Continental Develops a ‘Road AND Driver' Camera System for Autonomous Vehicles
【Summary】Global auto parts supplier Continental AG developed what it calls a “Road AND Driver” camera for automated vehicles that monitors both the driver and traffic in front of the vehicle. The dual-camera system continuously detects whether a driver is paying attention to the road, while at the same time monitors the vehicle's surroundings.
Although self-driving cars have not officially arrived yet, many automakers are working on Level 3 autonomy and advanced driver assist systems (ADAS), which handle some of the driving tasks, such as keeping the vehicle centered in a highway lane or automatically keeping up with the flow of traffic. Tesla's Autopilot feature is one example.
Global auto parts supplier Continental AG has developed what it calls a "Road AND Driver" camera, that monitors both the driver and traffic in front of the vehicle. The dual-camera system continuously detects whether the driver is paying attention to the road, while also monitoring the surroundings.
Continental says the camera provides a holistic model of the environment and is a prerequisite for the safe deployment self-driving vehicles.
The challenge for automakers is designing a system for a vehicle that is partially automated, but still allows a human driver to quickly take over in certain situations. To achieve this, both a view of the road ahead and passenger cabin is required, according to Continental.
The Road AND Driver camera is located behind the windshield of the vehicle, above the rear-view mirror and faces the driver. It's installed at the same location as existing forward-facing cameras in newer vehicles. The secondary lens is aimed at the road ahead and provides the data for the vehicle's ADAS.
The camera data is continuously evaluated by software, and shows for example, whether the driver is attentive, distracted or is looking at a smartphone. The interior camera can also detect direction of the driver's gaze and if their hands are on the steering wheel.
The software can determine if driver is ready to take over. If not, the vehicle will not suddenly try to hand over control, creating an additional layer of safety. In addition to conventional computer vision processing, neural networks are used that can be scaled to match the robustness of the available hardware, according to Continental.
"Thanks to the new camera system, vehicle and driver are constantly aware of one another. Ultimately, this comes down to trust. The human can rest assured that the technology will not abruptly hand back responsibility without warning, but that this will take place according to clear and comprehensible criteria," says Georg Binder, Head of Strategy & Planning, Advanced Driver Assistance System business unit at Continental.
Distraction, fatigue, or forgetting about small children or sleeping babies in the backseat of a vehicle are also risks that can be minimized by Continental's new camera system.
According to Continental, automated driving will be possible only when the transition between "automated" and "manual" driving modes is safe and reliable. Drivers must be able to trust that the vehicle will hand over responsibility only when they are ready to accept it.
Cameras combined with lidar and radar are becoming an integral part of the sensor suite for autonomous vehicles. The latest generation of vehicle cameras have excellent, better than human night vision capabilities and high image resolution along with a 125-degree field of view, enabling cross-traffic objects to be detected even earlier at intersections.
The data from the interior camera is not only evaluated for the safe transfer of driving functions. With the aid of a "Occupant Safety Monitor" it can also be used to adapt passive safety systems such as seatbelts and airbags to the prevailing situation. The deployment of airbags, for example, can be tailored to the situation detected in the interior in order to optimize its protective effect.
An important aspect of the Road AND Driver camera is that the data is evaluated frame by frame, but is not recorded, eliminating concerns about data privacy over what is captured inside the vehicle.
"The focus is solely on interpreting the prevailing situation in the vehicle in order to increase the safety of the occupants and other road users," says Andreas Forster, Next Generation Technology manager in Continental's Passive Safety & Sensorics business unit.
Series production of the "Road AND Driver" camera is planned for 2021, around the same time The first automated vehicles are expected to be on the roads, equipped with camera systems to monitor the road and the interior.
Originally hailing from New Jersey, Eric is a automotive & technology reporter covering the high-tech industry here in Silicon Valley. He has over 15 years of automotive experience and a bachelors degree in computer science. These skills, combined with technical writing and news reporting, allows him to fully understand and identify new and innovative technologies in the auto industry and beyond. He has worked at Uber on self-driving cars and as a technical writer, helping people to understand and work with technology.
Ford is Testing a New Robotic Charging Station to Assist Drivers of EVs With Disabilities
Ford Raises the Prices of the F-150 Lightning Electric Pickup Due to Rising Raw Material Costs
The BMW 7-Series to Feature HD Live Maps From HERE Technologies for Hands-Free Highway Driving in North America at Speeds up to 80 MPH
AutoX to Use the 'Eyeonic Vision Sensor' from California-based SiLC Technologies for its Robotaxi Fleet in China
LG Develops ‘Invisible’ Speaker Sound Technology That Could Revolutionize In-Vehicle Audio
Researchers at South Korea’s Chung-Ang University Develop a ‘Meta-Reinforcement’ Machine Learning Algorithm for Traffic Lights to Improve Vehicle Throughput
Zeekr’s New 009 Electric Passenger Van is the World’s First EV to Feature CATL’s Advanced ‘Qilin’ Battery With a Range of 510 Miles
Redwood Materials is Building an Electric Vehicle Battery Recycling Facility in South Carolina
- Apple Reveals the Next-Gen Version of CarPlay, Which Takes Over a Vehicle’s Entire Dashboard and Screens
- SiLC Technologies Launches its Eyeonic Vision System, a LiDAR Sensor That Can Identify Objects up to 1 Kilometer Away
- NHTSA Upgrades Tesla's Autopilot Investigation to 'Engineering Analysis'
- Michigan-based May Mobility Closes on $111 Million Funding Round, Begins Development on Toyota’s Next-Gen Commercial Autonomous Vehicle Platform
- Volkswagen’s Software Unit CARIAD Selects Innoviz as its Direct Lidar Supplier for the Automaker's Future Software-Defined Vehicles
- NHTSA Opens Investigations Into Two New Fatal Tesla Accidents
- EV Charging Provider Electrify America Raises $450 Million, Siemens to Become a Minority Shareholder
- China’s Baidu Reveals the Apollo RT6, a Fully Autonomous, Production Ready Level-4 Robotaxi with Removable Steering Wheel
- Tesla's Battery Supplier CATL Unveils its New ‘Qilin’ Battery That Can Deliver 600+ Miles of Range to EVs
- Construction of Panasonic’s New EV Battery Factory in Kansas to Start in November