Neural Task Programming: Learning to Generalize Across Hierarchical Tasks

10/04/2017
by   Danfei Xu, et al.
0

In this work, we propose a novel robot learning framework called Neural Task Programming (NTP), which bridges the idea of few-shot learning from demonstration and neural program induction. NTP takes as input a task specification (e.g., video demonstration of a task) and recursively decomposes it into finer sub-task specifications. These specifications are fed to a hierarchical neural program, where bottom-level programs are callable subroutines that interact with the environment. We validate our method in three robot manipulation tasks. NTP achieves strong generalization across sequential tasks that exhibit hierarchal and compositional structures. The experimental results show that NTP learns to generalize well to- wards unseen tasks with increasing lengths, variable topologies, and changing objectives.

READ FULL TEXT

page 1

page 3

page 7

research
03/09/2022

One-Shot Learning from a Demonstration with Hierarchical Latent Language

Humans have the capability, aided by the expressive compositionality of ...
research
07/10/2018

Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration

Our goal is for a robot to execute a previously unseen task based on a s...
research
04/03/2019

Self-Evaluation in One-Shot Learning from Demonstration of Contact-Intensive Tasks

Humans naturally "program" a fellow collaborator to perform a task by de...
research
08/20/2023

Robotic Planning under Hierarchical Temporal Logic Specifications

Past research into robotic planning with temporal logic specifications, ...
research
02/03/2020

Elaborating on Learned Demonstrations with Temporal Logic Specifications

Most current methods for learning from demonstrations assume that those ...
research
11/23/2019

Meta Adaptation using Importance Weighted Demonstrations

Imitation learning has gained immense popularity because of its high sam...
research
10/11/2017

Neural Program Meta-Induction

Most recently proposed methods for Neural Program Induction work under t...

Please sign up or login with your details

Forgot password? Click here to reset