Acquiring Grounded Representations of Words with Situated Interactive Instruction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912251714207744 |
|---|---|
| author | Mohan, Shiwali Mininger, Aaron H. Kirk, James R. Laird, John E. |
| author_facet | Mohan, Shiwali Mininger, Aaron H. Kirk, James R. Laird, John E. |
| contents | We present an approach for acquiring grounded representations of words from mixed-initiative, situated interactions with a human instructor. The work focuses on the acquisition of diverse types of knowledge including perceptual, semantic, and procedural knowledge along with learning grounded meanings. Interactive learning allows the agent to control its learning by requesting instructions about unknown concepts, making learning efficient. Our approach has been instantiated in Soar and has been evaluated on a table-top robotic arm capable of manipulating small objects. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_20754 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Acquiring Grounded Representations of Words with Situated Interactive Instruction Mohan, Shiwali Mininger, Aaron H. Kirk, James R. Laird, John E. Artificial Intelligence Computation and Language Human-Computer Interaction We present an approach for acquiring grounded representations of words from mixed-initiative, situated interactions with a human instructor. The work focuses on the acquisition of diverse types of knowledge including perceptual, semantic, and procedural knowledge along with learning grounded meanings. Interactive learning allows the agent to control its learning by requesting instructions about unknown concepts, making learning efficient. Our approach has been instantiated in Soar and has been evaluated on a table-top robotic arm capable of manipulating small objects. |
| title | Acquiring Grounded Representations of Words with Situated Interactive Instruction |
| topic | Artificial Intelligence Computation and Language Human-Computer Interaction |
| url | https://arxiv.org/abs/2502.20754 |