Technology peripherals
AI
First there was Tesla, then there was Xpeng. Is the advanced driver assistance system still worthy of trust?
First there was Tesla, then there was Xpeng. Is the advanced driver assistance system still worthy of trust?
On August 11, 2022, a video went viral on the Internet. Two people got off the car and stopped in the innermost lane. One person was squatting behind the car, and the other was preparing to place a tripod to warn cars coming from behind. A Xiaopeng P7 suddenly rushed forward and knocked one of them away.
It is understood that at that time, the owner of the Xpeng P7 turned on the advanced assisted driving function and the vehicle speed was 80km/h. However, the vehicle did not detect anyone in front of it when danger was about to occur. Hit it straight. The car owner said that when driving advanced assisted driving before, there would be an early warning, but this time there was no prompt and he was distracted at the time.
Xpeng Motors responded after the accident: "After verification, on the afternoon of August 10, Ningbo A vehicle owner drove a vehicle and collided with a person checking for vehicle failure ahead, resulting in casualties. We feel sad and sorry for the victims who unfortunately passed away in this accident. Currently, the traffic police department has opened a case to handle it, and the store has gone to the scene as soon as possible to assist. . We will fully cooperate with relevant departments in the accident investigation, continue to follow up on the follow-up results, and assist customers in handling follow-up related matters." On August 9, 2022, Dan O'Dowd, CEO of Green Hills Software, posted a post on the social platform about Tesla FSD review video, which stated that Tesla’s FSD autopilot system repeatedly hit a child dummy model during testing.
Dan O'Dowd said: "We are very disturbed by the safety test results of Tesla FSD and this should be a call for action. Elon Musk says Tesla FSD software is amazing, but it is not. It is a mortal threat to all Americans."
Additionally, those who participated in the test According to the test report: Tesla has been tested dozens of times in the past month. Before hitting the mannequin, although the car slowed down a little, it still hit the speed of more than 25 miles per hour. and crushed the mannequin. It said that during operation, the Tesla started at a speed of 40 miles per hour and drove 100 yards in the designated lane before hitting the mannequin. Some netizens joked: Is there a possibility that it is because he knows that it is a dummy.
Neither Xpeng nor Tesla can ensure that the advanced assisted driving system can ensure driving safety at all times. In the accident of Xiaopeng P7, we discovered that the car owner was distracted when using the vehicle. That is to say, when the accident occurred, the car owner was not fully devoted to the driving process. There is great trust in the assisted driving system, which is also the main reason for this accident.
With the popularization of advanced assisted driving systems and partially autonomous driving systems in vehicles, more and more car owners are embracing the early adopter mentality to experience the changes in travel brought about by technological innovations. , for models such as Tesla, every software update will attract the attention of many car owners and bloggers, and will also arouse great pursuit in the automotive circle and autonomous driving followers. The more widely the technology is popularized, the more its problems are revealed. Every accident caused by advanced assisted driving systems/autonomous driving systems will attract great attention from society and trigger discussions again and again. Advanced assisted driving systems Is it really safe? Do self-driving systems really deserve our trust?
The advanced assisted driving system can participate in the driver's driving behavior while the driver is driving the car. The advanced assisted driving system has also experienced the transition from assisting driving to participating in driving. stage.
In the process of assisted driving, the main function of the advanced assisted driving system is to monitor road conditions. When possible dangers are detected, the system uses the vibration and sound of the steering wheel to The prompts and flashing lights remind the driver, allowing the driver to avoid possible dangers in time.
In the Participation in driving stage, the advanced assisted driving system becomes a participant in the trip and can control the steering wheel, brake pedal, Fine-tuning the accelerator pedal can make the driver's driving behavior safer and comply with driving standards, making the driving process safer.
As advanced assisted driving systems participate in an increasing proportion of driving behavior, in some scenarios such as highways where the road environment is single and congestion may be less, advanced assisted driving systems have already The driving process can be completed alone. With the addition of lane keeping assist, adaptive cruise and other functions, driving on the highway can be completely completed by the vehicle itself, and the driver only needs to pay attention to the road conditions. This phenomenon is gradually becoming a reality.
In the advertisements of many new car-making forces, the performance of advanced assisted driving systems is also highlighted. Many traditional car-making companies are also keeping up with the pace of new car-making forces and will become more and more popular. More and more advanced driver assistance systems are being added to cars. Cars have also transformed from being a travel tool into an intelligent hardware device that integrates travel, entertainment, and interaction.
The development of advanced assisted driving systems and autonomous driving technology is booming, but during the development process, few people pay attention to the dangers that advanced assisted driving systems bring to us. The dangers here mainly refer to the function dangers and the usage dangers.
Function Danger As the name suggests, it is whether the advanced assisted driving system can ensure that it functions in all scenarios. Just like in the accident of the Xpeng P7, after turning on the advanced assisted driving system, the vehicle will provide early warning when danger occurs. However, in this accident, the Xpeng P7 did not respond in time. The occurrence of this accident has caused many consumers to Autonomous driving enthusiasts have begun to doubt whether advanced assisted driving systems are safe enough. This will undoubtedly make many autonomous driving enthusiasts doubt the safety of advanced assisted driving systems and affect the popularity of advanced assisted driving systems.
Danger of useIt is mainly aimed at users of advanced assisted driving systems. Many consumers are using advanced assisted driving systems. After the system appeared, they were extremely willing to try it out and feel the changes brought about by the technology. When first starting to use advanced assisted driving, in addition to experiencing the changes brought by the advanced assisted driving system, they will also pay attention to the road conditions. However, as the advanced assisted driving system is used more and more frequently, users will also develop a sense of advanced assisted driving. The driving system is very safe and basically eliminates the illusion of observing the road conditions, which can easily lead to danger.
In the accident of Xiaopeng P7, we can know that the car owner has used the advanced assisted driving system many times, and there have been dangers before, but the advanced assisted driving system noticed and reminded The car owner. During this driving process, the car owner was distracted, whether because of something to deal with or because of his trust in the advanced assisted driving system. But what we can know is that the car owner’s trust in the advanced assisted driving system has become a driving habit. , in the driving habits of car owners, the advanced assisted driving system will definitely remind you when danger occurs, and occasional distractions will not cause problems.
When consumers have great trust in advanced assisted driving systems and even use advanced assisted driving systems to a high degree during travel, this raises great questions about the safety of advanced assisted driving systems. requirements, but the current advanced assisted driving system cannot completely guarantee 100% accuracy. When many companies promote advanced assisted driving, they will also remind passengers to pay attention to the road conditions. Even many vehicles need to turn on the advanced assisted driving function. The driver keeps his hands on the steering wheel to ensure he can take over extremely quickly if danger arises.
The development of technology cannot fully take into account the changes in human nature. With the deepening of the use of advanced assisted driving systems, consumers can easily rely on advanced assisted driving systems to handle the entire travel process. Therefore, some people have asked whether it is necessary for the development of autonomous driving to directly skip the transition stage of advanced assisted driving systems and wait until fully autonomous driving is realized before launching fully autonomous vehicles into the market.
However, the development of autonomous driving cannot be separated from the continuous learning of large amounts of data. The emergence of advanced assisted driving systems will be inevitable. As consumers, we can only pay attention to road conditions when using advanced assisted driving systems and avoid developing bad habits. Only by fully trusting the driving habits of the advanced assisted driving system can you better enjoy the convenience brought by the technology while the advanced assisted driving system is developing. As consumers, we also need to understand what autonomous driving is and what advanced assisted driving is, and we cannot mistake advanced assisted driving for autonomous driving. We must remember: There are levels of autonomous driving, and travel safety is no small matter !
The above is the detailed content of First there was Tesla, then there was Xpeng. Is the advanced driver assistance system still worthy of trust?. For more information, please follow other related articles on the PHP Chinese website!
Hot AI Tools
Undresser.AI Undress
AI-powered app for creating realistic nude photos
AI Clothes Remover
Online AI tool for removing clothes from photos.
Undress AI Tool
Undress images for free
Clothoff.io
AI clothes remover
Video Face Swap
Swap faces in any video effortlessly with our completely free AI face swap tool!
Hot Article
Hot Tools
Notepad++7.3.1
Easy-to-use and free code editor
SublimeText3 Chinese version
Chinese version, very easy to use
Zend Studio 13.0.1
Powerful PHP integrated development environment
Dreamweaver CS6
Visual web development tools
SublimeText3 Mac version
God-level code editing software (SublimeText3)
Hot Topics
Why is Gaussian Splatting so popular in autonomous driving that NeRF is starting to be abandoned?
Jan 17, 2024 pm 02:57 PM
Written above & the author’s personal understanding Three-dimensional Gaussiansplatting (3DGS) is a transformative technology that has emerged in the fields of explicit radiation fields and computer graphics in recent years. This innovative method is characterized by the use of millions of 3D Gaussians, which is very different from the neural radiation field (NeRF) method, which mainly uses an implicit coordinate-based model to map spatial coordinates to pixel values. With its explicit scene representation and differentiable rendering algorithms, 3DGS not only guarantees real-time rendering capabilities, but also introduces an unprecedented level of control and scene editing. This positions 3DGS as a potential game-changer for next-generation 3D reconstruction and representation. To this end, we provide a systematic overview of the latest developments and concerns in the field of 3DGS for the first time.
How to solve the long tail problem in autonomous driving scenarios?
Jun 02, 2024 pm 02:44 PM
Yesterday during the interview, I was asked whether I had done any long-tail related questions, so I thought I would give a brief summary. The long-tail problem of autonomous driving refers to edge cases in autonomous vehicles, that is, possible scenarios with a low probability of occurrence. The perceived long-tail problem is one of the main reasons currently limiting the operational design domain of single-vehicle intelligent autonomous vehicles. The underlying architecture and most technical issues of autonomous driving have been solved, and the remaining 5% of long-tail problems have gradually become the key to restricting the development of autonomous driving. These problems include a variety of fragmented scenarios, extreme situations, and unpredictable human behavior. The "long tail" of edge scenarios in autonomous driving refers to edge cases in autonomous vehicles (AVs). Edge cases are possible scenarios with a low probability of occurrence. these rare events
Choose camera or lidar? A recent review on achieving robust 3D object detection
Jan 26, 2024 am 11:18 AM
0.Written in front&& Personal understanding that autonomous driving systems rely on advanced perception, decision-making and control technologies, by using various sensors (such as cameras, lidar, radar, etc.) to perceive the surrounding environment, and using algorithms and models for real-time analysis and decision-making. This enables vehicles to recognize road signs, detect and track other vehicles, predict pedestrian behavior, etc., thereby safely operating and adapting to complex traffic environments. This technology is currently attracting widespread attention and is considered an important development area in the future of transportation. one. But what makes autonomous driving difficult is figuring out how to make the car understand what's going on around it. This requires that the three-dimensional object detection algorithm in the autonomous driving system can accurately perceive and describe objects in the surrounding environment, including their locations,
This article is enough for you to read about autonomous driving and trajectory prediction!
Feb 28, 2024 pm 07:20 PM
Trajectory prediction plays an important role in autonomous driving. Autonomous driving trajectory prediction refers to predicting the future driving trajectory of the vehicle by analyzing various data during the vehicle's driving process. As the core module of autonomous driving, the quality of trajectory prediction is crucial to downstream planning control. The trajectory prediction task has a rich technology stack and requires familiarity with autonomous driving dynamic/static perception, high-precision maps, lane lines, neural network architecture (CNN&GNN&Transformer) skills, etc. It is very difficult to get started! Many fans hope to get started with trajectory prediction as soon as possible and avoid pitfalls. Today I will take stock of some common problems and introductory learning methods for trajectory prediction! Introductory related knowledge 1. Are the preview papers in order? A: Look at the survey first, p
SIMPL: A simple and efficient multi-agent motion prediction benchmark for autonomous driving
Feb 20, 2024 am 11:48 AM
Original title: SIMPL: ASimpleandEfficientMulti-agentMotionPredictionBaselineforAutonomousDriving Paper link: https://arxiv.org/pdf/2402.02519.pdf Code link: https://github.com/HKUST-Aerial-Robotics/SIMPL Author unit: Hong Kong University of Science and Technology DJI Paper idea: This paper proposes a simple and efficient motion prediction baseline (SIMPL) for autonomous vehicles. Compared with traditional agent-cent
Let's talk about end-to-end and next-generation autonomous driving systems, as well as some misunderstandings about end-to-end autonomous driving?
Apr 15, 2024 pm 04:13 PM
In the past month, due to some well-known reasons, I have had very intensive exchanges with various teachers and classmates in the industry. An inevitable topic in the exchange is naturally end-to-end and the popular Tesla FSDV12. I would like to take this opportunity to sort out some of my thoughts and opinions at this moment for your reference and discussion. How to define an end-to-end autonomous driving system, and what problems should be expected to be solved end-to-end? According to the most traditional definition, an end-to-end system refers to a system that inputs raw information from sensors and directly outputs variables of concern to the task. For example, in image recognition, CNN can be called end-to-end compared to the traditional feature extractor + classifier method. In autonomous driving tasks, input data from various sensors (camera/LiDAR
FisheyeDetNet: the first target detection algorithm based on fisheye camera
Apr 26, 2024 am 11:37 AM
Target detection is a relatively mature problem in autonomous driving systems, among which pedestrian detection is one of the earliest algorithms to be deployed. Very comprehensive research has been carried out in most papers. However, distance perception using fisheye cameras for surround view is relatively less studied. Due to large radial distortion, standard bounding box representation is difficult to implement in fisheye cameras. To alleviate the above description, we explore extended bounding box, ellipse, and general polygon designs into polar/angular representations and define an instance segmentation mIOU metric to analyze these representations. The proposed model fisheyeDetNet with polygonal shape outperforms other models and simultaneously achieves 49.5% mAP on the Valeo fisheye camera dataset for autonomous driving
nuScenes' latest SOTA | SparseAD: Sparse query helps efficient end-to-end autonomous driving!
Apr 17, 2024 pm 06:22 PM
Written in front & starting point The end-to-end paradigm uses a unified framework to achieve multi-tasking in autonomous driving systems. Despite the simplicity and clarity of this paradigm, the performance of end-to-end autonomous driving methods on subtasks still lags far behind single-task methods. At the same time, the dense bird's-eye view (BEV) features widely used in previous end-to-end methods make it difficult to scale to more modalities or tasks. A sparse search-centric end-to-end autonomous driving paradigm (SparseAD) is proposed here, in which sparse search fully represents the entire driving scenario, including space, time, and tasks, without any dense BEV representation. Specifically, a unified sparse architecture is designed for task awareness including detection, tracking, and online mapping. In addition, heavy
