We at TDB.ai provide end to end Robotics & IOT based solutions or services in order to automate the process in certain industries. We have a team of experts of robotics, IOT, Embedded devices, electronics, raspberry pi, jetson nano, Networking Administration, Robotics, C#, Electronic Devices, etc.
A robot must protect its own existence as long as such protection does not conflict with the First or Second Laws.
We help in your business
It is beneficial for the companies to look to automate the process. Robots are more precise and efficient than humans. Medical, and industrial errors can be almost eliminated with the use of robots. By using robots, businesses can see massive savings and cost effective changes to jobs that may take humans days to complete. Robots can produce high quality products.
We have considerable expertise and experience with various hardware platforms, sensors, actuators, and other components, ranging from the actual microcontroller to miniaturized yet robust PC platforms. We've come a long way in establishing ourselves as a trusted brand supplying world-class safe solutions for years, with experience in every wireless solution imaginable, starting with Bluetooth.
Our embedded systems design services can help you create an embedded system. Our designers use microcontrollers, microprocessors, and even custom-designed chips, as well as the required operating systems. Our design team provides you with the best designs and development services made using cutting-edge technology and techniques with their extensive industry expertise. We can solve your requirements, whether they are essential or complicated. We assemble the embedded system's numerous components, write application code, and undertake support qualification testing and system integration.
This is one of the finest solutions we have developed for a middle east based hospital. If the patient or person has fallen down on the ground or has been lying for more than 10 seconds, it will directly create an alert to respond to this issue. Also it can be used to detect the injuries or any suspicious event in many sites. We have used YOLOR to dtec the person and posenet to detect the poses and applying LSTM transformer to detect the event like fall/ lying down etc.
This is the project that we have done in which if the driver is driving a car and having any kind of fatigue, or smoking or drinking in a car. It will create an alert and the owner can take some action on the driver. This solution has been developed for a dubai based automobile company.
This is the solution we have implemented in an ABU DHABI based hospital in which any kind of smoke/fire is occurring in an area. It will detect and report it directly. We have used LSTM and Transformer with YOLOV4 to detect the fire at real time on RGB and Thermal RGB images with the segmentation layer of SOLOv2. The accuracy we have achieved is around 95% so far.
This is the live project that has been going on in an India based smart city for parking lot management in which we have to detect the car, truck, bike and its number plate at real time with the accuracy of 96% test videos. We have used YOLOv4 with TensorRT(use to optimise the frame rate i.e if you get 4FPS on yolov4 then using TensorRT you will get 40FPS) to detect the Licence Plate, Car, Truck, Motorcycle, etc and using our own text recognition model which is Bi-Directional LST with transformers to recognise the text at real time on GPU.
This is the solution that we have developed for a US based organization in which their major problem was the invoice reading by a human. Daily around 150000 invoices have been generated over there and hundreds of humans were assigned to do the manual data entry on their SAP Platform. We have built a solution in which one has to just upload the PDF from the system/database and select the fields they want to extract like Shipping address, billing address, Invoice number, Email address, Telephone Number, Billing and shipping date, etc and start reviewing. All the required details will be published on the database and then assigned to the separate SAP platform. In this, we have reduced manual monitoring. As in one minute, 1000 invoices have been processed.