Skip to main content

Task-Driven Estimation and Control via Information Bottlenecks

Author(s): Pacelli, V; Majumdar, Anirudha

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr13k4v
Full metadata record
DC FieldValueLanguage
dc.contributor.authorPacelli, V-
dc.contributor.authorMajumdar, Anirudha-
dc.date.accessioned2021-10-08T20:20:07Z-
dc.date.available2021-10-08T20:20:07Z-
dc.date.issued2019en_US
dc.identifier.citationPacelli, V, Majumdar, A. (2019). Task-Driven Estimation and Control via Information Bottlenecks. 2019-May (2061 - 2067. doi:10.1109/ICRA.2019.8794213en_US
dc.identifier.urihttp://arks.princeton.edu/ark:/88435/pr13k4v-
dc.description.abstractOur goal is to develop a principled and general algorithmic framework for task-driven estimation and control for robotic systems. State-of-the-art approaches for controlling robotic systems typically rely heavily on accurately estimating the full state of the robot (e.g., a running robot might estimate joint angles and velocities, torso state, and position relative to a goal). However, full state representations are often excessively rich for the specific task at hand and can lead to significant computational inefficiency and brittleness to errors in state estimation. In contrast, we present an approach that eschews such rich representations and seeks to create task-driven representations. The key technical insight is to leverage the theory of information bottlenecks to formalize the notion of a 'task-driven representation' in terms of information theoretic quantities that measure the minimality of a representation. We propose novel iterative algorithms for automatically synthesizing (offline) a task-driven representation (given in terms of a set of task-relevant variables (TRVs)) and a performant control policy that is a function of the TRVs. We presentonline algorithms for estimating the TRVs in order to apply the control policy. We demonstrate that our approach results in significant robustness to unmodeled measurement uncertainty both theoretically and via thorough simulation experiments including a spring-loaded inverted pendulum running to a goal location.en_US
dc.format.extent2061 - 2067en_US
dc.language.isoen_USen_US
dc.relation.ispartofProceedings - IEEE International Conference on Robotics and Automationen_US
dc.rightsAuthor's manuscripten_US
dc.titleTask-Driven Estimation and Control via Information Bottlenecksen_US
dc.typeConference Articleen_US
dc.identifier.doidoi:10.1109/ICRA.2019.8794213-
pu.type.symplectichttp://www.symplectic.co.uk/publications/atom-terms/1.0/conference-proceedingen_US

Files in This Item:
File Description SizeFormat 
Task-Driven Estimation and Control via Information Bottlenecks.pdf496.65 kBAdobe PDFView/Download


Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.