Unmanned Transport (autonomous transport, self-driving transport, driverless transport, or robotic transport) is a type of transport capable of moving without human intervention.

Unmanned Transport Vehicle - a highly or fully automated vehicle that operates without human intervention (Decree of the Government of the Russian Federation dated March 25, 2020, No. 724-r).

Unmanned transport uses various sensors to perceive the surrounding environment, such as thermographic cameras, radar, LiDAR, sonar, GPS, odometers, and inertial measurement units.

Control systems interpret sensor information to create a three-dimensional model (3D) of the surrounding environment. Based on this model, the vehicle determines appropriate navigation paths and strategies for managing road traffic (stop signs, intersections, main roads, speed, flow, etc.) and obstacles. High definition (HD maps) maps road maps are also an integral part of this technology.

IoT sensors, artificial intelligence, machine learning technologies, and big data analysis are all fundamental to the connected car and autonomous driving phenomenon. It is expected that by 2025, the global IoT automotive market will reach $541.73 billion, with an annual growth rate of 16.4%, and connected car shipments, according to Business Insider forecasts, will reach 65 million by 2030.

World Unmanned Transport Market Growth Forecast
Fig.1 World Unmanned Transport Market Growth Forecast

At the end of 2022, Resolution of the Government of the Russian Federation dated December 29, 2022, No. 2495, on the launch of a new experimental legal regime (ELR) for the operation of unmanned passenger and freight vehicles in cities and suburbs in 38 regions of Russia, came into effect.

"This experiment will be the largest in Russia and will allow the implementation of unmanned transport technology under various climatic and road conditions from Crimea to the Khabarovsk Krai. It already involves 38 regions from the very beginning, and various unmanned transport vehicles from several initiators are planned to be used," said Mikhail A. Kolesnikov, Deputy Minister of Economic Development.

"The team of Geospatial Agency Innoter provides reliable support to the industry in creating the cartographic base for unmanned transport," said Natalya N. Malkova, CEO of Innoter LLC.

Why is Autonomous Transport Needed?

Unmanned transport is primarily needed to save on the logistics component of cargo delivery on long-distance routes. This savings amounts to hundreds of billions of US dollars worldwide. Secondly, the absence of the human factor eliminates cargo manipulation and reduces criminal and corrupt practices. Thirdly, the growing trend of replacing hydrocarbon fuels with electric ones will lead to simple, safer, and more digital solutions for self-driving transport.

The autonomous vehicle consists of 5 main components:

  • Computer vision - identification and classification of objects using cameras.
  • Sensor fusion - the use of multiple sensors to improve the vehicle's perception of the world.
  • Localization.
  • Trajectory planning.
  • Control.

Vehicle automation consists of 5 levels:

  • Level 0 (no driving automation).
  • Level 1 (driver assistance).
  • Level 2 (partial driving automation).
  • Level 3 (conditional driving automation).
  • Level 4 (high driving automation).
  • Level 5 (full driving automation).

The autonomous vehicle management system includes the following main components:

  • Adaptive Cruise Control (ACC).
  • Adaptive Front Lighting (AFL).
  • Automatic Emergency Braking (AEB).
  • Blind Spot Detection (BSD).
  • Cross-Traffic Alert (CTA).
  • Driver Monitoring System (DMS).
  • Forward Collision Warning (FCW).
  • Intelligent Parking Assist (IPA).
  • Lane Departure Warning (LDW).
  • Night Vision System.
  • Pedestrian Detection System (PDS).
  • Road Sign Recognition (RSR).
  • Tire Pressure Monitoring System (TPMS).
  • Traffic Jam Assistant (TJA).

In global practice, the practical preparation of data for a comprehensive autonomous transport solution is based on using data from geospatial surveys conducted by UAVs and Earth observation satellites.

Countries at the forefront of the unmanned revolution - China, Germany, South Korea, and the USA - as of 2022, use level 4 autonomous vehicles that can operate in autonomous mode but allow human intervention to block control manually, at most and only within limited territories with strict restrictions in place. Therefore, it is worth questioning whether the implementation of level 5 autonomous driving systems will become a reality if infrastructure and legislation do not develop at a fast pace.

Traffic Jam Assistant (TJA)
Fig.2 Traffic Jam Assistant (TJA)

Goals and Objectivesfor High definition maps hd maps for autonomous vehicles:

Goal: To create a system for the support and facilitation of unmanned vehicle movement on the road network with a high level of safety.

Objectives: The preparatory geospatial work includes:

  • 3D modeling of urban road conditions or complex surrounding environments, digital elevation models.
  • Digitization of road traffic map objects in urban conditions:
    1. Digitization of lane map objects.
    2. Data digitization scale is 1:200.
    3. Digitization of roadway polygons.
    4. Boundaries of roadway polygons.
    5. Movements trajectories of unmanned vehicles.
    6. Centerlines of lanes should be separated into individual objects in the following cases:
      1. Change of lane markings on the right or left side of the lane.
      2. Merging with another lane.
      3. Lane division.
      4. Change in lane width.
      5. Change in vehicle speed on the lane.
      6. Entry to an intersection.
      7. Exit from an intersection.
      8. Entry to a pedestrian crossing.
      9. Exit from a pedestrian crossing.
      10. At a stop line.
      11. Transition from a straight road segment to a curved one.
      12. Entry to an artificial roughness.
      13. Exit from an artificial roughness.
      14. Change in stopping/parking possibilities in the lane.
    7. Outline of maneuvers at intersections.


Advantages of Using Earth Observation Data

The extensive coverage on highways, high detail in cities, and surrounding environment that hinders the building and control of autonomous driving, the transition from hidden structures (tunnels, mountains) to open terrain, poor weather conditions on the roads at a given moment - all these can be solved with field geodetic and textural work combined with Earth observation data carriers from satellites, aerial platforms (UAVs), to mobile Earth observation laboratories:

  • High positional accuracy (sub-meter level accuracy) in time (synchronized for the entire system to milliseconds), ensured by recordings from various position and control sensors.
  • UAVs are capable of creating complex digital road high definition maps (hd maps) and road conditions, including digital elevation models.
  • Precise geospatial descriptions of movements serve as an indisputable legal basis for resolving legal disputes and identifying insurance cases.


Precise geospatial descriptions of movements
Fig.3 Precise geospatial descriptions of movements



Prices for services

Consultation Free
Selection of technical solution, preparation of technical task Paid
Data ordering, providing shooting Paid
Data processing Paid
Cost of digitization for 1 km2 (including creation of 3D model) From 500 USD

The price starts from 40,000 rubles (1 square kilometer 3D model) and is calculated individually for each customer.


The cost of execution is calculated on an individual basis, taking into account a specific of task.

After receiving the task description, we calculate the cost and send you a commercial offer.

Period of execution

The completion period for the work is from 15 (fifteen) working days and is calculated individually for each customer.

The completion period depends on:

  • The area of the area (urban streets) or the length of the route.
  • The configuration of the autonomous vehicle.
  • The time required for assembling technical equipment.
  • The testing duration.

How to place an order:

  1. Step №1: Submit an application on the website with the following details:
    • Mapping area (coordinates, district name, region, shp-file, etc.);
    • What specific task needs to be solved using geospatial technologies?
  2. Step №2: Agreement on the technical task and cost:
    • Depending on the level of detail provided by the Customer, consulting may be required to determine the optimal technology, prepare the technical task, and justify the budget - for a separate budget.
  3. Step №3: Sign the contract and start the work.

We work with individuals, legal entities, individual entrepreneurs, government and municipal authorities, foreign clients, etc.).

You can also send your application via e-mail to: innoter@innoter.com, or contact us by phone: +7 495 245-04-24, or through the online chat on the website.


Need for consultation?

Fill the form and we will contact you

By clicking the «Send» button, you give your consent to the processing of your personal data, in accordance with Federal Law No. 152-FZ of July 27, 2006 «On Personal Data», on the conditions and for the purposes specified in the Consent to the processing of personal data.

Stages of service provision

Stage № 0 (BEFORE Contract Conclusion) - Express Assessment:

  • Assessment of the area;
  • Assessment of the Client's stated requirements regarding deadlines and final results;
  • Verification of the possibility to work on the Client's territory.

RESULT: possibility (YES/NO) of providing the service

Stage № 1 (BEFORE Contract Conclusion) - Development of Technical Task, Draft Contract:

  • Agreement with the Client on the requirements for the final result;
  • Agreement on requirements for source data;
  • In case the Client does not provide source data, agreement on the technical solution for obtaining the required source data;
  • Allocation of responsibilities/roles;
  • Final determination of labor and material costs, agreement on the deadlines for creating cartographic materials, and the cost.

RESULT: concluded contract

Stage № 2 (Contract Execution):

  • Receipt of an advance payment;
  • Creation of a prototype;
  • Agreement on the prototype with the Client;
  • Printing for the entire work area;
  • Data unloading in various coordinate systems and projections.

RESULT: the project is 100% completed in accordance with the requirements of the Technical Task.

The result of the provision of services

3D road models, digital map with road texture attributes, HD maps.high definition map (hd maps), high definition (hd) maps for autonomous vehicles


Requirements for Source Data

Selection of archived data from satellite (high-resolution) or UAV (drone) imagery for the territory or route of autopiloting.

If it is not possible to provide the specified information, please provide details about the intended use of the remote sensing materials. The specialists of GEO INNOTER will analyze the requirements and suggest an optimal solution to address the issue.

Related services

Satellite imagery. Satellite data
Satellite imagery. Satellite data
Find out the price
SAR imagery (Radar satellite data)
SAR imagery (Radar satellite data)
Find out the price
Digital terrain models (DTM)
Digital terrain models (DTM)
Find out the price
Aerial & UAV imagery
Aerial & UAV imagery
Find out the price
LIDAR Aerial Survey
LIDAR Aerial Survey
Find out the price
Photogrammetric processing (Image Processing)
Photogrammetric processing (Image Processing)
Find out the price
Радиолокационная съемка (радарные снимки)
Радиолокационная съемка (радарные снимки)
Find out the price
Фотограмметрические работы
Фотограмметрические работы
Find out the price
Заказ космической съемки. Космоснимки
Заказ космической съемки. Космоснимки
Find out the price
Цифровые модели местности (ЦММ)
Цифровые модели местности (ЦММ)
Find out the price
Аэрофотосъемка (АФС / БПЛА)
Аэрофотосъемка (АФС / БПЛА)
Find out the price
Лазерное сканирование (LIDAR)
Лазерное сканирование (LIDAR)
Find out the price
Zazulyak Evgeny Leonidovich
The material was checked by an expert
Zazulyak Evgeny Leonidovich
Engineer, 28 years of experience, Education - Moscow Topographic Polytechnic Technical School, St. Petersburg Higher Military Topographic Command School named after Army General A.I. Antonov, Military Engineering University named after V.V. Kuibyshev. Kuibyshev Military Engineering University.

Customers

FAQ

Unmanned cars use sensors, actuators, complex algorithms and optimized processors to execute software. Based on this system, autonomous cars build and update a map of their environment and determine how to navigate through it. The software analyzes all the sensory data from the car, draws a path and issues commands to actuators in the car that control acceleration, braking and steering. The software helps you follow traffic rules and avoid obstacles through the use of hard-coded rules, obstacle avoidance algorithms, predictive modeling and object identification
  • Traffic management.
  • Bureaucracy.
  • Infrastructure.
  • Revenue.
  • Liability insurance.
  • Police and emergency response.
The biggest benefit of using an unmanned vehicle is significantly fewer traffic accidents. More than 90% of all accidents are caused in some way by human error, including distraction, impaired driving or poor decision making.
Knowledge of GPS and wayfinding algorithms. Control is perhaps the most important building block of an autonomous vehicle. It includes guidance, navigation, and motion control systems and requires knowledge of math, engineering, and programming to build this function.
Unmanned vehicles using on-board sensors and evaluation equipment will always have a 360-degree view of their surroundings. Removing the driver from the controls will also reduce the element of human error in driving, which today is responsible for 90% of all accidents.
high definition (hd) maps (hd maps) for autonomous vehicles its a digital map with high definition
The high-definition maps (hd map) concept was first introduced in the Mercedes-Benz research in 2010 and later contributed to the Bertha Drive Project (Ziegler et al., 2014) in 2013. In the Bertha Drive Project, a Mercedes-Benz S500 completed the Bertha Benz Memorial Route in a fully autonomous mode, utilizing a highly precise and informative 3D road map, which was later named “High Definition (HD) Live Map
The initial step in producing high-definition maps (hd maps) is data sourcing and collection. This stage is paramount and takes precedence over all others, as the effectiveness of point cloud map generation and feature extraction techniques is heavily reliant on the volume and quality of the data gathered. Data is typically gathered using a mobile mapping system (MMS), which involves outfitting a mobile vehicle with mapping sensors such as GNSS (Global Navigation Satellite System), IMU, LiDAR (light detection and ranging), and a camera.
After gathering image data and creating a point cloud map, the next crucial step is feature extraction. This process is vital for making the HD maps (high definition maps) informative and enabling the ego vehicle to locate itself and adhere to motion and mission plans. Road/lane extraction, road marking extraction, and pole-like object extraction are essential feature extractions for this purpose. In the past, feature extractions were labor-intensive, expensive, time-consuming, and often lacked precision.
The advancement of HD maps (high definition maps) generation technologies has been significant in recent years but still has its limitations. While feature extractions on 2D images can efficiently produce elements such as lane lines and road markings for large-scale maps using aerial images, these extractions lack altitude or depth information. One way to address this is by adding altitude or height data manually to the 2D map, creating a 2.5D map through GPS data matching and incorporating additional altitude details.
Painted Lines, Signs, 3D Building Models, signals and Stop Lines, semantic Data
High Definition (HD) maps for autonomous vehicles are detailed, three-dimensional maps specifically designed to support the safe and precise navigation of self-driving cars. These maps go beyond traditional navigation maps by providing a comprehensive, up-to-date representation of the environment, including not only road layouts and surface topology but also information about lane markings, traffic signs, traffic signals, and other critical elements of the driving environment.
High Definition (HD) maps for autonomous vehicles are detailed and precise digital maps created to support the navigation and decision-making capabilities of self-driving cars. Unlike traditional maps, HD maps provide granular information about the road environment, including lane-level details, road geometry, and specific features crucial for autonomous vehicle navigation.
Remote sensing data, obtained from satellites, aerial surveys, or other sensors, is used in the creation and updating of HD maps for autonomous vehicles. This data helps capture accurate information about the road infrastructure, terrain, and dynamic elements such as traffic flow, enabling the construction of highly detailed and up-to-date maps.
Sensors on autonomous vehicles, including lidar, radar, and cameras, play a crucial role in real-time data collection for HD maps. These sensors continuously scan the surroundings, capturing details such as road conditions, obstacles, and other dynamic elements. The real-time data contributes to improved navigation and safety by providing the latest information for the autonomous system to make informed decisions.
The precision and accuracy of HD maps significantly impact the performance and reliability of autonomous vehicles. High-quality maps are essential for precise localization and path planning. Measures taken to ensure map quality include frequent updates based on real-time data, rigorous validation processes, and the integration of multiple data sources to minimize errors and discrepancies.
HD maps contribute to the safe and efficient operation of autonomous vehicles by providing detailed information about the road environment, enabling precise navigation and decision-making. They enhance the overall adoption and acceptance of self-driving technology by instilling confidence in users, regulators, and stakeholders regarding the reliability and safety of autonomous systems, fostering a smoother transition to widespread adoption.

Licenses

Warranty

&

Our partners