Moscow

RoboCV

System for automation of floor movements of pallet cargo

automation

driverless

driverless_cars

robotics

RoboCV X-MOTION NG

CROC

CROC UAV is a universal management system that supports autopilots and UAVs: DJI, MavLink-compatible, Yuneec, Mikrokopter, Microdrones.



The system allows to plan and manage UAVs flights; manages drone flocks and conduct high-rise surveillance using tethered UAV (cable-powered from a ground station).



The solution also allows to manage one or several UAVs, receive and record telemetry and alert an operator about a dangerous drone approaching other aerial vehicles, support simultaneous activities of several operators and can be integrated with automatic dependent surveillance-broadcast (ADS-B) systems.

drones

quadcopters

CROC UAV

Marvelmind_Robotics

Precise (±2cm) navigation system for autonomous robots and virtual reality systems. It is used indoors and outdoors and is based on stationary ultrasonic beacons united by radio interface in license-free band. Location of a mobile beacon installed on the robot (vehicle/copter/human) is identified based on propagation delay of ultrasonic signal to a set of stationary ultrasonic beacons using trilateration.

High-precision navigation for autonomous robots, drones and VR systems

facebook.com/Marvelmind-Robotics-1414019918621418

navigation

Marvelmind Robotics high-precision navigation

WareVision is a hybrid robotic system based on UAV and a mobile robot intended for warehouse inventory. The robotized system includes UAV navigation algorithms, UAV indoor management algorithms, computer vision system with pallets’ barcodes and RFID tags recognition and a specially created protocol for synchronization with WMS using base station.

Autonomous robots for warehouse inventory

warehouse

computer_vision

artificial_intelligence

RFID

WareVision

An unmanned aerial vehicle COEX Pelican can perform an autonomous takeoff and landing on designated marks. It can independently land in a station for automatic charging of its batteries.

It can be equipped with different types of cameras and sensors and used for monitoring and delivery of cargoes that weigh up to 1 kg.&nbsp;

Autonomous drone for monitoring and cargo delivery

Copter Express Pelican

A cloud-based web platform for construction quality and costs control with the help of a visual interface and analytic algorithms based on the data collected by an unmanned aerial vehicle (UAV, drone).

The data collected by drones and geodetic tools are used to create an accurate 3D copy of a construction site, which is further compared against the expected results (drafts, models). This way it is possible to identify the differences between the plan and real-life results, letting one detect errors at an early stage.

The solution is used throughout all construction stages: design, ground and road works, mounting of a building, housing improvements and actual use.

The solutions include the sale and maintenance of drones: collection, processing and analysis of collected data; a suite of tools for working with construction processes using the TraceAir platform; analytics of construction processes and control of areas of particular importance.

Remote control of construction sites based on data collected by drones

construction

TraceAir

Cognitive_Pilot

Cognitive_Technologies

The autonomous control system based on artificial intelligence is designed for installation on agricultural machinery – farm tractors, combine harvesters. The automated system, in addition to the AI system, includes a camera and a calculator with additional interface units with combine harvester’s onboard systems.

The Cognitive Agro Pilot is based on the technology of deep learning for neural networks. The Cognitive Technologies’ team of developers in real-life conditions worked on collecting datasets (the images that contain the main elements of a field environment used for neural network training) and taught neural networks to perceive objects and situations a smart combine harvester will confront during the process of its work and which should be recognized by the artificial intelligence.

AI systems can see different types of boundaries of a field (edge, cutting), eliminating the need in installing extra sensors on the equipment. The solution also allows for adding new types of boundaries (rowing – the shape of planting certain crops, for instance, corn, as well as that of tilled and untilled parts of a field).

Autonomous control system for agricultural machinery

farming

Cognitive Agro Pilot

The system automates the horizontal pallets movement within the FMCG distribution centres and warehouses.

The solution consists of a regular electrical forklift equipped with an autopilot system by RoboCV and a cloud-based service which optimizes task distribution among robots in real time. It allows for implementation of a client-server module to enable centralized management of robots’ tasks and monitoring of their state. It can also be integrated with external IT systems.

The solution automates up to70% of all warehouse processes.

A system designed to automate horizontal pallets movement 

Yandex

Yandex.Taxi

Yandex_Self_Driving_Group

Yandex self-driving cars are equipped with a hardware and software system that includes cameras, all-round lidar and radar. The lidar uses a light emitter to scan the environment, converting the information about ray reflections into a 3D map and calculating the precise distance to the obstacles in front of a car. The radar with a smaller angle of view tracks the distance to farther objects, which is crucial for cars running on higher speeds.

In addition, Yandex driverless car is equipped with sensors that track its location, speed and movement direction: GPS/GLONASS receivers, IMU and sensors that measure the rotation speed of certain wheels. The sensors use all the data they collect to enable a complex algorithm to produce a model of the environment that allows for the car to make its riding decisions. The system uses a variety of Yandex technologies, building from computer vision.

During year-round rides the self-driving car collects the data about the traffic environment to use it for further training of the technology. Before autonomous cars are allowed to ride on public roads, they undergo multiple tests in a closed-off testing site. A car using an autonomous vehicle technology has already ridden 780 km from Moscow to Kazan. A safety engineer was in the driver seat to take control of the car at any moment.

Tech Solutions

RoboCV X-MOTION NG

CROC UAV

Marvelmind Robotics high-precision navigation

add your project!
fill out the form

WareVision

Copter Express Pelican

TraceAir

Cognitive Agro Pilot

RoboCV X-MOTION NG

Yandex self-driving car

Tech Solutions

RoboCV X-MOTION NG

CROC UAV

Marvelmind Robotics high-precision navigation

add your project!fill out the form

WareVision

Copter Express Pelican

TraceAir

Cognitive Agro Pilot

RoboCV X-MOTION NG

Yandex self-driving car

add your project!
fill out the form