Learning Neuro-symbolic Programs for Language Guided Robot Manipulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kalithasan, Namasivayam, Singh, Himanshu, Bindal, Vishal, Tuli, Arnav, Agrawal, Vishwajeet, Jain, Rahul, Singla, Parag, Paul, Rohan
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910394256195584
author Kalithasan, Namasivayam
Singh, Himanshu
Bindal, Vishal
Tuli, Arnav
Agrawal, Vishwajeet
Jain, Rahul
Singla, Parag
Paul, Rohan
author_facet Kalithasan, Namasivayam
Singh, Himanshu
Bindal, Vishal
Tuli, Arnav
Agrawal, Vishwajeet
Jain, Rahul
Singla, Parag
Paul, Rohan
contents Given a natural language instruction and an input scene, our goal is to train a model to output a manipulation program that can be executed by the robot. Prior approaches for this task possess one of the following limitations: (i) rely on hand-coded symbols for concepts limiting generalization beyond those seen during training [1] (ii) infer action sequences from instructions but require dense sub-goal supervision [2] or (iii) lack semantics required for deeper object-centric reasoning inherent in interpreting complex instructions [3]. In contrast, our approach can handle linguistic as well as perceptual variations, end-to-end trainable and requires no intermediate supervision. The proposed model uses symbolic reasoning constructs that operate on a latent neural object-centric representation, allowing for deeper reasoning over the input scene. Central to our approach is a modular structure consisting of a hierarchical instruction parser and an action simulator to learn disentangled action representations. Our experiments on a simulated environment with a 7-DOF manipulator, consisting of instructions with varying number of steps and scenes with different number of objects, demonstrate that our model is robust to such variations and significantly outperforms baselines, particularly in the generalization settings. The code, dataset and experiment videos are available at https://nsrmp.github.io
format Preprint
id arxiv_https___arxiv_org_abs_2211_06652
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Learning Neuro-symbolic Programs for Language Guided Robot Manipulation
Kalithasan, Namasivayam
Singh, Himanshu
Bindal, Vishal
Tuli, Arnav
Agrawal, Vishwajeet
Jain, Rahul
Singla, Parag
Paul, Rohan
Robotics
Artificial Intelligence
Machine Learning
Given a natural language instruction and an input scene, our goal is to train a model to output a manipulation program that can be executed by the robot. Prior approaches for this task possess one of the following limitations: (i) rely on hand-coded symbols for concepts limiting generalization beyond those seen during training [1] (ii) infer action sequences from instructions but require dense sub-goal supervision [2] or (iii) lack semantics required for deeper object-centric reasoning inherent in interpreting complex instructions [3]. In contrast, our approach can handle linguistic as well as perceptual variations, end-to-end trainable and requires no intermediate supervision. The proposed model uses symbolic reasoning constructs that operate on a latent neural object-centric representation, allowing for deeper reasoning over the input scene. Central to our approach is a modular structure consisting of a hierarchical instruction parser and an action simulator to learn disentangled action representations. Our experiments on a simulated environment with a 7-DOF manipulator, consisting of instructions with varying number of steps and scenes with different number of objects, demonstrate that our model is robust to such variations and significantly outperforms baselines, particularly in the generalization settings. The code, dataset and experiment videos are available at https://nsrmp.github.io
title Learning Neuro-symbolic Programs for Language Guided Robot Manipulation
topic Robotics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2211.06652