CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks

General-purpose robots coexisting with humans in their environment must learn to relate human language to their perceptions and actions to be useful in a range of daily tasks. Moreover, they need to acquire a diverse repertoire of general-purpose skills that allow composing long-horizon tasks by fol...

Full description

Saved in:
Bibliographic Details
Published in:IEEE robotics and automation letters Vol. 7; no. 3; pp. 7327 - 7334
Main Authors: Mees, Oier, Hermann, Lukas, Rosete-Beas, Erick, Burgard, Wolfram Burgard
Format: Journal Article
Language:English
Published: Piscataway IEEE 01.07.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Benchmark testing
Benchmarks
Cameras
Data sets for robot learning
Grippers
Horizon
imitation learning
Language
machine learning for robot control
natural dialog for HRI
Robot learning
Robot sensing systems
Robot vision systems
Robots
Task analysis
Task complexity
ISSN:2377-3766, 2377-3766
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:General-purpose robots coexisting with humans in their environment must learn to relate human language to their perceptions and actions to be useful in a range of daily tasks. Moreover, they need to acquire a diverse repertoire of general-purpose skills that allow composing long-horizon tasks by following unconstrained language instructions. In this letter, we present Composing Actions from Language and Vision (CALVIN) ( C omposing A ctions from L anguage and Vi sio n ), an open-source simulated benchmark to learn long-horizon language-conditioned tasks. Our aim is to make it possible to develop agents that can solve many robotic manipulation tasks over a long horizon, from onboard sensors, and specified only via human language. CALVIN tasks are more complex in terms of sequence length, action space, and language than existing vision-and-language task datasets and supports flexible specification of sensor suites. We evaluate the agents in zero-shot to novel language instructions and to novel environments. We show that a baseline model based on multi-context imitation learning performs poorly on CALVIN, suggesting that there is significant room for developing innovative agents that learn to relate human language to their world models with this benchmark.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2377-3766
2377-3766
DOI:10.1109/LRA.2022.3180108