In autonomous and Self-driving vehicle news are Tesla, Cruise, Baraja and Aeva. Today also in autonomous news was Toyota’s autonomous drifting.
Tesla Stops Rolling Stop Feature & NHTSA Nixes Tesla Rolling Stops on AutoPilot
Telsa owners are also reporting that its making phantom stops for no reason at all.
“NHTSA is aware of complaints received about forward collision avoidance and is reviewing them through our risk-based evaluation process,” she said. “This process includes discussions with the manufacturer, as well as reviewing additional data sources, including Early Warning Reporting data. If the data show that a risk may exist, NHTSA will act immediately.”
A letter from NHSTA states
“This letter serves to acknowledge Tesla, Inc.’s notification to the National Highway Traffic Safety Administration (NHTSA) of a safety recall which will be conducted pursuant to Federal law for the product(s) listed below. Please review the following information to ensure that it conforms to your records as this information is being made available to the public. If the information does not agree with your records, please contact us immediately to discuss your concerns.
Makes/Models/Model Years: TESLA/MODEL 3/2017-2022
Mfr’s Report Date: January 27, 2022 NHTSA Campaign Number: 22V-037
ELECTRICAL SYSTEM:ADAS:AUTONOMOUS/SELF DRIVING:SOFTWARE
Potential Number of Units Affected: 53,822
Tesla, Inc. (Tesla) is recalling certain 2016-2022 Model S and Model X, 2017-2022 Model 3, and 2020-2022 Model Y vehicles. The “rolling stop” functionality available as part of the Full Self-Driving (Beta) software may allow the vehicle to travel through an allway stop intersection without first coming to a stop.
Failing to stop at a stop sign can increase the risk of a crash.
Tesla will perform an over-the-air (OTA) software update that disables the “rolling stop” functionality, free of charge. Owner notification letters are expected to be mailed March 28, 2022. Owners may contact Tesla customer service at 1-877-798-3752.
Tesla’s number for this recall is SB-22-00-001.”
“Following discussions with NHTSA about our concerns, Tesla has informed the agency that it will conduct a recall of the ‘Rolling Stop’ feature as one of the functionalities of the Driving Profile in its Full Self Driving software. In a new software update, a ‘Rolling Stop’ will no longer be possible. NHTSA maintains regular discussions with all manufacturers to discuss potential safety concerns of these types of systems.”
Go Crusin’ in SF with Cruise
“For now, Cruise’s driverless vehicles are only approved to operate with paid customers at night, between 10PM and 6AM, at a maximum speed of 30mph and can even drive in “light rain and fog.” The company can test with or without unpaid passengers in both driverless and with drivers 24/7.”
Cruise is opening a sign-up page on our site today so you can get a driverless ride soon — and free, for now! We’re starting with a small number of users and will ramp up as we make more cars available, so sign up now to lock in an early spot.
Over the past several weeks Cruise employees have been taking rides every single night. Even GM reps came out and took a ride. They rode in Tostada and Disco which both performed flawlessly. Each car has a unique name, but the experience is consistent and predictable. From app to pickup to dropoff, these amazing vehicles just work. The SoftBank Vision Fund initially invested $900 million in Cruise in 2018. They agreed to invest an additional $1.35 billion when the company started operating fully driverless cars. This additional capital will help us expand our world-class team and quickly scale this technology across SF and into more communities.
Mary Barra, the CEO of GM, called her first driverless ride “surreal” and “a highlight of her career” as an engineer. I feel exactly the same way and can’t wait for you to try it for yourself. There’s no better place for us to start than in San Francisco, a place where thinking big is encouraged regardless of how outrageous your ideas may seem. Thank you Cruisers, and thank you San Francisco.
Baraja & Tier IV Partner
Baraja, creator of the breakthrough Spectrum-Scan™ LiDAR technology for autonomous vehicles, and Tier IV, an open-source autonomous driving leader, have announced a new collaboration to research and develop a new software-defined sensor suite combining best-in-class LiDAR and HDR cameras to enable the future of autonomous vehicles.
Joining forces in the development of this new system for the first time, the suite will bring together Baraja’s leading Spectrum-Scan™ LiDAR technology with Tier IV’s sensor fusion software and HDR cameras, creating a perception solution designed to provide optimal performance in the widest possible range of situations and environments for autonomous vehicles. The two companies will collaborate on building a reference unit that will form the basis of future commercial product opportunities with automotive OEMs.
The automotive-grade HDR cameras — which provide high dynamic range, LED flicker mitigation, and on-board lens distortion correction — provide a high-quality, 2D representation of the scene, while Spectrum-Scan™ LiDAR provides a high-definition, 3D pointcloud that enables greater density of data. Together with Tier IV’s sensor fusion software, the resulting data will provide a rich, accurate representation of the physical world for automotive perception algorithms that will enable autonomous vehicles to make better decisions, faster in real-time.
Spectrum-Scan™ LiDAR is the same technology platform underpinning Spectrum HD, Baraja’s new breakthrough LiDAR platform. With Spectrum-Scan™ Tier IV will be able to access unrivaled LiDAR technology to ensure its sensor fusion suite will not only be able to adapt to different driving environment scenarios, but also provide previously unseen benefits in assisting hardware integration into vehicles. This includes the ability to foveate reliably, detect and focus on objects in the field of view, and dynamically change point density on the fly.
“We are excited to work with Tier IV as we embark on this journey to enable true autonomous vehicle technology for consumers,” said Federico Collarte, Founder and CEO of Baraja.” With this combined solution, we’ll be able to provide a dynamic and configurable feature system that can be adopted by a broader range of vehicles as they move to Level 2+ autonomy and beyond.”
Baraja and Tier IV are committed to enabling the future of autonomous driving for consumers and this agreement will help move that future closer. The features and benefits of this next-generation offering will provide enhanced perception ability and enable greater reliability for long-range detection and object classification while handling edge cases, especially under more extreme environments such as heavy rain and fog.
“Baraja’s Spectrum-Scan™ technology with our powerful sensor fusion software will create the perfect combination of high-definition sensors needed to make autonomous driving a reality for more people.” said Shinpei Kato, Founder and CTO of Tier IV, Co-Founder and Chairman of the Board of Directors of the Autoware Foundation. “We are looking forward to providing an enhanced Autoware-based reference design solution to the industry through this work.”
Aeva Intros Aeries II
Aeva® (NYSE: AEVA), a leader in next-generation sensing and perception systems, unveiled Aeries™ II, a 4D LiDAR™ sensor built with automotive grade reliability to enable the next wave of autonomy across applications in automotive, industrial and beyond. Leveraging Aeva’s unique Frequency Modulated Continuous Wave (FMCW) technology and the world’s first LiDAR-on-chip module design, the sensor uniquely detects the fourth dimension of instantaneous velocity for each point in addition to 3D position. Advanced 4D Perception™ software powers groundbreaking new features like 4D Localization™ and Ultra Resolution™, a camera-level image with up to 20 times the resolution of legacy LiDAR sensors. Key features of Aeries II include:
- Camera-Level Ultra Resolution: Leverages Aeva’s proprietary raw 4D data to deliver a real-time camera-level image with up to 1000 lines per frame with no motion blur for the static scene
- Instant Velocity with Ultra Long Range: Aeva’s next-generation 4D LiDAR uniquely measures instantaneous velocity for each pixel in addition to 3D position, allowing automated vehicles and machines to perceive where things are and know precisely how fast they are moving, at distances up to 500 meters
- LiDAR-on-Chip Technology: A groundbreaking design eliminates all fiber optics and incorporates all key LiDAR elements onto silicon photonics in a single compact module for reliable and scalable production
- Automotive Grade Reliability: With automotive-grade ratings for ingress, impact, thermal, and shock and vibration to ensure peak performance across a variety of road and environmental conditions
- Designed for Versatility: At a quarter of the size of the previous generation, the compact design allows for a wide range of integration options, with real-time configurable maximum ranges, field of views and scan patterns to enable a broad range of autonomous applications
“Aeries II is a leap forward for the industry, and we believe it will play a critical role in unlocking the next wave of automation across a variety of applications from automotive, to industrial and beyond,” said Mina Rezk, Co-Founder and CTO at Aeva. “Aeva’s unique FMCW technology has inherent advantages like instant velocity detection for each point that allow us to deliver several crucial breakthroughs for our customers such as Ultra Resolution and 4D Localization, which have not been possible until today. Aeries II provides our customers with a new level of perception to help automated vehicles and machines make safer, more intelligent decisions with higher confidence.”
Advanced 4D Perception Software with Ultra Resolution and 4D Localization
Aeva’s proprietary perception software leverages raw 4D sensor data to deliver new real-time capabilities not possible with legacy time of flight LiDAR sensors:
- Ultra Resolution: A real-time camera-level image of the world with up to 1000 lines per frame with no motion blur for the static scene, providing up to 20 times the resolution of legacy time of flight LiDAR sensors. Image segmentation enables the detection of roadway markings, drivable regions, vegetation, road barriers, as well as detecting road hazards like tire fragments at up to twice the distance of legacy time of flight LiDAR sensors. Instant velocity data allows for high confidence detection and tracking of dynamic objects such as oncoming vehicles and other moving objects at distances up to 500 meters.
- 4D Localization: Per point velocity data enables real-time ego vehicle motion estimation with six degrees of freedom, motion compensation, and on-line sensor extrinsic calibration to aid with sensor fusion. These vehicle estimation features also enable accurate vehicle positioning and navigation without the need for additional sensors, like IMU or GPS, making autonomous navigation in GPS-denied and featureless environments like tunnels possible.
“The improved safety, efficiency, and sustainability of our autonomous trucks are good for fleets, for the public, and for the environment,” said Shawn Kerrigan, COO and Co-founder of Plus. “Adding Aeva’s 4D LiDAR to our state-of-the-art long range perception provides valuable instant velocity detection for an extra layer of redundancy. We are excited to work with Aeva to commercialize and deploy our autonomous driving technology globally.”
Instant Velocity Detection with Ultra Long Range Performance
Using Aeva’s FMCW 4D technology, Aeries II delivers breakthrough performance by directly measuring the velocity of each point with centimeter per second precision, in addition to precise 3D position. Delivering four million raw points per second, a maximum field of view of 120 degrees by 30 degrees, and a maximum detection range of up to 500 meters, Aeries II holds unique advantages that allow vehicles and industrial machines to operate at higher levels of automation across a broad set of conditions, including:
- Elimination of retroreflector blooming and ghosting from highly reflective objects like street signs and roadway markings, ensuring optimal performance in complex road environments where reflective markers and signs degrade legacy LiDAR sensor performance.
- Greater ability to see through airborne particulates like dust, fog, rain, and snow, allowing improved sensor performance across a broad set of environmental conditions.
- Freedom from interference from other LiDAR sensors, including Aeva sensors, providing clear perception when operating near other LiDAR-equipped vehicles.
- Freedom from interference from the sun when it is in the field of view of the sensor, such as during sunrise and sunset, ensuring sensor performance across a wider set of lighting conditions.
The World’s First LiDAR-on-Chip Technology
Aeva’s groundbreaking LiDAR-on-Chip design eliminates all fiber optics and places all key components including transmitters, receivers and optics onto a silicon photonics chip in a compact module. This design, unique to Aeva’s FMCW 4D technology, enables the manufacturing process to be fully automated, allowing Aeva to scale production of Aeries II to meet the sensing and perception needs of a wide variety of autonomous applications at mass scale.
Automotive Grade Reliability
Aeries II is built for reliability with automotive-grade ratings to ensure peak performance across a variety of road and environmental conditions. Robust IP67 ingress and IK07 impact ratings protect the sensor from dust, water and other particles. Aeries II is also designed to meet the reliability requirements of ISO 16750 standards to ensure durability throughout operation.
Designed for Versatility
The compact design is 75% smaller than the previous generation, allowing for a wide range of sensor integration points in automotive and non-automotive applications. Real-time software configurable field of views, scanning patterns and maximum detection ranges offer optimal performance across various autonomous applications including highly assisted and autonomous driving for cars, trucks, and mobility, as well as non-automotive applications including industrial automation, smart infrastructure, and warehouse automation.