Autonomous vehicles tested in California. Bosch and Daimler are accelerating the city’s development of fully automated and autonomous driving (SAE Level 4/5) and are firmly establishing the path. The partners have picked California as the first test fleet’s pilot site.
Table of Contents
“Driverless driving” is being tested in California
Bosch and Daimler have been offering clients a shuttle service with driverless cars on specified routes in a Californian city since the second half of 2019. The test fleet and the app-based mobility service are operated by Daimler Mobility Services.
The goal of the pilot project is to show how mobility services like vehicle sharing (car2go), ride-hailing (mytaxi), and multi-modal platforms (moovel) can be intelligently linked to define the future of mobility. In addition, as part of their control unit network, the partners have chosen US tech specialist Nvidia as the provider of the artificial intelligence platform.
The partners’ tradition in innovation is the backbone of the project
Bosch and Daimler are collaborating on the development of a driving system for fully automated and driverless cars, relying on their decades of automotive experience to bring mature and safe ideas to market.
“The decisive factor is to introduce a safe, dependable and mature system,” says Dr Michael Hafner, Head of Automated Driving at Daimler AG. “Safety has the highest priority, and is the constant theme of all aspects and development stages on our way to the start of series production. If in doubt, thoroughness comes before speed.”
“Developing automated driving to a level ready for series production is like a decathlon”, according to Dr Stephan Hönle, Senior Vice President Business Unit Automated Driving at Robert Bosch GmbH. “It’s not enough to be good in one or two areas. Like us, you have to master all disciplines. Only then will we succeed in bringing automated driving to the roads and the city safely.”
A plethora of sensors and power to read the data in an instant
As the old adage goes, four eyes are better than two. When it comes to completely autonomous, driverless driving, Bosch and Daimler depend on even more detecting elements: optical cameras, radar signals, ultrasound, and Lidar all detect the vehicle’s immediate and distant surroundings and assist it in navigating.
The sensors vary not just in terms of range and vehicle installation position. They all have distinct advantages due to technological considerations.
Only by combining data from all sensors, a process known as sensor fusion, can a model of the environment be created that meets Bosch and Daimler’s stringent safety criteria – a necessary prerequisite for fully autonomous, driverless driving, according to both firms. After all, the sensors must continually and in real-time monitor their surroundings.
The Automated Drive Controller (ADC), the fully automated, driverless vehicle’s core computer, makes choices and transmits orders to the in-vehicle actuators through the Motion Control Unit based on this data.
Daimler also has extremely specific specifications for actuators, including steering, acceleration, and braking: all important actuators and motion sensors, as well as the control units and power supply, must be replicated in a fully autonomous, driverless Mercedes-Benz. This implies the electronic steering system comprises not just two motors, but also duplicated power electronics.
The i-Booster from Bosch, an electromechanical brake booster, replaces the previously used pneumatic brake booster. When teamed up with the ESP system, a combined braking system is created that enables safe stopping even if separate components fail.
The actuators are controlled by a network of software modules spread over many control units. This not only performs the Motion Control Software’s directives, but also utilizes its own sensors to accurately and consistently track the vehicle’s motions and, if required, follow the specified course.
Extraneous variables like crosswinds, potholes, or an unexpectedly slick road surface are examples of what this entails. If there are no driving directions from the ADC or if they are improbable, it may also bring the car to a safe halt.
The system continually develops a halting route to which the remaining network might have access if required, much as a person utilizes the last vision of the situation when abruptly thrown into darkness.
Bosch and Daimler depend on a control unit network made up of multiple discrete control units for their driving system. The foundation necessary for this is provided by Nvidia, a US technology firm that can operate the Artificial Intelligence (AI) algorithms developed by Bosch and Daimler for the vehicle’s movement.
With radar, video, lidar, and ultrasonic technologies (sensor data fusion), the network of control units collects data from all sensors, assesses it in milliseconds, and plans the vehicle’s motions. The control unit network as a whole has a computational capacity of hundreds of trillions of operations per second.
Just a few years ago, a group of S-Class automobiles might achieve that speed.
California was the first testing ground
The control unit network will also be employed in Daimler and Bosch’s commercial cars, which hit Californian roads in the second half of 2019. Furthermore, both companies will provide consumers with an automated shuttle service on specific routes in a city in Silicon Valley’s San Francisco Bay.
The tests will reveal how fully automated and self-driving cars may be incorporated into a multi-modal transportation network. Many communities are confronted with a slew of issues that are straining the current transportation infrastructure. The goal of the tests is to demonstrate how this new technology may help solve these problems.
Autonomous cars could make urban mobility more appealing
With their development collaboration on fully automated and autonomous driving in urban areas, which started in April 2017, Bosch and Daimler want to improve traffic flow in cities, increase road safety, and lay the groundwork for the future of traffic. Among other things, the technology will increase the appeal of automobile sharing.
It will also enable users to make the most of their time in the car, as well as provide new mobility options for persons who do not have a driver’s license, for example.
The vehicle approaches the driver rather than the driver approaching the car. Users may easily request a car-sharing automobile or a vehicle that drives by without a driver inside a predetermined metropolitan region.
The project combines one of the world’s top premium manufacturers’ total vehicle and mobility knowledge with one of the world’s major suppliers’ systems and hardware expertise. The goal of the resulting synergies is to deliver the new technology early and well verified.