Results 121 to 130 of about 270,599 (317)
Grounding Large Language Models for Robot Task Planning Using Closed‐Loop State Feedback
BrainBody‐Large Language Model (LLM) introduces a hierarchical, feedback‐driven planning framework where two LLMs coordinate high‐level reasoning and low‐level control for robotic tasks. By grounding decisions in real‐time state feedback, it reduces hallucinations and improves task reliability.
Vineet Bhat +4 more
wiley +1 more source
Semantic linking and personalization in context
The World Wide Web (WWW) is intended for humans to create and share documents. However, it does not support machine-processable data and automated processing. The Semantic Web is an extension to the WWW and can overcome its shortcomings. The Semantic Web
Şah, Melike
core
Semantic-Aware Low-Light Image Enhancement by Learning from Multiple Color Spaces
Extreme low-light image enhancement presents persistent challenges due to compounded degradations involving underexposure, sensor noise, and structural detail loss.
Bo Jiang +5 more
doaj +1 more source
Visual teach‐and‐repeat (VTR) navigation allows robots to learn and follow routes without building a full metric map. We show that navigation accuracy for VTR can be improved by integrating a topological map with error‐drift correction based on stereo vision.
Fuhai Ling, Ze Huang, Tony J. Prescott
wiley +1 more source
Instant Effects of Semantic Information on Visual Perception. [PDF]
Enge A, Süß F, Abdel Rahman R.
europepmc +1 more source
10232 Report – The Semantics of Information
The Dagstuhl Seminar 10232, "Semantics of Information" was devoted to talks by researchers in a wide range of disciplines: mathematics, computer science, systems biology, physics, and economic gam theory, all of which explored the relationship of computer science and its theory to their area.
Martin, Keye R., Mislove, Michael W.
openaire +4 more sources
Continual Learning for Multimodal Data Fusion of a Soft Gripper
Models trained on a single data modality often struggle to generalize when exposed to a different modality. This work introduces a continual learning algorithm capable of incrementally learning different data modalities by leveraging both class‐incremental and domain‐incremental learning scenarios in an artificial environment where labeled data is ...
Nilay Kushawaha, Egidio Falotico
wiley +1 more source
A CityGML ADE for flood simulations
Floods are one of the most frequent types of destructive natural disaster that causes serious safety risks and economic losses. Flood simulation has been an effective way to model the behavior and dynamics of flood and support the analysis like flood ...
Shaohua Luo, Linfang Ding, Hongchao Fan
doaj +1 more source
Multimodal Human–Robot Interaction Using Human Pose Estimation and Local Large Language Models
A multimodal human–robot interaction framework integrates human pose estimation (HPE) and a large language model (LLM) for gesture‐ and voice‐based robot control. Speech‐to‐text (STT) enables voice command interpretation, while a safety‐aware arbitration mechanism prioritizes gesture input for rapid intervention.
Nasiru Aboki +2 more
wiley +1 more source
The effects of presentation methods and semantic information on multi-ethnicity face recognition
Studies have shown that own-race faces are more accurately recognised than other-race faces. The present study examined the effects of own- and other-race face recognition when different ethnicity targets are presented to the participants together.
Kaarel Rundu, Kristjan Kask
doaj

