ZREMB
Our collaborative efforts with IT Corner partners have created a cutting-edge elevator management system named Martha, which uses AI vision to detect users and optimize traffic while also providing users with personalized content.
Project duration
- September 2021 - July 2023
Industry
- Manufacturing, Industrial Automation
Awards
- PropTech Festival 2022
Services provided
- Custom software development
- Business Advisory
- Testing
Team
- 3 Full Stack Developers
- 1 Software Architect
- and 1 Product Owner
Country of operation
- Poland
Project summary
We helped secure an innovation grant of PLN 3 million for ZREMB.- Martha won the PropTech Festival 2022 competition among the likes of Żabka Nano and Park Cash.
Thanks to a Lean approach, we successfully decreased the project budget for the MVP version from PLN 3 million projected by the client to PLN 500 thousand, optimizing the budget use.
We greatly optimized the estimated implementation time for an MVP from 2 years to just 6 months.
About the Client
ZREMB (eng. ZREMB Elevator Equipment Company) is an established company with over 70 years of successful presence in the Polish market. ZREMB excels in providing holistic technological solutions for elevators, with a distinct emphasis on sustainability and environmental preservation. Their expertise lies in delivering cutting-edge elevator systems engineered for heavy-duty use, ensuring prolonged operational lifespans without the necessity for frequent replacements.
What truly distinguishes ZREMB and contributes to their success are seamlessly integrated lift control systems. These systems boast universal compatibility with equipment manufacturers worldwide, setting a new standard for industry synergy. Their broad offer included extensive elevator solutions, encompassing small freight elevators, accessible platforms, passenger and freight elevators, escalators, moving walkways, and steel construction elevator shafts. From installation and modernization to repair and maintenance – they've got you covered.
About the project
Operating in a highly specialized field of industrial automation and seeking innovation that would further confirm their role as an industry leader, ZREMB has envisioned a state-of-the-art elevator management system.
Here comes Martha – an AI-powered robot with a mission to offer a personalized, human-like approach instead of the simple press-the-button interaction we know from elevators installed in our buildings. To turn our client’s vision into reality, Martha needed to utilize a well-rounded machine-human interface, incorporating automatic recognition and voice & touch interfaces.
Yet – that’s not all. It was necessary to introduce graceful degradation so that when one interface is not preferred by the user, the other one takes over. The users are, therefore, empowered to switch interfaces as they see fit. Combined with a must-have support for the Polish language and offline accessibility, Martha called for a custom solution.
The ZREMB project wouldn’t have been possible without ITCorner. It all started when Rafał Pisz, CEO of QuantUp, shared information about the Martha project within our community. With vast experience and a proven track record of successfully navigating innovative projects, Vazco was strongly recommended as a business & technology partner for ZREMB.
What client challenges did the team have to overcome?
Balancing budget constraints with ambitious project goals
Vazco had to find innovative ways to optimize costs and deliver a feature-rich MVP that would meet business objectives.
Acquiring an innovation grant to fuel long-term growth
Martha is a system designed with scalability in mind, and its growth was dependent on attracting investors.
Introduce complex machine vision algorithms
This intricate endeavor necessitated integrating cutting-edge technology to enable facial recognition and behavioral pattern analysis within the elevator control system.Optimizing the timeframe
The two-year timeline for the original plan could harm the project by allowing competitors enough time to replicate the idea.
Integrating complex and diverse technologies
Combining facial recognition, voice interaction, and touch interfaces posed technical challenges. Moreover, graceful degradation was required.
Overcoming hardware compatibility issues
Ensuring seamless integration between the software solution and the elevator's hardware components.
Team Perspective
When ZREMB approached us with their innovative project, we immediately saw great potential in their vision – however, we also noticed that they needed to refine their plan to become clearer. Also, the project required a software, hardware, and machine learning company, so we had to find trusted partners.
Moreover, we also knew that the original two-year timeframe would pose a threat to the project’s success, as it gave much time for the competitors to outperform ZREMB by executing a similar idea. We wouldn’t have allowed that to happen.
Starting with an in-depth discovery session and analysis, we restructured our client’s business plan. We reached out to our most trusted community – ITCorner – to arrange and orchestrate a smooth collaboration with world-class experts. We also created a concrete plan that produced the MVP within 3 months. This allowed our client to gain a competitive advantage and outperform potential competitors. The time was now on ZREMB’s side.
Michał Zacher
CEO of Vazco
How did we navigate the client for success?
Optimize budget & secure funding
Martha is a long-term investment, so the project must operate within an optimized budget. We helped ZREMB cut costs for the MVP version by 600% compared to the initial projection provided by the client. We have also leveraged our vast business experience and know-how in securing funding for startups to attract potential investors.
Joining forces with QuantUp, we helped ZREMB acquire an innovation grant of PLN 3 million (~USD 750 thousand) by partaking in panels organized by NCBiR (The National Centre for Research and Development located in Warsaw, Poland) as well as submitting the application.
Connect the client with the industry’s finest
Thanks to a seamless web of deserved trust we have created within the ITCorner community, we were able to connect ZREMB with top-tier experts in areas that went beyond our expertise at the time. We subdivided the entire scope into interconnected projects entrusted to our ITCorner partners while also coordinating the whole. The project wouldn’t have seen the light of day in the form it proudly boasts today if not for our ability to connect different companies that share the same goals.Sophisticated machine vision algorithms, facial recognition, and behavioral patterns were entrusted to QuantUp. We also collaborated with Alfa-Net to consult hardware-related issues and Ideacto for UX/UI.We also built a partnership with the Wroclaw University of Science and Technology, one of the top 5% of higher education institutions in the world, according to CUWR. A group of students carried out a pilot project for us under the study of an innovative approach to speech recognition mechanisms in Polish.Moreover, we secured smooth communication and cooperation between all parties involved, ensuring client satisfaction. Our effort to create a multidisciplinary team has paid off, notably by reducing the time and resources needed to complete the project.
Rapid MVP delivery
Our team has been tasked with delivering the Minimal Variable Product as swiftly as possible. By leveraging the lean approach, we successfully delivered a system that met the client’s goals within an optimized timeframe.
We delivered the first functional prototype within weeks. It included a web-based elevator control solution, voice interaction, facial recognition, and elevator maintenance and management support. The client assessed this first iteration and laid the groundwork for the final product. After 3 months, the system was ready for testing. In about 6 months, it was ready to test in production.
Tech stack choice & technical excellence
We delivered the API Gateway, implemented as a Node-based server, which is a vital intermediary between the system's diverse elements and the elevator's industrial controllers, facilitated through the CANopen protocol. The cap application was built with React/Electron, and the management and maintenance system relies on Meteor/React. All tech stack choices have been thoroughly researched and proved to be bulletproof in development.
The project's most challenging aspect was creating a sophisticated system that combines facial recognition, voice interface, and touch interface. Moreover, we need to carefully plan for how the system interacts with different users. For example, if one is wearing a mask, facial recognition will not work. If one has limited speech or hearing abilities, the voice interface may not be suitable. Thanks to graceful degradation, one functionality takes over the other when required. Moreover, we needed to account for unexpected technical issues and make Martha accessible offline.
Deliver elevator audit application
In the initial phase of our project, ZREMB has also confidently decided to expand our partnership. We took on the challenge of creating an elevator audit application. Our ADA solution boasts an extensive form containing hundreds of questions, including closed, multiple-choice, dependent, and open-ended questions. Additionally, the app automatically generates an audit report that aligns with Zremb's ToR format, which is widely used for selling repair services and bidding.This solution has been made possible by utilizing Forminer. Thanks to utilizing our product, ZREMB can save up your time on form-building feature development, which is now streamlined and does not require a developer.
The scope delivered
The comprehensive scope of the project reflected an intricate interplay between hardware, machine vision algorithms, communication protocols, and software. The endeavor necessitated a meticulous selection process, an informed algorithmic approach, and a strategic perspective on future system development, all synergistically contributing to realizing the project's overarching objectives.
We can segment the scope of work into two distinct projects: the Martha project and ADA - elevator audit application. It is worth noting that ADA is an integral component of the communication part within the Martha system.
Architecture plan for key system elements:
- the hardware driver,
- the gateway on Raspberry Pi to the hardware driver,
- guidelines for panel and hardware setup,
- the cabin app and communication infrastructure, taking into account environmental constraints like electromagnetic interference, etc
Developing sophisticated machine vision algorithms for facial recognition and behavioral patterns.
Analysis of the Controller Area Network open 417 standards and implementation of the CAN node for the gateway.
Implementation of the system communication API.
Implementation of the cabin Kiosk application.
Preparation of a comprehensive requirement specification for the elevator audit application.
Analysis of the elevator audit document based on detailed & very specific requirements.
Implementation of the audit application for administrators, including testing, iterative improvements, and bug fixes.
Successful deployment of the audit application.
The Martha project
Martha is not just a machine; she is a robot that continuously learns the building's dynamics by understanding user habits and predicting their intentions. She follows users, navigates them without the need for buttons, and always knows where she’s needed next. Martha’s self-learning capabilities allow her to continuously acquire new skills, making it easy to add functionalities based on property owners' needs – similar to downloading an app on a smartphone.
Martha can also display personalized offers on in-cabin screens, or serve as a real-time bulletin board for building administrators to update content, including videos, images, and information. With AI-driven automation, Martha self-diagnoses any issues, alerts handlers, and can even facilitate remote repairs, minimizing downtime and additional costs. Furthermore, Martha enhances security by capturing images in-cabin and on floors, ensuring that the building remains secure.
Some of Martha’s capabilities include:
Martha learns user habits, predicts intentions, and delivers personalized assistance in real-time thanks to advanced features such as voice interaction and facial recognition. It recognizes users thanks to infrared-based devices and can interact with them or propose personalized content. Martha's programming allows for continuous skill expansion, adapting to new functions as needed.
Martha is compatible with various elevator systems, streamlining management through a single interface. It’a also possible to integrate Martha with building devices and systems, like automatic cleaning machines and medical robots.
Martha's recognition technology provides a remarkable advantage through its ability to deliver tailored content and information display, which also presents opportunities for advertising. Building administrators can efficiently manage content updates across multiple elevators via Martha's system.
Elevator trips are simplified as Martha allocates floors without the need for buttons, ensuring smooth passenger journeys. Thanks to graceful degradation, it’s also more accessible to users with disabilities or limited mobility. With in-cabin and floor image capture, Martha enhances building security and monitoring capabilities.
This innovation also aimed to reduce crane usage by automatically allocating floors to users, which makes it less prone to human error. Simply put, less usage means fewer breakdowns. Moreover, Martha self-diagnoses faults, alerts handlers, and facilitates remote repairs and updates, minimizing downtime. Her design and proactive maintenance minimize malfunctions, ensuring a dependable and efficient service.
How did the client perceive our partnership?
Support from a consortium of ITCorner companies was important to us because everything was done under one umbrella. The team of these companies was so complimentary that we were able to implement each of the "digital" stages without worrying that we would have to look for another partner. This was beneficial for us in terms of time and finances.
Paweł Tymowski
CEO of ZREMB sp.z.o.o (for ITCorner)
Key values delivered
- 84%
Reduction in budget
- 75%
Reduction in timeframe
- PLN 3 M
Grant acquired
Next Steps
Through our cultivated and collaborative relationship with ZREMB, we have not only achieved successful project delivery but have also initiated endeavors to expand their horizons within the industry. Leveraging our network, we are actively exploring opportunities to forge connections between ZREMB and esteemed entities we cooperate with, like CBRE, fostering potential synergies and partnerships.
Our engagement extends beyond the confines of the current system, manifesting as discussions about continued collaboration on system enhancements and extending advisory support on diverse subjects. Our strong rapport is a testament to the rapport we have diligently nurtured, grounded in mutual respect and shared objectives.
ZREMB, thank you for this exciting journey. Now – to the future!