Empowered by the advanced 3D sensing, computer vision and AI algorithm, autonomous robotics provide an unprecedented possibility for close-up infrastructure environment inspection in an efficient and reliable fashion....
详细信息
The fundamental challenges for full-duplex(FD)relay networks are the self-interference cancellation(SIC)and the cooperative transmission design at the *** paper presents a practical amplify-and-forward(AF)FD one-way r...
详细信息
The fundamental challenges for full-duplex(FD)relay networks are the self-interference cancellation(SIC)and the cooperative transmission design at the *** paper presents a practical amplify-and-forward(AF)FD one-way relay scheme for orthogonal frequency division multiplexing(OFDM)transmission with multi-domain *** is found that the residual self-interference(SI)signals at the relay can be regarded as an equivalent multipath *** effects of the residual sI at the relay are incorporated into the equivalent end-to-end channel model,and the inter-block interference can be removed at the destination by using cyclic prefix(CP)*** on the equivalent multipath model,we present a solution for optimizing the amplification factor on the performance of signal-to-interference-plus-noise ratio(SINR)when the equivalent multipath length is longer than the ***,a practical one way FD relay network with 3 nodes is built and *** simulation and measured results verify the superior performance of the proposed scheme.
Large language models (LLMs) are revolutionizing numerous domains with their remarkable natural language processing (NLP) capabilities, attracting significant interest and widespread adoption. However, deploying LLMs ...
详细信息
ISBN:
(数字)9798331518493
ISBN:
(纸本)9798331518509
Large language models (LLMs) are revolutionizing numerous domains with their remarkable natural language processing (NLP) capabilities, attracting significant interest and widespread adoption. However, deploying LLMs in resource-constrained environments, such as edge computing and robotics systems without server infrastructure, while also aiming to minimize latency, presents significant challenges. Another challenge lies in delivering medical assistance to remote areas with limited healthcare facilities and infrastructure. To address this, we introduce RoboMed, an on-premise healthcare robot that utilizes compact versions of large language models (tiny-LLMs) integrated with LangChain as its backbone. Moreover, it incorporates automatic speech recognition (ASR) models for user interface, enabling efficient, edge-based preliminary medical diagnostics and support. RoboMed employs model optimizations to achieve minimal memory footprint and reduced latency during inference on embedded edge devices. The training process optimization involves low-rank adaptation (LoRA), which reduces the model's complexity without significantly impacting its performance. For fine-tuning, the LLM is trained on a diverse medical dataset compiled from online health forums, clinical case studies, and a distilled medicine corpus. This fine-tuning process utilizes reinforcement learning from human feedback (RLHF) to further enhance its domain-specific capabilities. The system is deployed on Nvidia Jetson development board and achieves 78% accuracy in medical consultations and scores 56 in USMLE benchmark, enabling an resource-efficient healthcare assistance robot that alleviates privacy concerns due to edge-based deployment, thereby empowering the community.
The built-in elastic autoscaling strategy of Kubernetes, a container cloud orchestration and management system, balances the relationship between application service quality and cluster resource usage by regularly mon...
详细信息
ISBN:
(数字)9798350353174
ISBN:
(纸本)9798350353181
The built-in elastic autoscaling strategy of Kubernetes, a container cloud orchestration and management system, balances the relationship between application service quality and cluster resource usage by regularly monitoring a single resource and comparing it with a set threshold to determine whether to scale up or down. However, the built-in strategy has the problems of incomplete evaluation of a single resource index, response delay and scaling jitter. To address the above problems, this paper uses an adaptive weighting algorithm to obtain a comprehensive prediction index based on long-range time multi-resource prediction sequences. This index is not only more comprehensive than a single index, but also measures the resource usage in the future time period, so that the adaptive comprehensive prediction index has the ability to more comprehensively measure the changes in application workload in the future time period. The experimental results show that the autoscaling strategy based on adaptive integrated resource forecast can effectively solve the problems of regulation lag and scaling jitter.
Given the importance of forests and their role in maintaining the ecological balance, which directly affects the planet, the climate, and the life on this planet, this research presents the problem of forest fire moni...
详细信息
The challenge of satellite stabilization, particularly for those with uncertain flexible dynamics, has become a pressing concern in control and robotics. These uncertainties, especially the dynamics of a third-party c...
详细信息
We report numerical results on solving linear-quadratic model predictive control (MPC) problems by exploiting graphics processing units (GPUs). The presented method reduces the MPC problem by eliminating the state var...
We report numerical results on solving linear-quadratic model predictive control (MPC) problems by exploiting graphics processing units (GPUs). The presented method reduces the MPC problem by eliminating the state variables and applies a condensed-space interior-point method to remove the inequality constraints in the KKT system. The final condensed matrix is positive definite and can be efficiently factorized in parallel on GPU/SIMD architectures. In addition, the size of the condensed matrix depends only on the number of controls in the problem, rendering the method particularly effective when the problem has many states but few inputs and moderate horizon length. Our numerical results for PDE-constrained problems show that the approach is an order of magnitude faster than a standard CPU implementation. We also provide an open-source Julia framework that facilitates modeling (***) and solution (***) of MPC problems on GPUs.
Acquiring contact patterns between hands and nonrigid objects is a common concern in the vision and robotics community. However, existing learning-based methods focus more on contact with rigid ones from monocular ima...
Photovoltaic (PV) systems are indispensable elements in clean energy production. Predicting PV power is crucial for optimizing system performance and ensuring grid stability. This paper investigates the performance of...
详细信息
ISBN:
(数字)9798350361025
ISBN:
(纸本)9798350361032
Photovoltaic (PV) systems are indispensable elements in clean energy production. Predicting PV power is crucial for optimizing system performance and ensuring grid stability. This paper investigates the performance of gradient boosting approaches, XGBoost and Catboost, in predicting PV power. Datasets recorded each minute, including weather data and power output from two distinct PV systems in Brisbane, Australia, are used in this study for evaluation. Results show that the XGBoost slightly outperformed Catboost and achieved good prediction performance. Also, the XGBoost output was interpreted using the Shapley additive interpretation (SHAP) method to identify the important factor impacting PV power prediction. Results confirm that solar radiation is the most important factor influencing the performance of photovoltaic systems, and the other weather variables have a weaker impact. These findings contribute valuable insights for enhancing the efficiency and reliability of PV systems in renewable energy applications.
作者：
Jiwei ShanYirui LiQiyu FengDitao LiLijun HanHesheng WangDepartment of Automation
Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai China School of Mechanical Engineering
Shanghai Jiao Tong University Shanghai China
Building a self-model for robots, enabling them to simulate their physical selves and predict future states without direct interaction with the physical world, is crucial for robot motion planning and control. Existin...
详细信息
ISBN:
(数字)9798350377705
ISBN:
(纸本)9798350377712
Building a self-model for robots, enabling them to simulate their physical selves and predict future states without direct interaction with the physical world, is crucial for robot motion planning and control. Existing self-modeling methods primarily focus on rigid robots and typically require significant time, effort, and resources to gather training data. In this study, we introduce SoftNeRF, a self-supervised visual self-model designed for soft robots. We use a hybrid neural shape representation based on the Signed Distance Function (SDF) to capture both the geometry and complex nonlinear motion of soft robots. By leveraging differentiable rendering, our method learns a self-model from readily available RGB images, similar to how humans understand their physical state through reflection. To improve training efficiency and model accuracy, we propose an error-guided adaptive sampling strategy. SoftNeRF can serve as a plug-in for various downstream tasks, even when trained with data unrelated to those tasks. We demonstrate SoftNeRF’s ability to support shape prediction and motion planning for robots in both simulated and real-world environments. Furthermore, SoftNeRF excels in detecting and recovering from damage, thereby enhancing machine resilience. Code is available at: https://***/irmvlab/soft-nerf.
暂无评论