The design and implementation of sensing and power mechanisms in microdevices for biomedical applications present significant challenges. In this context, we introduce a new three-layer bi-metallic metamaterial absorb...
详细信息
3D object detection is crucial for applications like autonomous driving and robotics. However, in real-world environments, variations in sensor data distribution due to sensor upgrades, weather changes, and geographic...
详细信息
3D object detection is crucial for applications like autonomous driving and robotics. However, in real-world environments, variations in sensor data distribution due to sensor upgrades, weather changes, and geographic differences can adversely affect detection performance. Semi-Supervised Domain Adaptation (SSDA) aims to mitigate these challenges by transferring knowledge from a source domain, abundant in labeled data, to a target domain where labels are scarce. This paper presents a new SSDA method referred to as Target-Oriented Domain Augmentation (TODA) specifically tailored for LiDAR-based 3D object detection. TODA efficiently utilizes all available data, including labeled data in the source domain, and both labeled data and unlabeled data in the target domain to enhance domain adaptation performance. TODA consists of two stages: TargetMix and AdvMix. TargetMix employs mixing augmentation accounting for LiDAR sensor characteristics to facilitate feature alignment between the source-domain and target-domain. AdvMix applies point-wise adversarial augmentation with mixing augmentation, which perturbs the unlabeled data to align the features within both labeled and unlabeled data in the target domain. Our experiments conducted on the challenging domain adaptation tasks demonstrate that TODA outperforms existing domain adaptation techniques designed for 3D object detection by significant margins. IEEE
Semi-supervised learning (SSL) aims to reduce reliance on labeled data. Achieving high performance often requires more complex algorithms, therefore, generic SSL algorithms are less effective when it comes to image cl...
详细信息
This paper investigates the cooperative adaptive optimal output regulation problem of continuous-time linear multi-agent *** the multi-agent system dynamics are uncertain,solving regulator equations and the correspond...
详细信息
This paper investigates the cooperative adaptive optimal output regulation problem of continuous-time linear multi-agent *** the multi-agent system dynamics are uncertain,solving regulator equations and the corresponding algebraic Riccati equations is challenging,especially for high-order *** this paper,a novel method is proposed to approximate the solution of regulator equations,i.e.,gradient descent *** is worth noting that this method obtains gradients through online data rather than model information.A data-driven distributed adaptive suboptimal controller is developed by adaptive dynamic programming,so that each follower can achieve asymptotic tracking and disturbance ***,the effectiveness of the proposed control method is validated by simulations.
The advent of smart manufacturing in Industry 4.0 signifies the era of connections. As a communication protocol, object linking and embedding for process control unified architecture (OPC UA) can address most semantic...
详细信息
Robots are increasingly being deployed in densely populated environments, such as homes, hotels, and office buildings, where they rely on explicit instructions from humans to perform tasks. However, complex tasks ofte...
详细信息
Robots are increasingly being deployed in densely populated environments, such as homes, hotels, and office buildings, where they rely on explicit instructions from humans to perform tasks. However, complex tasks often require multiple instructions and prolonged monitoring, which can be time-consuming and demanding for users. Despite this, there is limited research on enabling robots to autonomously generate tasks based on real-life scenarios. Advanced intelligence necessitates robots to autonomously observe and analyze their environment and then generate tasks autonomously to fulfill human requirements without explicit commands. To address this gap, we propose the autonomous generation of navigation tasks using natural language dialogues. Specifically, a robot autonomously generates tasks by analyzing dialogues involving multiple persons in a real office environment to facilitate the completion of item transportation between various *** propose the leveraging of a large language model(LLM) through chain-of-thought prompting to generate a navigation sequence for a robot from dialogues. We also construct a benchmark dataset consisting of 625 multiperson dialogues using the generation capability of LLMs. Evaluation results and real-world experiments in an office building demonstrate the effectiveness of the proposed method.
This paper proposes an immersion and invariance (I&I) fuzzy adaptive image-based visual servoing (IBVS) method for an omnidirectional mobile robot (OMR), ensuring robustness against the uncertainties in feature po...
详细信息
This paper proposes an immersion and invariance (I&I) fuzzy adaptive image-based visual servoing (IBVS) method for an omnidirectional mobile robot (OMR), ensuring robustness against the uncertainties in feature point dynamics. Most existing IBVS studies for OMR systems have only addressed the kinematics of OMRs, and studies that consider the dynamics of OMRs have only been conducted recently. In particular, the practical uncertainties caused by dynamic uncertainty, interaction matrix uncertainty, and target motion have not been considered in previous studies. In this paper, feature point dynamics of OMRs are modeled by including all of the dynamic uncertainty, interaction matrix uncertainty, and target motion. To approximate and compensate for these uncertainties, fuzzy logic systems (FLS) with two update laws—the general adaptive law and I&I law—are proposed. Notably, the proposed I&I law eliminates the limitations of general adaptive methods, improving transient response owing to its noncertainty-equivalent adaptive structure. The proposed methods are designed by based on the FLS, I&I law, and integral sliding mode control all together to compensate for the practical uncertainties in feature point dynamics, guaranteeing global asymptotic stability unlike the existing studies. The stability and feasibility of the proposed methods are verified via the Lyapunov stability analysis, simulations, and experiments in an environment with uncertain feature point dynamics. IEEE
During the last 35 years, the community devoted to the design and fabrication of solid-state circuits has benefited from the outstanding scientific contributions of Prof. Michiel Steyaert (Figure 1). The finding of in...
详细信息
Bioanalysis at a single-cell level has yielded unparalleled insight into the heterogeneity of complex biological *** with Lab-on-a-Chip concepts,various simultaneous and high-frequency techniques and microfluidic plat...
详细信息
Bioanalysis at a single-cell level has yielded unparalleled insight into the heterogeneity of complex biological *** with Lab-on-a-Chip concepts,various simultaneous and high-frequency techniques and microfluidic platforms have led to the development of high-throughput platforms for single-cell ***(DEP),an electrical approach based on the dielectric property of target cells,makes it possible to efficiently manipulate individual cells without *** review focusses on the engineering designs of recent advanced microfluidic designs that utilize DEP techniques for multiple single-cell ***-chip DEP is primarily effectuated by the induced dipole of dielectric particles,(i.e.,cells)in a non-uniform electric *** addition to simply capturing and releasing particles,DEP can also aid in more complex manipulations,such as rotation and moving along arbitrary predefined routes for numerous ***,DEP electrodes can be designed with different patterns to achieve different geometric boundaries of the electric *** many single-cell analyses require isolation and compartmentalization of individual cells,specific microstructures can also be incorporated into DEP *** article discusses common electrical and physical designs of single-cell DEP microfluidic devices as well as different categories of electrodes and *** addition,an up-to-date summary of achievements and challenges in current designs,together with prospects for future design direction,is provided.
Urban Air Mobility(UAM)is an emerging aviation sector which the goal is to transform air transportation with safe,on-demand air travel for both passengers and *** flight planning strategically separates flows of aircr...
详细信息
Urban Air Mobility(UAM)is an emerging aviation sector which the goal is to transform air transportation with safe,on-demand air travel for both passengers and *** flight planning strategically separates flows of aircraft on intersecting routes vertically by allocating distinct flight levels to them,and aircraft are required to maintain the flight level when crossing the ***,there is a possibility that an aircraft may fail to maintain the assigned flight level,leading to a potential conflict at *** paper aims to address conflicts at intersections in the context of UAM,focusing on decentralized conflict detection and resolution.A novel approach is developed to facilitate information exchange among UAM components,including the provider of services to UAM,UAM operators,and the pilot in command.A receding horizon trajectory planning approach is proposed for the execution of conflict resolution,optimizing trajectory planning by eliminating potential problems and challenges associated with geometric *** proposed trajectory planner considers the model and constraints of UAM aircraft,offering optimal solutions for safe separation at UAM airspace *** significance of the proposed planning framework is demonstrated through simulations considering conflict at intersections by communicating the UAM components through request and replay services and generating resolution maneuvers on-the-fly for each aircraft involved in the conflict.
暂无评论