Autonomy promises the perfect driver for every car

Automated and autonomous driving promises many benefits in terms of road safety, user experience and vehicle fuel economy. Today, developers are looking to apply it to every use case imaginable, from mining applications and yard tractors to city taxis and heavy trucks.

The ideal driver is not a person

Fusion Processing boasts that it can “autonomize a vehicle of any size, be it electric, hybrid or internal combustion.” The company’s CAVstar control system acts as the brain of the unmanned vehicle, relying on data from camera, radar and LiDAR sensors. The controller processes the data to create a picture of the vehicle’s environment and plan a safe route ahead. “With autonomous vehicle (AV) technology, we can put the perfect driver in every car,” comments Jim Fleming, director of marketing at Fusion Processing.

An ideal driver does not fall asleep at the wheel and is not distracted by his mobile phone. This will also avoid speeding and unnecessary sudden braking. For fleets operating on a thin margin, these improvements can mean significant savings. “We have car manufacturers reporting a 25 percent difference in fuel consumption between the best and worst drivers in their fleet,” Fleming says. Automotive world. “This is a huge cost savings waiting to be realized with our AV technologies. It can also offer the manufacturer a smaller battery, larger payload or longer range.”

The technology developer has automated a range of vehicles, including small electric vehicles such as the Renault Twizy, off-road electric pods, 12m buses for Stagecoach and a 9m minibus for First Group. His main focus today is on SAE Level 4 commercial vehicle applications.

This includes buses. The CAVstar system is currently proving its worth in the CAVForth autonomous bus pilot in Scotland, where it allows buses to travel autonomously on pre-selected roads. “Later in 2022, we expect two bus operators to launch passenger services using different vehicles, but both types of vehicles will be equipped with our CAVStar system,” says Fleming.

For this project, Fusion Processing provided the complete installation, including sensors, antennas and processors, and worked with vehicle manufacturers and their key suppliers to include redundancy for steering, braking and transmission systems. “We pride ourselves on being more than just a software provider,” he clarifies. “Yes, we use all our own software, but we also design the processing and sensor hardware to create the most optimized, low-latency system possible. This is evident not only in the very high performance levels we achieve, but also in how heat and power consumption is kept to a minimum, eliminating the need for things like forced air cooling, making it easier to achieve automotive-level reliability.”

Trucks

The company is also looking to show that its technology can be used effectively in trucks. “We’re interested in automated center-to-center transportation, automated warehouses, automated logistics centers and store-to-consumer delivery systems,” adds Fleming. Fusion has two new projects in these segments that will be announced in September 2022. “The introduction of autonomous technology in trucking is full of opportunities,” he emphasizes.

The company expects the emergence of two different modes of operation in the field of autonomous cargo transportation. One of them has a driver in the cockpit, but with an accompanying audio system that can guide the car on certain parts of the route, such as on motorways. Even this limited application can have a significant impact on the fleet. “Truck operations have the added complexity of driver hours,” notes Fleming. However, with an automated system, the entire operation could be optimized so that trucks are never idled on the side of the road because drivers have reached their hourly limit.

In the second promising operational model, the driver is not in the cockpit, but in a remote operations center. This remote driver will work efficiently in the office and not on the road. The job involves monitoring more than one vehicle with the need to intervene only when necessary, such as when a derailment or collision occurs. “This type of vehicle would greatly improve aerodynamics and fuel economy and reduce the weight of the tractor, which could lead to increased payload or range,” says Fleming.

Platoon

Fusion is also exploring platoon applications. Platooning uses connected technology and automated driving to connect two or more trucks in a convoy. By automatically maintaining a set short distance from each other during sections of the journey, both trucks can reduce fuel consumption. This arrangement can also ease the burden on drivers and improve traffic flow on the road.

The UK Government’s HelmUK project was first announced in August 2017 and only recently completed. Supported by Highways England and led by TRL, the aim was to operate a platoon of trucks on motorways in a vibrant commercial environment. Fusion Processing was one of the project partners along with DAF, Ricardo and DHL. His role in the project was to measure and analyze the location and movement of other vehicles around the platoon, in addition to recoding data from the platoon’s vehicles regarding speed, position, fuel consumption and vehicle condition. “Fusion’s system allows us to accurately measure the position of different vehicles of road users around the platoon and classify them by type, effectively measuring how drivers of different types of vehicles behave around the platoon in different conditions,” explains Fusion CEO Jim Hutchinson. .

Data is a central focus of HelmUK and project partners are collecting information to support several research objectives. These include providing security and cyber security evidence about drivers, other vehicles and V2V communications; quantification of environmental benefits regarding vehicle fuel consumption and emissions; assessment of commercial compatibility; infrastructure impact assessment and traffic management; and informing standards and regulatory bodies.

By analyzing some of the data, Fusion was able to indicate where there might have been safety issues, such as sudden braking by one of the surrounding vehicles. To achieve this, Fusion added its own radar and camera sensors to each of the platoon’s vehicles and accessed CAN bus data from the truck’s own systems. This spectrum of information was processed by CAVstar control units installed on the vehicle. As Hutchinson explains, each type of sensor—radar, LiDAR, and camera—brings different advantages and different limitations. “We have always been interested in the possibilities of combining information flows from different types of sensors; that’s why we’re called Fusion Processing,” he says.

What’s next?

Notably, Platoon is not a program for fully autonomous driving. Hutchinson notes that for SAE Level 4 and 5 automated control, where human intervention is not possible, “it’s important to be able to rely on the sensor data, and if a sensor component fails, the system can detect it and have sufficient redundancy. built in to ensure it can maneuver itself into a safe state.”

Moving forward, Fusion will be ramping up its Level 4 autonomous operation in commercial applications. “The media often focuses on autonomous passenger cars, but we believe commercial vehicles will be the first to be commercialized,” says Fleming. “The commercial vehicle fleet is professionally managed and technology that offers increased safety, lower fuel costs, lower tire emissions, lower operating costs and improved optimization of driver hours and vehicle use will be very compelling.”