[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124422-en":3,"doc-seo-124422-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},124422,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",6,"Technology","Human-In-The-Loop Machine Learning for Safe and Ethical Autonomous Vehicles - Principles, Challenges, and Opportunities","Rapid advances in machine learning are reshaping autonomous vehicles by enabling perception, hazard prediction, and navigation optimization, yet full autonomy in cluttered, complex environments remains difficult and labeling costs limit progress. Human-In-The-Loop (HITL-ML) integrates human creativity, ethical judgment, and emotional intelligence to strengthen robustness and effectiveness. The work reviews HITL-ML methods for AVs, including curriculum learning, HITL reinforcement learning, and active learning, then emphasizes embedding ethical principles into AV behavior and outlines future research directions.","Human-In-The-Loop Machine Learning for Safe and Ethical Autonomous Vehicles: Principles, Challenges, and Opportunities  \nYousef Emami, Member, IEEE, Luis Almeida, Senior Member, IEEE, Kai Li, Senior Member, IEEE, Wei Ni, Fellow Member, IEEE, and Zhu Han, Fellow Member, IEEE,  \narXiv :2408 . 12548v2 [ cs .LG] 8 Sep 2024  \nAbstract—Rapid advances in Machine Learning (ML) have triggered new trends in Autonomous Vehicles (AVs). ML algorithms play a crucial role in interpreting sensor data, predicting potential hazards, and optimizing navigation strategies. However, achieving full autonomy in cluttered and complex situations, such as intricate intersections, diverse sceneries, varied trajectories, and complex missions, is still challenging, and the cost of data labeling remains a significant bottleneck. The adaptability and robustness of humans in complex scenarios motivate the inclusion of humans in the ML process, leveraging their creativity, ethical power, and emotional intelligence to improve ML effectiveness. The scientific community knows this approach as Human-In-The-Loop Machine Learning (HITL-ML). Towards safe and ethical autonomy, we present areview of HITL-ML for AVs, focusing on Curriculum Learning (CL), Human-In-The-Loop Reinforcement Learning (HITL-RL), Active Learning (AL), and ethical principles. In CL, human experts systematically train ML models by starting with simple tasks and gradually progressing to more difficult ones. HITL-RL significantly enhances the RL process by incorporating human input through techniques like reward shaping, action injection, and interactive learning. AL streamlines the annotation process by targeting specific instances that need to be labeled with human oversight, reducing the overall time and cost associated with training. Ethical principles must be embedded in AVs to align their behavior with societal values and norms. In addition, we provide insights and specify future research directions.  \nIndex Terms—Human-In-The-Loop, Machine Learning, Curriculum Learning, Reinforcement Learning, Active Learning, Ethical Principles, Autonomous Vehicles, Unmanned Aerial Vehicles  \nI. INTRODUCTION  \nRecent developments in Autonomous Vehicles (AVs) have been useful in improving efficiency and safety [1] . AVs have ushered in a substantial transformation in terms of automation and connectivity. The global AVs market size was valued at USD 1,500.3$ billion in 2022 and is projected to grow from USD 1,921.1$ billion in 2023 to USD 13,632.4$ billion by 2030 [2] . Commercially envisioned and available self-driving cars can perform functions such as lane-changing, highway driving, and autonomous parking by sensing the environment using built-in technologies [3] . Ground-based autonomous systems can be paired with aerial ones to drive a significant advancement in transportation and technology and offer a range of exciting possibilities, including surveillance, monitoring, traffic management, remote sensing, and autonomous control [4] [5] .  \nCopyright (c) 2024 IEEE. Personal use of this material is permitted. However, permission to use this material for any other purposes must be obtained from the IEEE by sending a request to [pubs-permissions@ieee.org](pubs-permissions@ieee.org).  \nTABLE I: List of Acronyms  \n\n| Acronym | Definition |\n| --- | --- |\n| AD | Autonomous Driving |\n| AL | Active Learning |\n| AUV | Autonomous Underwater Vehicle |\n| AVs | Autonomous Vehicles |\n| CNN | Convolutional Neural Network |\n| CL | Curriculum Learning |\n| CPSs | Cyber-Physical Systems |\n| CV | Connected Vehicle |\n| DDPG | Deep Deterministic Policy Gradients |\n| DL | Deep Learning |\n| DQN | Deep-Q-Network |\n| DRL | Deep Reinforcement Learning |\n| EVs | Electric Vehicles |\n| HITL | Human-In-The-Loop |\n| MDP | Markov Decision Process |\n| ML | Machine Learning |\n| MLR | Multiple Linear Regression |\n| PPO | Proximal Policy Optimization |\n| RL | Reinforcement Learning |\n| SVM | Support Vector Machine |\n| SVR | Support Vector Re","cbCailTmzcreSiZN","https://ap.wps.com/l/cbCailTmzcreSiZN","pdf",6625787,1,16,"English","en",105,"# Introduction\n## Motivation and Background\n## Overview of HITL-ML Approaches\n## Ethical Principles and Future Directions","[{\"question\":\"为什么在自动驾驶中需要 Human-In-The-Loop 机器学习（HITL-ML）？\",\"answer\":\"在复杂、难以覆盖的场景中实现完整自动驾驶仍然困难，且数据标注成本高。HITL-ML通过引入人的创造力、伦理判断与情感智能来提升模型的鲁棒性与有效性。\"},{\"question\":\"文中重点回顾了哪些 HITL-ML 技术方向？\",\"answer\":\"主要包括课程学习（Curriculum Learning, CL）、人参与的强化学习（HITL-RL）以及主动学习（Active Learning, AL）。文中说明了各方法如何在训练与交互过程中提升安全性与效率。\"},{\"question\":\"HITL-RL 如何改善强化学习过程？\",\"answer\":\"通过将人类输入纳入强化学习，采用奖励塑形（reward shaping）、动作注入（action injection）与交互式学习等技术来增强学习过程。\"}]","Human-In-The-Loop Machine Learning for Safe and Ethical Autonomous Vehicles - Principles, Challenges, and Opportunities | PDF",1785822202,40,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"human-in-the-loop-machine-learning-for-safe-and-ethical-autonomous-vehicles-principles-challenges-and-opportunities","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/technology/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/human-in-the-loop-machine-learning-for-safe-and-ethical-autonomous-vehicles-principles-challenges-and-opportunities/124422/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"为什么在自动驾驶中需要 Human-In-The-Loop 机器学习（HITL-ML）？","Question",{"text":75,"@type":76},"在复杂、难以覆盖的场景中实现完整自动驾驶仍然困难，且数据标注成本高。HITL-ML通过引入人的创造力、伦理判断与情感智能来提升模型的鲁棒性与有效性。","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"文中重点回顾了哪些 HITL-ML 技术方向？",{"text":80,"@type":76},"主要包括课程学习（Curriculum Learning, CL）、人参与的强化学习（HITL-RL）以及主动学习（Active Learning, AL）。文中说明了各方法如何在训练与交互过程中提升安全性与效率。",{"name":82,"@type":73,"acceptedAnswer":83},"HITL-RL 如何改善强化学习过程？",{"text":84,"@type":76},"通过将人类输入纳入强化学习，采用奖励塑形（reward shaping）、动作注入（action injection）与交互式学习等技术来增强学习过程。","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,113,117,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":111,"slug":112},50,"technology",{"id":114,"doc_module":4,"doc_module_name":46,"category_name":115,"show_sort_weight":29,"slug":116},7,"Healthcare","healthcare",{"id":118,"doc_module":4,"doc_module_name":46,"category_name":119,"show_sort_weight":120,"slug":121},8,"Research & Report",30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]