industries. It is receiving specific interest from augmented and virtual reality industries, and from the robotics and automation sector.
SLAM is in fact now able to address localization problems that many industries have been facing along the years.
There is however large variety of SLAM systems available, from the academic world and from the industry: in this context, and to clarify the typical confusion around this new technology, it is worth exploring what SLAM means and how it works.
What is SLAM?
‘SLAM’ does not refer to a particular algorithm or specific software: it rather refers to the problem of simultaneously localisation (know the location/position and orientation) of a device with respect to its surroundings and at the same time create a map of the environment.
SLAM can be done in a number of different ways: SLAM is not strictly a computer vision topic, and it could also work with other technologies, such as lasers scanners and LiDARS.However, in this article, we will focus on visual SLAM, which is the most innovative technology. In fact, at Accuware, we have decided to focus on the development of Dragonfly, our visual SLAM system, to offer a valid alternative to other SLAM technologies that rely on specific hardware, such as LiDARs, and to create a brand new positioning algorithm.
Computing both the position of the device and the map, through the on-board camera, when neither are known, distinguishes the SLAM problem from other technologies.
For example, 3D mapping/reconstruction with a fixed camera rig is not SLAM, because while the map is being recovered, the positions of the cameras are already known and fixed. SLAM instead provides the ability to recover both device’s pose and the map structure, initially knowing neither of them.
It is important to note that this if one of the key features of SLAM: computing the pose creating the map in real time is in fact what makes SLAM different from other systems. This also means that the processing is typically “on the fly” so that the camera’s location is continuously known and updated.
Dragonfly, however, is able to also post-process existing videos: this is extremely useful in order to improve the accuracy inside some challenging environments, and to perform preliminary tests to estimate the final accuracy of the system, without being on site.
A Brief History of SLAM
The first researches on SLAM began among the robotics community: 1986
papers by Smith and Cheeseman are usually
indicated as the first technical documents about SLAM, originally applied to wheeled
robots on a flat ground. The first SLAM systems were combining different sensor
readings (laser scanner or sonar, for example) with data from the control input
(steering angle) and mechanical measurements (such as wheel rotations counts).
In recent years, instead, visual sensors have become a crucial aspect of
SLAM research: the improvement of computer vision techniques and the high
computation power of processors are opening a new era for SLAM.
Many studies on visual SLAM focused on the use of stereo cameras, or
cameras in combination with other sensors (“sensor fusion”).
At Accuware we have decided instead to explore the pure computer vision SLAM, using only monocular cameras, without external sensors. While Stereo Cameras can be used with Accuware Dragonfly, they are not required.
Our scope has been to make SLAM a widely useful technology that does not
require additional hardware or sensors. We wanted to deliver a precise location
system based on visual information that can be derived from an existing
on-board camera, removing the need of sensor fusion and of other hardware to be
mounted on board of robots and drones.
How SLAM Works
Dragonfly analyzes the video stream coming from the device’s camera: it keep tracks of a set of points (“features”) through multiple camera frames and uses them to triangulate the 3D location of the device and create a virtual map of the environment. At the same time, Dragonfly can use the estimated point locations to calculate the camera’s pose.
With the use of a single monocular camera, carefully merging the different features detected over multiple frames, Dragonfly can elaborate the pose of the device (6-DOF) and map the structure of the surrounding ambient with high accuracy, up to an accuracy of 5 cm.
Dragonfly also includes the ability to improve the map quality over time, to increase the accuracy, and leverages loop closure: this automated procedure makes it possible to reduce the gradual accumulation of errors over time. The current location computed by Dragonfly can be associated to a preliminary known location inside the map (Visual or Virtual Markers), optimizing the map structure and reducing the accumulated error.
The map is then used to perform relocalisation: if the device experience a low tracking performance, which can lead to the system getting “lost”, Dragonfly is able to recognize a previously detected “feature” and use it as a marker to compute the relative location inside the map.
Relocalisation is also useful to start the positioning of the device from any place inside an existing map: the starting point is automatically recognized by Dragonfly, analyzing and recognizing the surrounding features.
SLAM in Real Applications
Now that we know how SLAM works, how can this system be useful in real
life? How can Dragonfly be applied to actual projects?
Visual SLAM is nowadays needed in many different applications.
Dragonfly is used to remotely track the location of moving vehicles, such as forklifts, inside large environments. Dragonfly’s ability to dynamically update the map is extremely important in similar venues, which are subject to constant changes. Some of our customers are leveraging Dragonfly to monitor the usage of machines and ground robots (think about industrial cleaning machines, lawn mowers…), and others have been installing Dragonfly on board of flying drones to improve some operations inside GPS denied environments, such as inventory management.
We work with
customers that have been developing self-driving robots and vehicles, and who
are exploring autonomous navigation for drones as well.
In the era of automation, with the roll out of unmanned vehicles and with the beginning of commercial drones’ applications, Dragonfly is becoming an essential technology to provide positioning where GPS is not an option and where centimeter accuracy is necessary.