The Latest Version of Tesla's Autopilot Can Read Speed Limit Signs, Along with Other New Features
【Summary】Tesla vehicles with the latest version of Autopilot get a new feature called “Speed Assist” which uses the vehicle’s cameras to detect speed limit signs to improve the accuracy of speed limit data on local roads, Tesla announced.
Tesla's Autopilot autonomous driving system has always been a work in progress, with over-the-air updates pushed out to Tesla's vehicles as they are developed. The latest update to Autopilot is version 2020.36, which started rolling out just a few days ago. It includes the ability to recognize speed limits signs, according to the release notes.
Tesla's incremental software updates are the first of their kind in the auto industry and is one of the technologies that sets Tesla apart from other automakers, as well as its robust autonomous driving capabilities.
A Tesla vehicle with the latest version of Autopilot gets a new feature called "Speed Assist" which uses the vehicle's cameras to detect speed limit signs to improve the accuracy of speed limit data on local roads, Tesla said.
Detected speed limit signs are displayed in the driving visualization and used to set the associated speed limit warning. Drivers can also fine tune the Speed Assist settings to their personal preferences.
At the March 2018 Scaled Machine Learning Conference at Stanford University, Tesla's director of AI and Autopilot Andrey Karpathy spoke about the planned rework of Tesla's "Full Self Driving" feature, which places much more emphasis on improving road sign detection.
The rework of Autopilot is made possible by Tesla's new and more powerful self-driving processor that was custom built in-house to better support partially autonomous and fully autonomous driving. Tesla began shipping all of its vehicles with the new processor beginning in April 2019.
All Tesla vehicles produced after April 2019 now have the hardware needed in the future for full self-driving in almost all circumstances, according to the company. The automaker believes its future autonomous driving systems will be at least twice as good as the average human driver.
Tesla said its new processor is roughly 20 times more powerful than the computer previously by Nvidia, which allows Tesla to vastly improve its self driving features. The new processor is supported by 8 external cameras, radar and 12 ultrasonic sensors on the vehicle.
Speaking at Tesla's 2019 Q4 earnings call in February, Chief Executive Elon Musk commented, "We're really only beginning to take full advantage of the Autopilot hardware, the FSD hardware. The apparent progress as seen by consumers will seem to be extremely rapid, but actually what's really going on... is having the foundational software be very strong."
Green Traffic Signal Recognition
In addition to the Speed Limit Warning updates, Tesla latest software will notify the driver when a traffic signal turns green.
According to Tesla, "A chime will play when the traffic light you are waiting for turns green. If you are waiting behind another car, the chime will play once the car advances unless Traffic-Aware Cruise Control or Autosteer is active. When Traffic Light and Stop Sign Control is activated, a chime will play when you can confirm to proceed through a green traffic light."
The audible chime when a traffic light turns green will help distracted drivers from being caught off guard when the light changes. The update is available for Tesla vehicles in the U.S., Australia, Canada and New Zealand.
German automaker Audi also introduced a similar system in 2018 in ten U.S. cities. In February, Audi announced that the German city of Düsseldorf became the second European city after Ingolstadt where drivers can use Audi's Traffic Light Information service.
Tesla also pushed out an update to its Traffic-Aware Cruise Control (TACC) system. Drivers can now quickly set the speed to the current speed by simply tapping the cluster speedometer. However like before, drivers are still able to tap the speed limit icon to adjust the set speed to the speed limit.
When TACC is engaged, a Tesla vehicle will adjust its speed based on the vehicle traveling directly in front, decelerating and accelerating as needed. This feature is available only to customers who have Autopilot hardware installed in their vehicles and it's only available for vehicles in the U.S.
Tesla's Autopilot was originally marketed as a "hands free" autonomous driving system, the first in the auto industry for a production model. However, after a series of fatalities involving Tesla's vehicle navigating on Autopilot, the company made changes, instructing owners to keep their hands on the wheel at all times and pay attention to the road ahead.
Tesla has incorporated a system that monitors the steering angle, detecting subtle changes that are designed to make sure a drivers hands are on the wheel. If no steering input is detected the system automatically disables itself requiring the driver to take back full control.
Tesla's website now includes a warning that reads, "the currently enabled (Autopilot) features require active driver supervision and do not make the vehicle autonomous."
Other existing features of Autopilot include Navigate on Autopilot, which provides active guidance from highway on-ramp to off-ramp; Summon, which automatically retrieve the car from parking spot; Autopark, which automatically performs parallel and perpendicular parking maneuvers, with a single touch; and Auto Lane Change, a system for overtaking slower traffic by automatically changing lanes on the highway.
Upcoming features to Autopilot include Autosteer on city streets. That system is currently only available on highways and major secondary roads.
For added safety, all Tesla vehicles come standard with advanced driver assistance (ADAS) features such as emergency braking, collision warning and blind-spot monitoring.
Earlier this year, security firm McAfee discovered serious flaws in Telsa's forward facing cameras, particularly in how machine learning software detects common speed limit signs.
McAfee called its experiment "Model Hacking" which is the concept of exploiting weaknesses in machine learning algorithms to achieve adverse results. Tesla's cruise control system uses machine learning for image recognition, primarily to identify road signs.
McAfee stressed that the experiment was not to discredit Tesla or its former partner Mobileye, an Isreali-based company owned by Intel that developed the camera Tesla used for its image recognition software. Rather, the researchers were trying to highlight the vulnerability of such systems so Tesla could make improvements, which the company has done.
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
- Here’s How Waymo Uses Hyper-Local Weather Data to Improve the Capabilities of its Self-Driving Vehicles
- SiLC Technologies Launches its Eyeonic Vision System, a LiDAR Sensor That Can Identify Objects up to 1 Kilometer Away
- Qualcomm Ventures Invests in ThunderX, a Company Developing a Domain Controller-based Intelligent Vehicle Compute Platform
- The Tesla Model Y and Model 3 Take the 1st and 2nd Place Spots in the Annual Cars.com ‘American-Made Index’
- Qualcomm Technologies and Renault Group to Jointly Develop a Centralized, Software-Defined Vehicle Architecture for the Automaker’s Future Electric Models
- Mazda Outlines Plans to Invest $10.6 Billion in Electric and Hybrid Vehicle Development Through 2030
- Tesla Believes Its Dojo AI System Will Help It Win the Self-Driving Car Race
- GM’s New Blazer EV Will Take on the Tesla Model Y Performance and Ford Mustang Mach E
- BorgWarner Invests $500 Million in Wolfspeed Inc, a Developer of Semiconductors and Silicon Carbide Devices for Electric Vehicles
- Audi Rebrands its Premium Car Rental Service to ‘Audi on demand’