作者：
An, XiaoqiZhao, LinGong, ChenLi, JunYang, JianPCA Lab
Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology China
With the rapid development of autonomous driving, LiDAR-based 3D Human Pose Estimation (3D HPE) is becoming a research focus. However, due to the noise and sparsity of LiDAR-captured point clouds, robust human pose es...
详细信息
In 5G, network functions can be scaled out/in dynamically to adjust the capacity for network slices. The scale-out/-in procedure, namely autoscaling, enhances performance by scaling out instances and reduces operation...
详细信息
Providing quality healthcare services and promoting collaborative clinical research are easier and more efficient with electronic medical record (EMR) systems. All aspects of care are included in electronic health rec...
详细信息
Vision-based state estimation is challenging in underwater environments due to color attenuation, low visibility and floating particulates. All visual-inertial estimators are prone to failure due to degradation in ima...
Vision-based state estimation is challenging in underwater environments due to color attenuation, low visibility and floating particulates. All visual-inertial estimators are prone to failure due to degradation in image quality. However, underwater robots are required to keep track of their pose during field deployments. We propose robust estimator fusing the robot's dynamic and kinematic model with proprioceptive sensors to propagate the pose whenever visual-inertial odometry (VIO) fails. To detect the VIO failures, health tracking is used, which enables switching between pose estimates from VIO and a kinematic estimator. Loop closure implemented on weighted posegraph for global trajectory optimization. Experimental results from an Aqua2 Autonomous Underwater Vehicle field deployments demonstrates the robustness of our approach over different underwater environments such as over shipwrecks and coral reefs. The proposed hybrid approach is robust to VIO failures producing consistent trajectories even in harsh conditions.
Secondary control of voltage magnitude and frequency is essential to the stable and secure operation of microgrids (MGs). Recent years have witnessed an increasing interest in developing secondary controllers based on...
Secondary control of voltage magnitude and frequency is essential to the stable and secure operation of microgrids (MGs). Recent years have witnessed an increasing interest in developing secondary controllers based on multi-agent reinforcement learning (MARL), in order to replace existing model-based controllers. Nonetheless, unlike the vulnerabilities of model-based controllers, the vulnerability of MARLbased MG secondary controllers has so far not been addressed. In this paper, we investigate the vulnerability of MARL controllers to false data injection attacks (FDIAs). Based on a formulation of MG secondary control as a partially observable stochastic game (POSG), we propose to formulate the problem of computing FDIAs as a partially observable Markov decision process (POMDP), and we use state-of-the-art RL algorithms for solving the resulting problem. Based on extensive simulations of a MG with 4 distributed generators (DGs), our results show that MARL-based secondary controllers are more resilient to FDIAs compared to state of the art model-based controllers, both in terms of attack impact and in terms of the effort needed for computing impactful attacks. Our results can serve as additional arguments for employing MARL in future MG control.
Intrinsic motivation plays a key role in learning how to use tools, a fundamental aspect of human cultural evolution and child development that remains largely unexplored within the context of Reinforcement Learning (...
Intrinsic motivation plays a key role in learning how to use tools, a fundamental aspect of human cultural evolution and child development that remains largely unexplored within the context of Reinforcement Learning (RL). This paper introduces “object empowerment” as a novel concept within this realm, showing its role as information-theoretic intrinsic motivation that underpins tool discovery and usage. Using empowerment, we propose a new general framework to model the utilization of tools within RL. We explore how maximizing empowerment can expedite the RL of tasks involving tools, highlighting its capacity to solve the challenge posed by sparse reward signals. By employing object empowerment as an intrinsically motivated regulariser, we guide the RL agent in simple grid-worlds towards states beneficial for learning how to master tools for efficient task completion. We will show how object empowerment can be used to measure and compare the effectiveness of different tools in handling an object. Our findings indicate efficient strategies to learn tool use and insights into the integration and modeling of tool control in the context of RL.
Nowadays, secure and reliable management of logistics is highly needed. Logistics is the delivery of goods from producers to legitimate consumers in accurate amounts and good conditions. The use of low-capable sensor ...
详细信息
Nowadays, secure and reliable management of logistics is highly needed. Logistics is the delivery of goods from producers to legitimate consumers in accurate amounts and good conditions. The use of low-capable sensor nodes in smart logistics makes it vulnerable to many security threats. Smart logistics necessitated the delivery of suitable information to the authorized person at the appropriate time and place, which is only feasible with a stable infrastructure. This paper presents an authentication scheme together with blockchain technology to provide a secure supply chain management system. The presented authentication mechanism is based on standard KERBOROS scheme which is a ticket-based scheme. The scheme is evaluated by BAN logic which shows that it is an effective scheme in terms of improved response time and encryption/decryption time along with key generation time.
One of the most prevalent and disabling of the numerous disabilities is blindness. Based on the World Health Organization (WHO), there are 285 million blind people worldwide. Among them, 39% of the population is total...
One of the most prevalent and disabling of the numerous disabilities is blindness. Based on the World Health Organization (WHO), there are 285 million blind people worldwide. Among them, 39% of the population is totally blind. Individuals encounter a myriad of challenges regularly, especially when they undertake independent journeys from one place to another. Oftentimes, people heavily depend on the support and aid of others to fulfill their daily requirements. Therefore, implementing a technological solution to assist them poses a considerable challenge. So, an effective method like a machine learning algorithm is suggested as a remedy for such individuals. The essential data input is gathered using a method called image classification in order to access machine learning algorithms. The items around where blind persons are located include-with a camera, the surroundings of blind persons are photographed as images. It is capable of accurately detecting every object within a certain range. The visuals are then transformed into aural signals to give the blind persons practical means of assistance. This also generates alerts if they are far or very close to the object.
This paper investigates the problem of zero-day malicious software (Malware) detection through unsupervised deep learning. We built a sequence-to-sequence auto-encoder model for learning the behavior of normal softwar...
详细信息
We propose a digital twin agent that constructs elderly digital twins by digitally transforming daily life of the elderly. We developed the digital twin agent as an avatar run on a smartwatch. The digital twin agent p...
详细信息
暂无评论