Re: [情報] Cruise L4自駕配備人類駕駛

看板car作者 (錢德勒)時間1月前 (2024/05/14 18:20), 1月前編輯推噓6(6019)
留言25則, 7人參與, 1月前最新討論串2/2 (看更多)
[自駕] 1. 兩套以上獨立的自駕系統(備援、冗餘) 2. 承1,兩套系統可以互相檢視比對,一旦發生失效,系統會自行偵測到失效 3. 失效後在人不介入(接管)的條件下仍能保持安全 4. 重新恢復運作需要靠人接管 [輔助] 1. 系統單一 2. 當系統做了錯誤判斷,沒有另一套機制,所以系統壓根不知道產生錯誤 3. 系統無法自行偵測失效 4. 全仰賴在駕駛座的駕駛人注意和隨時接管 像Waymo這類自駕車 駕駛方式很笨拙,在限定區域的開放道路運行仍有一堆bug問題(卡住、逆向) 這些bug失效無法預期哪時出現,但發生當下系統 1. 能偵測到失效 2. 在人尚未接管下保持安全性 簡單講就是滿足失效安全 直到人類接管並恢復運作 Criuse則是輾死前車撞飛的人,即便車能停下但無法確保安全性,被要求需要安全駕駛 FSD會在絕大多數(99.9%)的條件下駕駛方式更接近人類 但機器學習、AI不可能訓練到完美(可能餵越多數據反而造成某些場景應對退步) 所以當今天遇到那極低的0.1%情況 系統出錯但系統並不認為失效(也沒法偵測到失效) 就得全靠駕駛人判斷是否要立即介入接管 像是ISO 26262功能安全、ISO 21448預期功能安全(SOTIF)、FIT(Failures In Time) 這些都是政府核准自駕牌照的依據,之前也都提過了 ※ 引述《LimYoHwan (gosu mage)》之銘言: : https://tinyurl.com/bvkhn237 : 簡易翻譯: : Cruise公司表示,他們將恢復採用有安全駕駛員監督的自動駕駛模式。這是因為他們去年 : 發生的一起無人駕駛事故後,暫時停止了無人駕駛服務,並進行了全面的安全評估。 : 經過評估後,Cruise決定先恢復自動駕駛,但仍然會有安全駕駛員在車內監督。這可以在提 : 供自動駕駛功能的同時保證乘客安全。 : https://i.imgur.com/WVhDrCF.jpeg
: Cruise表示,這種監督式自動駕駛模式只是過渡階段,他們最終的目標仍然是實現完全無人 : 駕駛。此次事故顯示,即使是先進的自動駕駛技術,在實際運營中仍需要更謹慎的安全措施 : 。 : 齁,cruise配備這麼多感知設備,一堆光達,也有備援系統,且通過政府法規認證可以運 : 行無人計程車,啊 怎麼車上又放人了,那我可以認為「人」才是備援嗎?那些光達根本 : 沒屁用….. : 自駕的瓶頸是AI問題還是光達、硬體問題? : 車版大師表示? : Starting this week, Cruise AVs will begin supervised autonomous driving in Pho : enix as Cruise takes further steps towards returning to its driverless mission : . : For the past several weeks Cruise has been mapping and collecting road informa : tion in Phoenix. Now, we will validate our AV’s end-to-end behaviors against : our rigorous safety and AV performance requirements. During this phase, the Cr : uise vehicles will drive autonomously with a safety driver present behind the : wheel to monitor and take over if needed. : Supervised autonomous driving is a critical validation phase prior to driverle : ss deployment and builds on our extensive work in simulation, closed-course dr : iving and more than 5 million driverless miles previously driven by our fleet : to ensure safe performance on real-world roads and driving scenarios. Safety d : rivers play an important role in testing the AV’s performance and the continu : ous improvement of our technology. We’ll begin supervised autonomous driving : in the city of Phoenix and will gradually expand to Scottsdale, Paradise Valle : y, Tempe, Mesa, Gilbert and Chandler measured against predetermined safety ben : chmarks. : Safety is the defining principle for everything we do and continues to guide o : ur progress towards resuming driverless operations. From comprehensive vehicle : management before our AVs depart the garage to continuous driver monitoring a : nd roadworthiness of the vehicle, we deploy rigorous safety procedures, protoc : ols and performance requirements to ensure supervised autonomous operations ar : e safe for operation on public roads. : Our safety measures and procedures are multifaceted and can be grouped into th : ree pillars: : Product Safety: Cruise AVs are fully-integrated autonomous vehicles derived fr : om the Chevy Bolt EV platform, manufactured by General Motors, and tested to v : alidate that the vehicles meet all motor vehicle safety requirements after th : e addition and installation of Cruise AV hardware (sensors, etc.). We have pro : cedures in place to ensure our AVs are appropriately maintained and that new s : oftware is thoroughly tested and validated through a measured release process : prior to deploying to the fleet. : Operational Safety: We have documented procedures and protocols in place to en : sure the safety of our fleet operations for those in our vehicles and those we : share the road with, including driver training, ongoing performance managemen : t processes, and responsible scaling of operations. : Enterprise Safety: Safe operations start with a safety-focused culture, and ev : ery worker at Cruise is empowered and responsible for the safety of our produ : ct and operations. We enable safety culture through appropriate governance, po : licies, reporting mechanisms, and regular safety training. : We are committed to partnering with the communities we serve, so whether human : -driven or autonomous, we encourage any community member to report driving con : cerns to our Community Feedback portal. When a concern is submitted, we will i : nvestigate the claim and, as needed, take appropriate action. Our feedback for : m: getcruise.com/support-center : As we continue through this journey, we look forward to working with local com : munities to jointly achieve our shared mission of making transportation safer : for all. -- ※ 發信站: 批踢踢實業坊(ptt.cc), 來自: 114.34.222.29 (臺灣) ※ 文章網址: https://www.ptt.cc/bbs/car/M.1715682027.A.82B.html ※ 編輯: chandler0227 (114.34.222.29 臺灣), 05/14/2024 18:21:35

05/14 18:23, 1月前 , 1F
結論: 不太好?
05/14 18:23, 1F

05/14 18:27, 1月前 , 2F
FSD會越來越爛 其他廠牌的只會越來越進步
05/14 18:27, 2F

05/14 19:04, 1月前 , 3F
錢大文也是先推再看了啦~
05/14 19:04, 3F

05/14 19:34, 1月前 , 4F
好像不是你說呢捏
05/14 19:34, 4F

05/14 19:34, 1月前 , 5F

05/14 20:01, 1月前 , 6F
演算法就算聰明,但Sensor只有一套時,誤判就會車禍(演
05/14 20:01, 6F

05/14 20:02, 1月前 , 7F
算法完全信了),所以才一直要求要備援機制自我驗證,而
05/14 20:02, 7F

05/14 20:02, 1月前 , 8F
不是很相信自己的破攝影機就輾過去(躺著的貨櫃車表示:
05/14 20:02, 8F

05/14 20:02, 1月前 , 9F
其他廠商自知還不成熟,所以沒人敢明目張膽的大吹特吹
05/14 20:02, 9F

05/14 20:03, 1月前 , 10F
更沒人敢躲在Lv2放消費者去幫忙測試
05/14 20:03, 10F

05/14 20:36, 1月前 , 11F
類神經網路到底從訓練中學習得什麼真的不好驗證。AI算
05/14 20:36, 11F

05/14 20:36, 1月前 , 12F
圖1個frame 出錯人眼沒看到就算了,但自駕可會出人命
05/14 20:36, 12F

05/14 20:36, 1月前 , 13F
撞貨櫃就是兩套camera+radar 這特黑有夠不專業的 而且
05/14 20:36, 13F

05/14 20:36, 1月前 , 14F
多久以前 還是ap 不是fsd 笑死
05/14 20:36, 14F

05/14 20:38, 1月前 , 15F
你那邊還來得及all in nVDA
05/14 20:38, 15F

05/14 20:46, 1月前 , 16F
演算法要兩套 你大腦是不是也要兩個
05/14 20:46, 16F

05/14 20:57, 1月前 , 17F
其實無論你用哪種方案 都逃不了AI
05/14 20:57, 17F

05/14 20:58, 1月前 , 18F
掌握算力 就掌握AI 就掌握自駕
05/14 20:58, 18F

05/14 20:59, 1月前 , 19F
現在不走端到端AI 基本就是死路
05/14 20:59, 19F
E2E的確是因為特斯拉才開始廣泛被一般民眾知道 但畢竟也不是特斯拉首創或獨創 E2E背後關鍵是DRL(深度強化學習)技術 例如幾年前的圍棋AlphaGo就是用DQN結合蒙地卡羅法 DRL也很早大量應用在自駕感知 (但決策和控制模塊) 即便DRL有極大發展潛力,有效解決傳統模塊分層的諸多問題 但依舊存在實際應用安全跟缺乏可解釋性等問題 跟自駕車應用安全相關的: Mobileye提出的RSS(Responsibility-Sensitive Safety)安全模型 Nvidia提出的SFF(Safety Force Field)

05/14 20:59, 1月前 , 20F
Waymo cruise都一攤死水
05/14 20:59, 20F

05/14 21:00, 1月前 , 21F
Mobile eye 沒聲音 專注在賣車廠基本方案
05/14 21:00, 21F

05/14 21:00, 1月前 , 22F
對岸華為 還有一戰之力
05/14 21:00, 22F

05/14 21:01, 1月前 , 23F
解決自駕 最重要的就是算力
05/14 21:01, 23F
※ 編輯: chandler0227 (114.34.222.29 臺灣), 05/14/2024 22:14:37

05/15 00:34, 1月前 , 24F
自己做不好就全世界都不准做好XDDD
05/15 00:34, 24F

05/15 00:35, 1月前 , 25F
737MAX的case應該可以說明
05/15 00:35, 25F
文章代碼(AID): #1cGphhWh (car)
文章代碼(AID): #1cGphhWh (car)