Multi-Level Compositional Reasoning for Interactive Instruction Following

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Bhambri, Suvaansh, Kim, Byeonghwi, Choi, Jonghyun
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914711204790272
author Bhambri, Suvaansh
Kim, Byeonghwi
Choi, Jonghyun
author_facet Bhambri, Suvaansh
Kim, Byeonghwi
Choi, Jonghyun
contents Robotic agents performing domestic chores by natural language directives are required to master the complex job of navigating environment and interacting with objects in the environments. The tasks given to the agents are often composite thus are challenging as completing them require to reason about multiple subtasks, e.g., bring a cup of coffee. To address the challenge, we propose to divide and conquer it by breaking the task into multiple subgoals and attend to them individually for better navigation and interaction. We call it Multi-level Compositional Reasoning Agent (MCR-Agent). Specifically, we learn a three-level action policy. At the highest level, we infer a sequence of human-interpretable subgoals to be executed based on language instructions by a high-level policy composition controller. At the middle level, we discriminatively control the agent's navigation by a master policy by alternating between a navigation policy and various independent interaction policies. Finally, at the lowest level, we infer manipulation actions with the corresponding object masks using the appropriate interaction policy. Our approach not only generates human interpretable subgoals but also achieves 2.03% absolute gain to comparable state of the arts in the efficiency metric (PLWSR in unseen set) without using rule-based planning or a semantic spatial memory.
format Preprint
id arxiv_https___arxiv_org_abs_2308_09387
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Multi-Level Compositional Reasoning for Interactive Instruction Following
Bhambri, Suvaansh
Kim, Byeonghwi
Choi, Jonghyun
Robotics
Artificial Intelligence
Robotic agents performing domestic chores by natural language directives are required to master the complex job of navigating environment and interacting with objects in the environments. The tasks given to the agents are often composite thus are challenging as completing them require to reason about multiple subtasks, e.g., bring a cup of coffee. To address the challenge, we propose to divide and conquer it by breaking the task into multiple subgoals and attend to them individually for better navigation and interaction. We call it Multi-level Compositional Reasoning Agent (MCR-Agent). Specifically, we learn a three-level action policy. At the highest level, we infer a sequence of human-interpretable subgoals to be executed based on language instructions by a high-level policy composition controller. At the middle level, we discriminatively control the agent's navigation by a master policy by alternating between a navigation policy and various independent interaction policies. Finally, at the lowest level, we infer manipulation actions with the corresponding object masks using the appropriate interaction policy. Our approach not only generates human interpretable subgoals but also achieves 2.03% absolute gain to comparable state of the arts in the efficiency metric (PLWSR in unseen set) without using rule-based planning or a semantic spatial memory.
title Multi-Level Compositional Reasoning for Interactive Instruction Following
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2308.09387