想像一下，只需告訴您的車輛，“我很著急”，它就會自動帶您走上最有效的路線，到達您需要去的地方。工程師發現，自動駕駛汽車 （AV） 可以在 ChatGPT 或其他聊天機器人的説明下做到這一點，這些聊天機器人由稱為大型語言模型的人工智慧演算法實現。
Imagine simply telling your vehicle, “I’m in a hurry,” and it automatically takes you on the most efficient route to where you need to be.
想像一下，只需告訴您的車輛“我很著急”，它就會自動帶您走上最有效的路線，到達您需要去的地方。
Purdue University engineers have found that an autonomous vehicle (AV) can do this with the help of ChatGPT or other chatbots made possible by artificial intelligence algorithms called large language models.
普渡大學的工程師發現，自動駕駛汽車 （AV） 可以在 ChatGPT 或其他聊天機器人的説明下做到這一點，這些聊天機器人由稱為大型語言模型的人工智慧演算法實現。
The study, to be presented Sept. 25 at the 27th IEEE International Conference on Intelligent Transportation Systems, may be among the first experiments testing how well a real AV can use large language models to interpret commands from a passenger and drive accordingly.
這項研究將於 9 月 25 日在第 27 屆 IEEE 智慧交通系統國際會議上發表，可能是測試真實自動駕駛汽車使用大型語言模型來解釋乘客命令並據此駕駛的首批實驗之一。
Ziran Wang, an assistant professor in Purdue’s Lyles School of Civil and Construction Engineering who led the study, believes that for vehicles to be fully autonomous one day, they’ll need to understand everything that their passengers command, even when the command is implied. A taxi driver, for example, would know what you need when you say that you’re in a hurry without you having to specify the route the driver should take to avoid traffic.
領導這項研究的普渡大學萊爾斯土木與建築工程學院助理教授 Ziran Wang 認為，要讓車輛有一天完全自動駕駛，它們需要理解乘客命令的一切，即使命令是隱含的。例如，當您說您很匆忙時，計程車司機會知道您需要什麼，而無需指定司機應該走的路線以避免交通擁堵。
Although today’s AVs come with features that allow you to communicate with them, they need you to be clearer than would be necessary if you were talking to a human. In contrast, large language models can interpret and give responses in a more humanlike way because they are trained to draw relationships from huge amounts of text data and keep learning over time.
儘管今天的 AV 具有允許您與它們通信的功能，但它們需要您比與人類交談時更清晰。相比之下，大型語言模型可以以更像人類的方式解釋和給出響應，因為它們經過訓練可以從大量文本數據中提取關係並隨著時間的推移不斷學習。
“The conventional systems in our vehicles have a user interface design where you have to press buttons to convey what you want, or an audio recognition system that requires you to be very explicit when you speak so that your vehicle can understand you,” Wang said. “But the power of large language models is that they can more naturally understand all kinds of things you say. I don’t think any other existing system can do that.”
“我們車輛中的傳統系統具有使用者介面設計，您必須按下按鈕才能傳達您想要的內容，或者音訊識別系統要求您在說話時非常明確，以便您的車輛能夠理解您，”Wang 說。“但大型語言模型的力量在於，它們可以更自然地理解你說的各種事情。我認為任何其他現有系統都無法做到這一點。
Conducting a new kind of study
開展新型研究
In this study, large language models didn’t drive an AV. Instead, they were assisting the AV’s driving using its existing features. Wang and his students found through integrating these models that an AV could not only understand its passenger better, but also personalize its driving to a passenger’s satisfaction.
在這項研究中，大型語言模型不會驅動AV。相反，他們正在使用AV的現有功能來輔助AV的駕駛。Wang 和他的學生發現，通過集成這些模型，自動駕駛汽車不僅可以更好地理解乘客，還可以個人化駕駛，讓乘客滿意。
Before starting their experiments, the researchers trained ChatGPT with prompts that ranged from more direct commands (e.g., “Please drive faster”) to more indirect commands (e.g., “I feel a bit motion sick right now”). As ChatGPT learned how to respond to these commands, the researchers gave its large language models parameters to follow, requiring it to take into consideration traffic rules, road conditions, the weather and other information detected by the vehicle’s sensors, such as cameras and light detection and ranging.
在開始實驗之前，研究人員使用提示來訓練 ChatGPT，這些提示範圍從更直接的命令（例如，“請快點開車”）到更間接的命令（例如，“我現在感覺有點暈動”）。隨著 ChatGPT 學習如何回應這些命令，研究人員為其大型語言模型提供了要遵循的參數，要求它考慮交通規則、道路狀況、天氣以及車輛感測器檢測到的其他資訊，例如攝像頭和光線檢測和測距。
The researchers then made these large language models accessible over the cloud to an experimental vehicle with level four autonomy as defined by SAE International. Level four is one level away from what the industry considers to be a fully autonomous vehicle.
然後，研究人員使這些大型語言模型可以通過雲訪問到 SAE International 定義的具有 4 級自動駕駛的實驗車輛。4 級與行業認為的全自動駕駛汽車相差一級。
When the vehicle’s speech recognition system detected a command from a passenger during the experiments, the large language models in the cloud reasoned the command with the parameters the researchers defined. Those models then generated instructions for the vehicle’s drive-by-wire system — which is connected to the throttle, brakes, gears and steering — regarding how to drive according to that command.
當車輛的語音辨識系統在實驗期間檢測到乘客的命令時，雲中的大型語言模型會根據研究人員定義的參數對命令進行推理。然後，這些模型為車輛的線控系統（連接到油門、制動器、齒輪和轉向系統）生成有關如何根據該命令駕駛的指令。
For some of the experiments, Wang’s team also tested a memory module they had installed into the system that allowed the large language models to store data about the passenger’s historical preferences and learn how to factor them into a response to a command.
在一些實驗中，Wang 的團隊還測試了他們安裝在系統中的記憶體模組，該模組允許大型語言模型存儲有關乘客歷史偏好的數據，並學習如何將它們分解為對命令的回應。
The researchers conducted most of the experiments at a proving ground in Columbus, Indiana, which used to be an airport runway. This environment allowed them to safely test the vehicle’s responses to a passenger’s commands while driving at highway speeds on the runway and handling two-way intersections. They also tested how well the vehicle parked according to a passenger’s commands in the lot of Purdue’s Ross-Ade Stadium.
研究人員在印第安那州哥倫布市的一個試驗場進行了大部分實驗，該試驗場曾經是機場跑道。這種環境使他們能夠在跑道上以高速行駛和處理雙向交叉路口時安全地測試車輛對乘客命令的回應。他們還測試了車輛在普渡大學羅斯-阿德體育場（Ross-Ade Stadium）停車場根據乘客的命令停放的情況。
The study participants used both commands that the large language models had learned and ones that were new while riding in the vehicle. Based on their survey responses after their rides, the participants expressed a lower rate of discomfort with the decisions the AV made compared to data on how people tend to feel when riding in a level four AV with no assistance from large language models.
研究參與者同時使用了大型語言模型學習的命令和在車輛中乘坐時的新命令。根據他們在騎行後的調查回復，與人們在沒有大型語言模型幫助的情況下乘坐 4 級 AV 時往往如何感受的數據相比，參與者對 AV 做出的決定的不適率較低。
The team also compared the AV’s performance to baseline values created from data on what people would consider on average to be a safe and comfortable ride, such as how much time the vehicle allows for a reaction to avoid a rear-end collision and how quickly the vehicle accelerates and decelerates. The researchers found that the AV in this study outperformed all baseline values while using the large language models to drive, even when responding to commands the models hadn’t already learned.
該團隊還將自動駕駛汽車的性能與根據人們平均認為安全舒適的乘坐數據創建的基線值進行了比較，例如車輛允許做出反應以避免追尾碰撞的時間，以及車輛加速和減速的速度。研究人員發現，本研究中的AV在使用大型語言模型進行駕駛時優於所有基線值，即使在回應模型尚未學習的命令時也是如此。
原文出處:https://www.sciencedaily.com/releases/2024/09/240916153501.htm