Nerd For Tech
Published in

Nerd For Tech

Typical Application Scenarios of Autonomous Driving

www.chinatimes.net.cn

Typical application scenarios where autonomous driving can be commercialized include independent taxi scenarios, warehousing, logistics, ports, docks, fixed-route area connections, sweepers, mining areas, etc. The following is a simple analysis of three representative landing scenes.

Application scenario 1: RoboTaxi (autonomous driving taxi)

Some time ago, Chinese companies such as Baidu, AutoNavi, Weride, AutoX, and Didi rushed to send good news in the field of RoboTaxi (self-driving taxi). It can be said that through the landing of RoboTaxi, human beings have opened a new page in the autonomous driving industry.

From point to point, then to the region, from targeting specific groups to more public groups, from free tests to charged trials, RoboTaxi is moving closer to ordinary travel services.

Although RoboTaxi has the advantage of being closer to the market, the process of “perception-decision” of autonomous driving systems is more difficult. It has higher requirements for scene-oriented training data and faces the pain points — lack of scene-oriented road data and poor data quality. Companies need high-quality scene-based AI data, which requires structured video, image, audio, text, LiDAR data.

Application Scenario 2: Unmanned Delivery

As a “star” during the epidemic prevention and control period, unmanned delivery robots have taken the challenge to the foreground and played an important role in contactless delivery. During the epidemic, consumer demand for intelligent, contactless services has increased largely, and the industry has begun to develop the potential of autonomous driving technology in the field of unmanned delivery.

Of course, unmanned delivery is nothing new. Before the epidemic, the main application scenarios were logistics parks, warehouses, communities, office buildings, etc. It can be seen that limited by technical difficulties, the goal of the current uncrewed delivery vehicle is still to solve the last-mile delivery problem. Freight and fixed traveling lines are still prominent features.

Application Scenario 3: Warehousing and Logistics

Logistics distribution is divided into long-distance trunk transportation and short-distance distribution.

Long-distance highway transportation overload, fatigue driving and traffic violations occur occasionally, however, the characteristics of expressways such as fast speed, no signal lights, and no obstacles are in favor of high efficient movement, which is very suitable for automatic driving.

Short-distance distribution often occurs in relatively closed scenarios such as warehouses, factories, and residential areas. Autonomous driving robots can accurately and efficiently undertake low-risk sorting, warehousing, outgoing, and delivery, saving the labor cost and reducing the error rate.

Taking the short-distance distribution warehousing logistics as an example, compared to Robotaxi, autonomous driving robots are more inclined to use computer vision technology to implement functions. On the premise of maintaining the data accuracy, the application’s requirement for AI data is relatively uniform. Scenario-based AI data training can help autonomous driving robots realize intelligent recognition and automatically classify the information to realize automatic sorting, etc.

The Industrialization Focus of Autonomous Driving Scenarios: AI Data

2D-3D fusion data:

For example, in order to develope multi-model machine learning algorithms for self-driving cars, some manufacturers need to fuse two distinct data sets with different dimensions. This operation is essential, but it is challenging to perform manually.

AI companies even hope that data companies can better understand algorithm technology and demand scenarios, participate in the research and development of algorithms, and give optimization suggestions on data collection. It has become the focus of data service providers to create competitive advatange as well.

Common Data Labeling Types Include:

A New Solution For the Self-Driving Data Annotation Project

ByteBridge, a human-powered and ML-powered data training platform provides high-quality services to collect and annotate different types of data such as text, image, audio, and video to accelerate the development of the machine learning industry.

Quality Guarantee

  • ML-assisted capacity can help reduce human errors by automatically pre-labeling
  • The real-time QA and QC are integrated into the labeling workflow as the consensus mechanism is introduced to ensure accuracy
  • Consensus — Assign the same task to several workers, and the correct answer is the one that comes back from the majority output
  • All work results are completely screened and inspected by machines and the human workforce

In this way, ByteBridge can affirm our data acceptance and accuracy rate is over 98%.

Communication Cost Saving

On ByteBridge’s SaaS dashboard, developers can start the labeling projects by using the labeling instruction template and get the results back instantly.
From online setting labeling briefing to expert support alongside, the instruction communication is not that hard anymore.

ByteBridge Labeling Instruction Template

3D Point Cloud Annotation Service

ByteBridge self-developed 3D Point Cloud labeling, quality inspection tool, and pre-labeling functions can complete high-quality and high-precision 3D point cloud annotation for 2D-3D fusion or 3D images provided by different manufacturers and equipment, and provide one-station management service of labeling, QA, and QC.

More info: ByteBridge Launches World’s First Mobile 3D Point Cloud Data Labeling Service

ByteBridge 3D Point Cloud Annotation Tool

3D Point Cloud Annotation Types:

  • Sensor Fusion Cuboids: 49 categories include car, truck, heavy vehicle, two-wheeled vehicle, pedestrian, etc.
  • Sensor Fusion Segmentation: obstacles classification, different types of lanes differentiation
  • Sensor Fusion Cuboids Tracking

① Tracking the same object with the same ID, labeling the leaving state;

② Time-aligned 2D images could be provided, point clouds outputs only.

Advantages of Our 3D Point Cloud Annotation Service:

· Support 2D/3D sensor fusion, support multiple cameras

· Support scalable data annotation

· AI-powered sensor fusion tool: labeling at 2X-5X speed

· Ease of use QC tool: real-time revision and synchronous feedback

ByteBridge 3D Point Cloud QC Tool

Cost-effective

A collaboration of the human-work force and AI algorithms ensure a 50% lower price compared to the conventional market.

End

If you need data labeling and collection services, please have a look at bytebridge.io, the clear pricing is available.

If you would like to have a look at the 3D point cloud live demo, please feel free to contact us: support@bytebridge.io

Source:https://baijiahao.baidu.com/sid=1673094480571846368&wfr=spider&for=pc

--

--

--

NFT is an Educational Media House. Our mission is to bring the invaluable knowledge and experiences of experts from all over the world to the novice. To know more about us, visit https://www.nerdfortech.org/.

Recommended from Medium

The Double Negative: How Technology Works

Beyond Limits Brings Space-Tested AI to Earth’s Harshest Terrains

What is reason, anyways?

Opex AI Roundup — April 2019

Data Annotation Service: By Typing Captcha, You are Actually Helping AI Model Training

Reading Reflection 1: Questioning the AI

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
ByteBridge

ByteBridge

A data labeling platform with robust tools for real-time workflow management, providing high-quality training data with efficiency. — https://bytebridge.io/#/

More from Medium

Stabilizing neural style-transfer for videos with PyTorch

Donkey car self-driving agent using Path Segmentation with deeplabv3-mobilenetv2 model

MASKRCNN- Tensorflow Object Detection API

High-speed nut counting based on Computer Vision | ignitarium.com