A5100437461- Robotic Path Planning Algorithms
- Robotics and Sensor-Based Localization
- Topic Modeling
- Advanced Vision and Imaging
- Caching and Content Delivery
- Diverse Educational Innovations Studies
- IoT Networks and Protocols
- Information Retrieval and Search Behavior
- Misinformation and Its Impacts
- Asymmetric Hydrogenation and Catalysis
- Synthesis and Catalytic Reactions
- Catalytic C–H Functionalization Methods
- Parallel Computing and Optimization Techniques
- Context-Aware Activity Recognition Systems
- Software-Defined Networks and 5G
- IoT and Edge/Fog Computing
- Reinforcement Learning in Robotics
- Video Coding and Compression Technologies
- Generative Adversarial Networks and Image Synthesis
- Anomaly Detection Techniques and Applications
- Sentiment Analysis and Opinion Mining
- Social Robot Interaction and HRI
- Text and Document Classification Technologies
- Bluetooth and Wireless Communication Technologies
- Influenza Virus Research Studies
Iowa State University
2020-2025
Beihang University
2024
Huazhong University of Science and Technology
2024
Liaoning Technical University
2023
Laboratoire d'Informatique de Paris-Nord
2023
China Academy of Space Technology
2023
Stanford University
2023
University College London
2022
Southern University of Science and Technology
2021
Tunghai University
2020
Abstract Chiral aliphatic amine and alcohol derivatives are ubiquitous in pharmaceuticals, pesticides, natural products fine chemicals, yet difficult to access due the challenge differentiate between spatially electronically similar alkyl groups. Herein, we report a nickel-catalyzed enantioselective hydroalkylation of acyl enamines enol esters with halides afford enantioenriched α-branched amines good yields excellent levels enantioselectivity. The operationally simple protocol provides...
Generative search engines directly generate responses to user queries, along with in-line citations. A prerequisite trait of a trustworthy generative engine is verifiability, i.e., systems should cite comprehensively (high citation recall; all statements are fully supported by citations) and accurately precision; every supports its associated statement). We conduct human evaluation audit four popular engines—Bing Chat, NeevaAI, perplexity.ai, YouChat—across diverse set queries from variety...
Abstract A fundamental task in robotics is to plan collision‐free motions among a set of obstacles. Recently, learning‐based motion‐planning methods have shown significant advantages solving different planning problems high‐dimensional spaces and complex environments. This article serves as survey various that been applied robot problems, including supervised, unsupervised learning, reinforcement learning. These either rely on human‐crafted reward function for specific tasks or learn from...
Sampling-based path planning is a popular methodology for robot planning. With uniform sampling strategy to explore the state space, feasible can be found without complex geometric modeling of configuration space. However, quality initial solution not guaranteed, and convergence speed optimal slow. In this paper, we present novel image-based algorithm overcome these limitations. Specifically, generative adversarial network (GAN) designed take environment map (denoted as RGB image) input...
Addressing the broadband gap between rural and urban regions requires rural-focused wireless research innovation. In meantime, provide rich, diverse use cases of advanced wireless, they offer unique real-world settings for piloting applications that advance frontiers systems (e.g., teleoperation ground aerial vehicles). To fill to leverage opportunities applications, we design implement ARA living lab innovation in their precision agriculture, community services, so on. focuses on community,...
Robot path planning in 3D space is a challenging problem for its complex configuration. Sampling-based algorithms have gained great success solving problems space, but the quality of initial not guaranteed and convergence to optimal solution slow. To address these problems, this article, we present novel sampling-based framework enhanced by deep neural network (DNN) with applications space. In proposed framework, first train DNN number successful cases Then utilized predict promising region...
Generative search engines directly generate responses to user queries, along with in-line citations. A prerequisite trait of a trustworthy generative engine is verifiability, i.e., systems should cite comprehensively (high citation recall; all statements are fully supported by citations) and accurately precision; every supports its associated statement). We conduct human evaluation audit four popular -- Bing Chat, NeevaAI, perplexity.ai, YouChat across diverse set queries from variety...
Aimed at the difficulty of path planning resulting from variable configuration wheel-legged robot for future deep space explorations, this paper proposes a algorithm based on Theta* and Timed Elastic Band (TEB) algorithm. Firstly, structure is briefly introduced, workspace single leg analyzed. Secondly, method to judge complete obstacles incomplete according height proposed alongside search virtual obstacles, generate grid map wheel body, respectively. By dividing into split body path. The...
A rapid method that uses super-resolution magnetic array data is proposed to localize an unknown number of magnets in a array. (SR) neural network was developed improve the resolution sensor The approximate 3D positions multiple targets were then obtained based on normalized source strength (NSS) and gradient tensor (MGT) inversion. Finally, refined inversion position moment performed using trust region reflective algorithm (TRR). effectiveness examined experimental field collected from...
Gaining insight into human personality and its impact on behavior is very valuable in many applications, such as web information credibility prediction.In this paper, we explore using weighted ML-kNN model for automatic recognition of traits users, based a given composition text.After extracting features through analysis the content user's Essays statues updates, discretize contiguous attribute Kohonen's feature-map algorithm, assign weight to extracted entropy.The dataset partitioned...
A 1D-DCT processor with parallel pipelined VLSI architecture is designed for MPEG visual and audio applications. The based on distributed arithmetic to obtain low power high computation efficiency. simulation EDA software shows that the can reach an efficient compromise between hardware cost computing speed real-time MPEG-related
With the rapid development of artificial intelligence, multimodal learning has become an important research area. For intelligent agents, state is a crucial modality to convey precise information alongside common modalities like images, videos, and language. This becomes especially clear with broad adoption reinforcement large language models. Nevertheless, representation still lags in development. To this end, we propose High-Fidelity Contrastive Language-State Pre-training (CLSP) method,...
To address the rural broadband challenge and to leverage unique opportunities that regions provide for piloting advanced wireless applications, we design implement ARA living lab research innovation in systems their applications precision agriculture, community services, so on. focuses on community, application, economic context of regions, it features first-of-its-kind, real-world deployment long-distance, high-capacity x-haul access platforms across a area diameter over 30 km. With both...
Although voids play an important role in Chinese paintings, when generating ink wash paintings from real life photos of horses, background detection and void-leaving remain challenges producing more credible paintings. To address the problem, a model with two-stage framework is proposed this paper. The divides generation process into lightening style transformation. In first stage, by training pix2pix paired original background-lightened photos, enabled to detect lighten correctly...
Building embodied agents on integrating Large Language Models (LLMs) and Reinforcement Learning (RL) have revolutionized human-AI interaction: researchers can now leverage language instructions to plan decision-making for open-ended tasks. However, existing research faces challenges in meeting the requirement of open-endedness. They typically either train LLM/RL models adapt a fixed counterpart, limiting exploration novel skills hindering efficacy interaction. To this end, we present...
Multi-object tracking (MOT) is an essential technique for navigation in autonomous driving. In tracking-by-detection systems, biases, false positives, and misses, which are referred to as outliers, inevitable due complex traffic scenarios. Recent methods based on filtering algorithms that overlook these leading reduced accuracy or even loss of the objects trajectory. To handle this challenge, we adopt a probabilistic perspective, regarding generation outliers misspecification between actual...
This article discusses the relationship between culture and body, with a particular focus on female body cultural construction of its biology by society. Culture always operates through in which is often embodied spheres labour, production reproduction, constantly reinforced scientific knowledge social common sense. based literature research method to explain this view. The explores ways practices perceive shape women’s gender bodies from different perspectives such as concluding that...