How does AV impact an organization’s performance?
Some impacts are:
Controlling Future Transport
Integrating Large-Scale Systems
Scale Intelligent Transportation: This is achieved through integrating city management, traveler payment and system information. Modernizing traffic control helps travelers find smarter ways to travel and easier ways to pay.
Modernize Commercial Ships: This is done by 360 degree sensing, modern bridge controls, advanced HMI and assisted maneuvering.Manage Critical National Assets
Distribute Real-Time Control: For Wind Turbine farms, gust control across the array requires fast communications with dynamic, selectie filtering
Increase Efficiency: Reducing manual operations and automating operations on different levels including dangerous operations with fast and safe handling.
Bring Autonomy to Harsh Environments: This can lead to cost reduction on operation and process improvement as well as environmental protection.
Support Common Platforms: This is done through satisfying the demands of other intelligent machines.
Ensure Reliability for Complex Systems: Delivering dependable and accurate results.
Connecting Vehicle/Cloud/Infrastructure: Exchanging critical patient care information in the healthcare sector.
How is the success of AV measured for users and for the business?
Specifically for AV are becoming more and more popular as companies are developing models and prototypes. As more businesses develop AV, they must address the issue of security. Businesses must design security measures beyond traditional firewalls first to avoid host lock downs.
Along with security, developing AV greater than level 4 shows a rise in trends and development.
What are the typical capabilities of AV?
Depending on the level that the vehicle is autonomous, there are different capabilities.
Level 1 is typical speed control or adaptive cruise control. Level 2 is “hands off, eyes off” but, the driver is supposed to be there all the time in case any issues arise. Level 3 is “hands off, eyes off” but, only in specific situations e.g freeway. The difference between level 2 and 3 is that the car is running safely in that environment without getting into emergency situations or at least detection of it early on to react to it. Level 4 is when the vehicle is running all the time. There is no need for a driver however, if it gets stuck it may need assistance to maneuver around i.e construction areas. Level 5 is “no steering wheel, no rate” which is entirely autonomous without a driver.
Data distribution service (DDS) is an industry standard for autonomous vehicles and is a key differentiator for RTI / AV. DDS is the proven data connectivity standard for the IoT. DDS is unique because it is open standard and cross-vendor. Some autonomy challenges that it addresses are; ensures reliable data, guaranteed real time response, manage complex data flows, ease system integration, allow any network, built-in security, flexible deployment, ease safety certification, adapt intelligence, connect vehicle to cloud systems.
Which organizations, departments or individuals typically make the investment decisions and allocate the AV budget?
Private companies in the auto industry develop the RTI Automotive technology in vehicles.
Which organizations, departments, or individuals are responsible for operating and maintaining AV?
Companies that conduct R&D internally such as Mercedes.
Who are the regular users of AV?
The application varies but it may be consumers, logistic companies or other companies that use automotives.
Which external stakeholders would benefit most from AV data?
Autonomous vehicle manufacturers, the military, Hardware companies that use DDS as an underlying platform. Some examples mentioned were Auto SAR, Nvidia and NXP.
What sensors are typically used to provide AV data into the IoT system, and which factors define their deployment?
Sensors on the vehicle that are fused with central computing. Typically these sensors are; low latency, high throughput and accessible to all data. As sensors are fused with a central computing system they can be distributed to support higher autonomy using a distributed architecture. To accomplish this, DDS must have subsystems to support the flow, space and time of data.
RADAR sensor acquires information from nearby objects like distance, size, and velocity (if it is moving) and warns the driver if an imminent collision is detected. Should the driver fails to intervene within the stipulated time (post-warning), the radar’s input may even engage advanced steering and braking controls to prevent the crash. The high-precision and weather-agnostic capabilities of radars make them a permanent fit for any autonomous vehicle prototype, notwithstanding the ambient conditions.
LiDARs are “light-based radars” that send invisible laser pulses and ascertain their return time to create a 3D profile around the car. Unlike cameras and radars, LiDARs do not technically detect the nearby objects; rather they “profile” them by illuminating the objects and analyzing the path of the reflected light. This, when repeated over a million times per second, yields a high-resolution image. Since LiDAR sensor uses emitted light, its operation is not impaired, notwithstanding the intensity of ambient light which means same intensity in night or day, clouds or sun, shadows or sunlight. The result is a greater accuracy of perception and high resilience to interference.
Camera-based systems are either mono-vision i.e. having one source of vision or stereo-vision i.e. a set of multiple (normally two) mono-vision cameras just like human eyesight. Depending upon the needs, they may be mounted on the front grilles, side mirrors, and rear door, rear windshield etc. They closely monitor the nearby vehicles, lane markings, speed signs, high-beam etc. and warn the driver when the car is in danger of an imminent collision with a pedestrian or an advancing vehicle. However, the most advanced camera systems do not only detect obstacles but also identify them and predict their immediate trajectories using advanced algorithms.
What types of analysis are typically used to transform AV data into actionable information?
For autonomous vehicles using DDS requires subsystems to be in place. Analysis in each databus include sensing such as cameras, data fusion and localization as well as situation awareness, planning,vehicle control and visualization. This data is typically stored and searched for to give results in real-time and react to what may come.
What factors define the cloud and edge platforms used to integrate AV?
Using DDS and a databus it is able to share data in real-time. Along with DDS, tools such as administrative console, monitoring and excel add-in gives it more functionality. Services and utilities including web integration service, replay service, code generator and more. Finally, having security and safety.
How is data obtained by the AV System?
DDS which utilizes a databus rather than a database. With a databus users can filter through a database and receive results in real-time. Having a data bus is preferable because of the filtration. Since autonomous vehicles uses sensors to collect data, the central computing system must filter the large amounts of data and deliver it reliably. , there is an extensive amount of data being collected.
What volume of data is expected from each deployment and AV as a whole?
Since there are huge amounts of data being collected through sensors, users can expect 100 terabytes of data collected per day.
What other requirements define AV data behavior?
With DDS collecting and filtering data, autonomy architecture patterns is another requirement to share that data. Each architecture design serves a different type of data behavior. The architectural decision is usually made before any component or application designs.
What business challenges could impact AV deployment?
Safety and security. Businesses continue to face this obstacle and must find a solution. Traditionally security like system edge security firewall and gaps were used but they are easy to overcome. Potential solutions like Rogue Prospect or whitelisting can lock down a host but it doesn’t do anything about networking. If a network level security is in place, then the data flow is disturbed. Hence, security is a challenge that must be designed through architecture.
What integration challenges could impact AV deployment?
Testing which components are important. Approaching how can companies can reuse the IP and the vehicle as one whole ecosystem.
What installation challenges could impact AV deployment?
A primary challenge for installing AV is deciding on the architectural design of the system. Once a design is issued, it is difficult to modify or replace it.
|p: +86 21 6010 5085 (ext 188) m: +86
156 0183 9705
a: 338 Nanjing West Road, Shanghai 200003 China
e: email@example.com w: www.iotone.com
twitter: @IoTONEHQ linkedin: IoT ONE