When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey
East China University of Science and Technology（华东理工大学）；Oklahoma State University（俄克拉荷马州立大学）；Potsdam Institute for Climate Impact Research（波茨坦气候影响研究所）；Humboldt University of Berlin（柏林洪堡大学）
Chongzhen Zhang, Jianrui Wang, Gary G. Yen, Chaoqiang Zhao, Qiyu Sun, Yang Tang, Feng Qian, Jürgen Kurths
With widespread applications of artificial intelligence (AI), the capabilities of the perception, understanding, decision-making and control for autonomous systems have improved significantly in the past years. When autonomous systems consider the performance of accuracy and transferability, several AI methods, like adversarial learning, reinforcement learning (RL) and meta-learning, show their powerful performance. Here, we review the learning-based approaches in autonomous systems from the perspectives of accuracy and transferability. Accuracy means that a well-trained model shows good results during the testing phase, in which the testing set shares a same task or a data distribution with the training set. Transferability means that when a well-trained model is transferred to other testing domains, the accuracy is still good. Firstly, we introduce some basic concepts of transfer learning and then present some preliminaries of adversarial learning, RL and meta-learning. Secondly, we focus on reviewing the accuracy or transferability or both of them to show the advantages of adversarial learning, like generative adversarial networks (GANs), in typical computer vision tasks in autonomous systems, including image style transfer, image superresolution, image deblurring/dehazing/rain removal, semantic segmentation, depth estimation, pedestrian detection and person re-identification (re-ID). Then, we further review the performance of RL and meta-learning from the aspects of accuracy or transferability or both of them in autonomous systems, involving pedestrian tracking, robot navigation and robotic manipulation. Finally, we discuss several challenges and future topics for using adversarial learning, RL and meta-learning in autonomous systems.
Learning Invariant Representations has been successfully applied for reconciling a source and a target domain for Unsupervised Domain Adaptation. By investigating the robustness of such methods under the prism of the cluster assumption, we bring new evidence that invariance with a low source risk does not guarantee a well-performing target classifier. More precisely, we show that the cluster assumption is violated in the target domain despite being maintained in the source domain, indicating a lack of robustness of the target classifier. To address this problem, we demonstrate the importance o…
Tsinghua University（清华大学）；Xiamen University（厦门大学）；Tencent AI Lab（腾讯AI实验室）
Due to the high efficiency and less weather dependency, autonomous greenhouses provide an ideal solution to meet the increasing demand for fresh food. However, managers are faced with some challenges in finding appropriate control strategies for crop growth, since the decision space of the greenhouse control problem is an astronomical number. Therefore, an intelligent closed-loop control framework is highly desired to generate an automatic control policy. As a powerful tool for optimal control, reinforcement learning (RL) algorithms can surpass human beings' decision-making and can also be sea…
The objective of the first CARLA autonomous driving challenge was to deploy autonomous driving systems to lead with complex traffic scenarios where all participants faced the same challenging traffic situations. According to the organizers, this competition emerges as a way to democratize and to accelerate the research and development of autonomous vehicles around the world using the CARLA simulator contributing to the development of the autonomous vehicle area. Therefore, this paper presents the architecture design for the navigation of an autonomous vehicle in a simulated urban environment t…
Osaka University（大阪大学）；The University of Electro-Communications（电气通信大学）
To realize autonomous collaborative robots, it is important to increase the trust that users have in them. Toward this goal, this paper proposes an algorithm which endows an autonomous agent with the ability to explain the transition from the current state to the target state in a Markov decision process (MDP). According to cognitive science, to generate an explanation that is acceptable to humans, it is important to present the minimum information necessary to sufficiently understand an event. To meet this requirement, this study proposes a framework for identifying important elements in the …
The convergent laboratory: when AI reasoning, autonomous experiments, high performance and quantum computing reshape chemistry
Argonne National Laboratory（阿贡国家实验室）；The University of Chicago（芝加哥大学）；NVIDIA Corporation（英伟达公司）；Northwestern University（西北大学）；Lila Sciences, Inc.（Lila Sciences公司）；PsiQuantum（PsiQuantum公司）；University of Toronto（多伦多大学）；Vector Institute for Artificial Intelligence（向量人工智能研究所）
Generative AI Meets Future Cities: Towards an Era of Autonomous Urban Intelligence
Computer Science University of Kansas Lawrence USA；Department of Computer Science Virginia Tech Falls Church USA；Department of Geography \& the Environment University of Alabama Tuscaloosa USA；Queensland University of Technology Brisbane Australia；School of Computing；Augmented Intelligence Arizona State University Tempe USA；University of Kansas；University of Alabama；Queensland University of Technology；Arizona State University
Bahçeşehir University（巴赫切谢希尔大学）；University of Padua（帕多瓦大学）；Florida International University（佛罗里达国际大学）
In the past decades, the rise of artificial intelligence has given us the capabilities to solve the most challenging problems in our day-to-day lives, such as cancer prediction and autonomous navigation. However, these applications might not be reliable if not secured against adversarial attacks. In addition, recent works demonstrated that some adversarial examples are transferable across different models. Therefore, it is crucial to avoid such transferability via robust models that resist adversarial manipulations. In this paper, we propose a feature randomization-based approach that resists …
The Responsibility-Sensitive Safety (RSS) model offers provable safety for vehicle behaviors such as minimum safe following distance. However, handling worst-case variability and uncertainty may significantly lower vehicle permissiveness, and in some situations safety cannot be guaranteed. Digging deeper into Newtonian mechanics, we identify complications that result from considering vehicle status, road geometry and environmental parameters. An especially challenging situation occurs if these parameters change during the course of a collision avoidance maneuver such as hard braking. As part o…
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；University of New South Wales（新南威尔士大学）；Weizmann Institute of Science（魏茨曼科学研究所）；Princeton University（普林斯顿大学）；Southern University of Science and Technology（南方科技大学）；Shenzhen Research Institute of Trustworthy Autonomous Systems（深圳市可信自主系统研究院）；University of Macau（澳门大学）
Realizing human-like perception is a challenge in open driving scenarios due to corner cases and visual occlusions. To gather knowledge of rare and occluded instances, federated learning assisted connected autonomous vehicle (FLCAV) has been proposed, which leverages vehicular networks to establish federated deep neural networks (DNNs) from distributed data captured by vehicles and road sensors. Without the need of data aggregation, FLCAV preserves privacy while reducing communication costs compared with conventional centralized learning. However, it is challenging to determine the network res…
Autonomous game design, generating games algorithmically, has been a longtime goal within the technical games research field. However, existing autonomous game design systems have relied in large part on human-authoring for game design knowledge, such as fitness functions in search-based methods. In this paper, we describe an experiment to attempt to learn a human-like fitness function for autonomous game design in an adversarial manner. While our experimental work did not meet our expectations, we present an analysis of our system and results that we hope will be informative to future autonom…
Singapore University of Technology and Design（新加坡科技设计大学）
This letter proposes an edge learning-based offloading framework for autonomous driving, where the deep learning tasks can be offloaded to the edge server to improve the inference accuracy while meeting the latency constraint. Since the delay and the inference accuracy are incurred by wireless communications and computing, an optimization problem is formulated to maximize the inference accuracy subject to the offloading probability, the pre-braking probability, and data quality. Simulations demonstrate the superiority of the proposed offloading framework.
Autonomous Cyber Operations Gym for Training and Evaluating AI Models for Defence
CortAIx Labs, Thales Deutschland（Thales Deutschland CortAIx 实验室）；University of Osnabrück（奥斯纳布吕克大学）；Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院）；University of Ulm（乌尔姆大学）
Cyber-Physical Security and Safety of Autonomous Connected Vehicles: Optimal Control Meets Multi-Armed Bandit Learning
Centre for Wireless Communications (CWC), University of Oulu, Finland（奥卢大学无线通信中心（CWC））；WINLAB, Dept. of ECE, Rutgers University, New Brunswick, NJ, USA（罗格斯大学WINLAB，电子与计算机工程系，新泽西州新布朗斯维尔，美国）
When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Need
Sydney AI Centre, The University of Sydney（悉尼人工智能中心，悉尼大学）；School of Computer Science, Wuhan University（武汉大学计算机学院）；Department of Computer Science, Hong Kong Baptist University（香港 Baptist 大学计算机系）
