In multi-agent reinforcement learning, centralized training with decentralized execution (CTDE) methods typically assume that agents make decisions based on their local observations independently, which may not lead t...
详细信息
Recent advancements in legged robot locomotion systems have led to significant improvements in their agility and overall performance. However, for these systems to effectively handle sudden obstacles, especially in fo...
详细信息
ISBN:
(数字)9798350391992
ISBN:
(纸本)9798350392005
Recent advancements in legged robot locomotion systems have led to significant improvements in their agility and overall performance. However, for these systems to effectively handle sudden obstacles, especially in foothold areas, real-time integration of external information is crucial. In this paper, we introduce a rapid integration approach between perception and action in legged robot locomotion to address such unexpected external obstacles. We utilize depth sensors to capture external data in the form of pointclouds. We have developed a fast surface perception model based on topological information, employing dynamic sparsity through the growing neural gas algorithm. This model addresses several key challenges in 3D point cloud extraction: 1) Extracting object features from a smaller portion of data. 2) Controlling granularity in unsupervised learning using a topological structure. 3) Controlling granularity with only 3D positional point cloud information. To evaluate the effectiveness of our proposed method, we conducted a series of progressive experiments. Initially, we compared the performance of our topological perception model with similar approaches. Subsequently, we carried out qualitative and quantitative experiments using a real, low-cost quadruped robot
Dual-function radar-communication (DFRC) system is considered one of the most promising technologies in wireless communication systems. By using orthogonal frequency division multiplexing (OFDM), the system can sense ...
详细信息
ISBN:
(数字)9798331504847
ISBN:
(纸本)9798331504854
Dual-function radar-communication (DFRC) system is considered one of the most promising technologies in wireless communication systems. By using orthogonal frequency division multiplexing (OFDM), the system can sense several spatial directions while serving multiple users concurrently. Multi-input multi-output (MIMO) DFRC with the aid of a reconfigurable intelligent surface (RIS) is examined in this paper. Using genetic algorithms, this paper optimizes the mutual information (MI) performance metric for the targets while ensuring a minimum error rate for the users. For the scenarios considered in this paper, it is shown that the proper RIS deployment can improve the system performance by 20%.
Modern digital signal transmission heavily relies on differential-mode signals. However, challenges such as asymmetrical routing, bending, and timing skew can compromise their symmetry, leading to common-mode noise is...
详细信息
ISBN:
(数字)9784885523472
ISBN:
(纸本)9798350349498
Modern digital signal transmission heavily relies on differential-mode signals. However, challenges such as asymmetrical routing, bending, and timing skew can compromise their symmetry, leading to common-mode noise issues. To address this challenge, we propose a dual-band absorptive common-mode noise suppression filter incorporating a series unified dual-band matching network. This approach effectively maintains the integrity of differential signals while suppressing common-mode noise. The proposed architecture has been verified to achieve an absorption efficiency of over 80% in the target frequency bands of 2.4-2.48 GHz and 5.18-5.32 GHz. They are furthermore, adding the dual-band matching network results in only a slight increase in the overall footprint. This implementation presents a promising solution for mitigating electromagnetic interference (EMI) challenges in digital signal transmission.
There is an immediate threat to the highway transportation system from road accidents, which can cause death, serious injury, and property damage. Accidents involving motor vehicles cause significant injury or death t...
详细信息
ISBN:
(数字)9798350388282
ISBN:
(纸本)9798350388299
There is an immediate threat to the highway transportation system from road accidents, which can cause death, serious injury, and property damage. Accidents involving motor vehicles cause significant injury or death to a large number of individuals annually. Fatigue, lack of focus, and lethargy are key contributors to vehicle collisions. In order to identify driver inattention or exhaustion in real-time, this research lays forth a system that combines an emergency alarm system with Eye Aspect Ratio (EAR), which is based on facial landmarks. The method's strength is that it can accurately differentiate between closed eyes and inattention, even in low-light conditions. The experimental results demonstrate the efficacy of the proposed method in resolving these critical issues, offering a practical means to enhance road safety.
In the evolving landscape of wireless communication, controlling electromagnetic (EM) waves has become increasingly crucial with the next generation of networks. Reconfigurable intelligent surfaces (RISs) lead a new e...
详细信息
ISBN:
(数字)9789463968119
ISBN:
(纸本)9798350359497
In the evolving landscape of wireless communication, controlling electromagnetic (EM) waves has become increasingly crucial with the next generation of networks. Reconfigurable intelligent surfaces (RISs) lead a new era in adaptive communication systems. These surfaces, engineered with arrays of metallic and dielectric elements, from focusing to redirecting signals, offer precise manipulation of EM waves. However, accurately modeling these surfaces, given their complex element arrangements, remains a formidable challenge.
The heuristic iterative pruning strategy has been widely used for neural network sparsification. However, it is challenging to identify the right connections to remove at each pruning iteration with only a one-shot ev...
The heuristic iterative pruning strategy has been widely used for neural network sparsification. However, it is challenging to identify the right connections to remove at each pruning iteration with only a one-shot evaluation of weight magnitude, especially at the early pruning stage. The erroneously removed connections, unfortunately, can hardly be recovered. In this work, we propose a weight decay strategy as a substitute for pruning, which let the "insignificant" weights moderately decay instead of being directly clamped to zero. At the end of the training, the vast majority of redundant weights will naturally become close to zero, making it easier to identify which connections could be removed safely. Experimental results show that the proposed weight decay method can achieve an ultra-high sparsity of 99%. Compared to the current pruning strategy, the model size is further reduced by 34%, improving the compression rate from 69× to 106× at the same accuracy.
The geomagnetic storms and solar flares are a threat to the Global Navigation Satellite Systems, especially GPS. Investigation of prediction ability of Ordinary Kriging built Meta-Model (OKMM) and the consequence on t...
详细信息
We explore the fair distribution of a set of m indivisible chores among n agents, where each agent’s costs are evaluated using a monotone cost function. Our focus lies on two fairness criteria: envy-freeness up to an...
详细信息
This paper presents an intelligent means of addressing characterization and grading problems in the oil palm industry for the purpose of quality control. A Layer-Sensitivity Based Artificial Neural Network (LSB_ANN) w...
详细信息
暂无评论