LVDiffusor: Distilling Functional Rearrangement Priors from Large Models into Diffusor
Object rearrangement, a fundamental challenge in robotics, demands versatile strategies to
handle diverse objects, configurations, and functional needs. To achieve this, the AI robot …
handle diverse objects, configurations, and functional needs. To achieve this, the AI robot …
Human-centered In-building Embodied Delivery Benchmark
Recently, the concept of embodied intelligence has been widely accepted and popularized,
leading people to naturally consider the potential for commercialization in this field. In this …
leading people to naturally consider the potential for commercialization in this field. In this …
DT-Transformer: A Text-Tactile Fusion Network for Object Recognition
S Qiu, B Li, X Wang, H Wang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Humans rely on multiple senses to understand their surroundings, and so do robots. Current
research in haptic object classification focuses on visual-haptic methods, but faces …
research in haptic object classification focuses on visual-haptic methods, but faces …
EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views
Understanding egocentric human-object interaction (HOI) is a fundamental aspect of human-
centric perception, facilitating applications like AR/VR and embodied AI. For the egocentric …
centric perception, facilitating applications like AR/VR and embodied AI. For the egocentric …
InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environment
Enabling robots to navigate following diverse language instructions in unexplored
environments is an attractive goal for human-robot interaction. However, this goal is …
environments is an attractive goal for human-robot interaction. However, this goal is …
MO-DDN: A Coarse-to-Fine Attribute-based Exploration Agent for Multi-object Demand-driven Navigation
The process of satisfying daily demands is a fundamental aspect of humans' daily lives. With
the advancement of embodied AI, robots are increasingly capable of satisfying human …
the advancement of embodied AI, robots are increasingly capable of satisfying human …
Cross-Domain Knowledge Transfer without Retraining to Facilitating Seamless Knowledge Application in Large Language Models
JH Kim, HR Kim - 2024 - researchsquare.com
Cross-domain knowledge transfer in large language models (LLMs) presents significant
challenges, particularly regarding the extensive resources required for retraining. This …
challenges, particularly regarding the extensive resources required for retraining. This …