Enhancing Robot Explanation Capabilities through Vision-Language Models: a Preliminary Study by Interpreting Visual Inputs for Improved Human-Robot Interaction.
David Sobrín-HidalgoMiguel Ángel González SantamartaÁngel Manuel Guerrero-HiguerasFrancisco Javier Rodríguez-LeraVicente Matellán OliveraPublished in: CoRR (2024)
Keyphrases
- document collections
- human robot interaction
- language model
- document retrieval
- information retrieval
- service robots
- test collection
- human robot
- language modeling
- robot programming
- pointing gestures
- n gram
- retrieval model
- probabilistic model
- gesture recognition
- speech recognition
- query terms
- humanoid robot
- vision system
- document ranking
- statistical language models
- language modelling
- query expansion
- smoothing methods
- context sensitive
- visual information
- vector space model
- manipulation tasks
- visual features
- relevance model
- natural interaction
- computer vision
- ad hoc information retrieval
- pseudo relevance feedback
- tf idf
- web search
- spatio temporal
- language model for information retrieval