Saved in:
Bibliographic Details
Main Authors: Wu, Bo, Lee, Bruce D., Daniilidis, Kostas, Bucher, Bernadette, Matni, Nikolai
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.18222
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913449993306112
author Wu, Bo
Lee, Bruce D.
Daniilidis, Kostas
Bucher, Bernadette
Matni, Nikolai
author_facet Wu, Bo
Lee, Bruce D.
Daniilidis, Kostas
Bucher, Bernadette
Matni, Nikolai
contents Large-scale robotic policies trained on data from diverse tasks and robotic platforms hold great promise for enabling general-purpose robots; however, reliable generalization to new environment conditions remains a major challenge. Toward addressing this challenge, we propose a novel approach for uncertainty-aware deployment of pre-trained language-conditioned imitation learning agents. Specifically, we use temperature scaling to calibrate these models and exploit the calibrated model to make uncertainty-aware decisions by aggregating the local information of candidate actions. We implement our approach in simulation using three such pre-trained models, and showcase its potential to significantly enhance task completion rates. The accompanying code is accessible at the link: https://github.com/BobWu1998/uncertainty_quant_all.git
format Preprint
id arxiv_https___arxiv_org_abs_2403_18222
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Uncertainty-Aware Deployment of Pre-trained Language-Conditioned Imitation Learning Policies
Wu, Bo
Lee, Bruce D.
Daniilidis, Kostas
Bucher, Bernadette
Matni, Nikolai
Robotics
Machine Learning
Large-scale robotic policies trained on data from diverse tasks and robotic platforms hold great promise for enabling general-purpose robots; however, reliable generalization to new environment conditions remains a major challenge. Toward addressing this challenge, we propose a novel approach for uncertainty-aware deployment of pre-trained language-conditioned imitation learning agents. Specifically, we use temperature scaling to calibrate these models and exploit the calibrated model to make uncertainty-aware decisions by aggregating the local information of candidate actions. We implement our approach in simulation using three such pre-trained models, and showcase its potential to significantly enhance task completion rates. The accompanying code is accessible at the link: https://github.com/BobWu1998/uncertainty_quant_all.git
title Uncertainty-Aware Deployment of Pre-trained Language-Conditioned Imitation Learning Policies
topic Robotics
Machine Learning
url https://arxiv.org/abs/2403.18222