Active uncertainty reduction for safe and efficient interaction planning: A shielding-aware dual control approach

The ability to accurately predict others’ behavior is central to the safety and efficiency of robotic systems in interactive settings, such as human–robot interaction and multi-robot teaming tasks. Unfortunately, robots often lack access to key information on which these predictions may hinge, such...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:The International journal of robotics research 2024-08, Vol.43 (9), p.1382-1408
Hauptverfasser: Hu, Haimin, Isele, David, Bae, Sangjae, Fisac, Jaime F
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 1408
container_issue 9
container_start_page 1382
container_title The International journal of robotics research
container_volume 43
creator Hu, Haimin
Isele, David
Bae, Sangjae
Fisac, Jaime F
description The ability to accurately predict others’ behavior is central to the safety and efficiency of robotic systems in interactive settings, such as human–robot interaction and multi-robot teaming tasks. Unfortunately, robots often lack access to key information on which these predictions may hinge, such as other agents’ goals, attention, and willingness to cooperate. Dual control theory addresses this challenge by treating unknown parameters of a predictive model as stochastic hidden states and inferring their values at runtime using information gathered during system operation. While able to optimally and automatically trade off exploration and exploitation, dual control is computationally intractable for general interactive motion planning, mainly due to the fundamental coupling between the robot’s trajectory plan and its prediction of other agents’ intent. In this paper, we present a novel algorithmic approach to enable active uncertainty reduction for interactive motion planning based on the implicit dual control paradigm. Our approach relies on sampling-based approximation of stochastic dynamic programming, leading to a model predictive control problem that can be readily solved by real-time gradient-based optimization methods. The resulting policy is shown to preserve the dual control effect for a broad class of predictive models with both continuous and categorical uncertainty. To ensure the safe operation of the interacting agents, we use a runtime safety filter (also referred to as a “shielding” scheme), which overrides the robot’s dual control policy with a safety fallback strategy when a safety-critical event is imminent. We then augment the dual control framework with an improved variant of the recently proposed shielding-aware robust planning scheme, which proactively balances the nominal planning performance with the risk of high-cost emergency maneuvers triggered by low-probability agent behaviors. We demonstrate the efficacy of our approach with both simulated driving studies and hardware experiments using 1/10 scale autonomous vehicles.
doi_str_mv 10.1177/02783649231215371
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_3110919063</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sage_id>10.1177_02783649231215371</sage_id><sourcerecordid>3110919063</sourcerecordid><originalsourceid>FETCH-LOGICAL-c264t-acf39080413e7c449f04b20d699a0d69fc1ef224aedc7bc3a5540827d31a4c793</originalsourceid><addsrcrecordid>eNp1kE9LAzEQxYMoWKsfwFvA82omSTeNt1L8BwUvel6m2Um7Zc1uk12l395dKngQLzPMzO-9B8PYNYhbAGPuhDRzlWsrFUiYKQMnbAJGQ6bA5KdsMt6zEThnFynthBAqF3bC9gvXVZ_E--AodliF7sAjlf2wbQL3TeQJPXEMJSfvK1dR6PhAUcQj0tYYQhU293zB07aiuhyGDL8wEi97rLlrQhebmmPbxgbd9pKdeawTXf30KXt_fHhbPmer16eX5WKVOZnrLkPnlRVzoUGRcVpbL_RaijK3FsfqHZCXUiOVzqydwtlMi7k0pQLUzlg1ZTdH3yF231Pqil3TxzBEFgpAWLAiVwMFR8rFJqVIvmhj9YHxUIAoxs8Wfz47aG6PmoQb-nX9X_ANK6V5uQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3110919063</pqid></control><display><type>article</type><title>Active uncertainty reduction for safe and efficient interaction planning: A shielding-aware dual control approach</title><source>SAGE Journals</source><creator>Hu, Haimin ; Isele, David ; Bae, Sangjae ; Fisac, Jaime F</creator><creatorcontrib>Hu, Haimin ; Isele, David ; Bae, Sangjae ; Fisac, Jaime F</creatorcontrib><description>The ability to accurately predict others’ behavior is central to the safety and efficiency of robotic systems in interactive settings, such as human–robot interaction and multi-robot teaming tasks. Unfortunately, robots often lack access to key information on which these predictions may hinge, such as other agents’ goals, attention, and willingness to cooperate. Dual control theory addresses this challenge by treating unknown parameters of a predictive model as stochastic hidden states and inferring their values at runtime using information gathered during system operation. While able to optimally and automatically trade off exploration and exploitation, dual control is computationally intractable for general interactive motion planning, mainly due to the fundamental coupling between the robot’s trajectory plan and its prediction of other agents’ intent. In this paper, we present a novel algorithmic approach to enable active uncertainty reduction for interactive motion planning based on the implicit dual control paradigm. Our approach relies on sampling-based approximation of stochastic dynamic programming, leading to a model predictive control problem that can be readily solved by real-time gradient-based optimization methods. The resulting policy is shown to preserve the dual control effect for a broad class of predictive models with both continuous and categorical uncertainty. To ensure the safe operation of the interacting agents, we use a runtime safety filter (also referred to as a “shielding” scheme), which overrides the robot’s dual control policy with a safety fallback strategy when a safety-critical event is imminent. We then augment the dual control framework with an improved variant of the recently proposed shielding-aware robust planning scheme, which proactively balances the nominal planning performance with the risk of high-cost emergency maneuvers triggered by low-probability agent behaviors. We demonstrate the efficacy of our approach with both simulated driving studies and hardware experiments using 1/10 scale autonomous vehicles.</description><identifier>ISSN: 0278-3649</identifier><identifier>EISSN: 1741-3176</identifier><identifier>DOI: 10.1177/02783649231215371</identifier><language>eng</language><publisher>London, England: SAGE Publications</publisher><subject>Automation ; Control theory ; Dynamic programming ; Interactive control ; Interactive systems ; Motion planning ; Multiple robots ; Planning ; Prediction models ; Predictive control ; Real-time programming ; Robot control ; Robot dynamics ; Robots ; Robust control ; Run time (computers) ; Safety critical ; Shielding ; Trajectory planning ; Uncertainty</subject><ispartof>The International journal of robotics research, 2024-08, Vol.43 (9), p.1382-1408</ispartof><rights>The Author(s) 2023</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c264t-acf39080413e7c449f04b20d699a0d69fc1ef224aedc7bc3a5540827d31a4c793</cites><orcidid>0000-0002-2676-5090 ; 0000-0001-9749-6951 ; 0000-0001-7974-8203 ; 0000-0002-4217-4776</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://journals.sagepub.com/doi/pdf/10.1177/02783649231215371$$EPDF$$P50$$Gsage$$H</linktopdf><linktohtml>$$Uhttps://journals.sagepub.com/doi/10.1177/02783649231215371$$EHTML$$P50$$Gsage$$H</linktohtml><link.rule.ids>314,780,784,21819,27924,27925,43621,43622</link.rule.ids></links><search><creatorcontrib>Hu, Haimin</creatorcontrib><creatorcontrib>Isele, David</creatorcontrib><creatorcontrib>Bae, Sangjae</creatorcontrib><creatorcontrib>Fisac, Jaime F</creatorcontrib><title>Active uncertainty reduction for safe and efficient interaction planning: A shielding-aware dual control approach</title><title>The International journal of robotics research</title><description>The ability to accurately predict others’ behavior is central to the safety and efficiency of robotic systems in interactive settings, such as human–robot interaction and multi-robot teaming tasks. Unfortunately, robots often lack access to key information on which these predictions may hinge, such as other agents’ goals, attention, and willingness to cooperate. Dual control theory addresses this challenge by treating unknown parameters of a predictive model as stochastic hidden states and inferring their values at runtime using information gathered during system operation. While able to optimally and automatically trade off exploration and exploitation, dual control is computationally intractable for general interactive motion planning, mainly due to the fundamental coupling between the robot’s trajectory plan and its prediction of other agents’ intent. In this paper, we present a novel algorithmic approach to enable active uncertainty reduction for interactive motion planning based on the implicit dual control paradigm. Our approach relies on sampling-based approximation of stochastic dynamic programming, leading to a model predictive control problem that can be readily solved by real-time gradient-based optimization methods. The resulting policy is shown to preserve the dual control effect for a broad class of predictive models with both continuous and categorical uncertainty. To ensure the safe operation of the interacting agents, we use a runtime safety filter (also referred to as a “shielding” scheme), which overrides the robot’s dual control policy with a safety fallback strategy when a safety-critical event is imminent. We then augment the dual control framework with an improved variant of the recently proposed shielding-aware robust planning scheme, which proactively balances the nominal planning performance with the risk of high-cost emergency maneuvers triggered by low-probability agent behaviors. We demonstrate the efficacy of our approach with both simulated driving studies and hardware experiments using 1/10 scale autonomous vehicles.</description><subject>Automation</subject><subject>Control theory</subject><subject>Dynamic programming</subject><subject>Interactive control</subject><subject>Interactive systems</subject><subject>Motion planning</subject><subject>Multiple robots</subject><subject>Planning</subject><subject>Prediction models</subject><subject>Predictive control</subject><subject>Real-time programming</subject><subject>Robot control</subject><subject>Robot dynamics</subject><subject>Robots</subject><subject>Robust control</subject><subject>Run time (computers)</subject><subject>Safety critical</subject><subject>Shielding</subject><subject>Trajectory planning</subject><subject>Uncertainty</subject><issn>0278-3649</issn><issn>1741-3176</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp1kE9LAzEQxYMoWKsfwFvA82omSTeNt1L8BwUvel6m2Um7Zc1uk12l395dKngQLzPMzO-9B8PYNYhbAGPuhDRzlWsrFUiYKQMnbAJGQ6bA5KdsMt6zEThnFynthBAqF3bC9gvXVZ_E--AodliF7sAjlf2wbQL3TeQJPXEMJSfvK1dR6PhAUcQj0tYYQhU293zB07aiuhyGDL8wEi97rLlrQhebmmPbxgbd9pKdeawTXf30KXt_fHhbPmer16eX5WKVOZnrLkPnlRVzoUGRcVpbL_RaijK3FsfqHZCXUiOVzqydwtlMi7k0pQLUzlg1ZTdH3yF231Pqil3TxzBEFgpAWLAiVwMFR8rFJqVIvmhj9YHxUIAoxs8Wfz47aG6PmoQb-nX9X_ANK6V5uQ</recordid><startdate>20240801</startdate><enddate>20240801</enddate><creator>Hu, Haimin</creator><creator>Isele, David</creator><creator>Bae, Sangjae</creator><creator>Fisac, Jaime F</creator><general>SAGE Publications</general><general>SAGE PUBLICATIONS, INC</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7TB</scope><scope>8FD</scope><scope>FR3</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0002-2676-5090</orcidid><orcidid>https://orcid.org/0000-0001-9749-6951</orcidid><orcidid>https://orcid.org/0000-0001-7974-8203</orcidid><orcidid>https://orcid.org/0000-0002-4217-4776</orcidid></search><sort><creationdate>20240801</creationdate><title>Active uncertainty reduction for safe and efficient interaction planning: A shielding-aware dual control approach</title><author>Hu, Haimin ; Isele, David ; Bae, Sangjae ; Fisac, Jaime F</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c264t-acf39080413e7c449f04b20d699a0d69fc1ef224aedc7bc3a5540827d31a4c793</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Automation</topic><topic>Control theory</topic><topic>Dynamic programming</topic><topic>Interactive control</topic><topic>Interactive systems</topic><topic>Motion planning</topic><topic>Multiple robots</topic><topic>Planning</topic><topic>Prediction models</topic><topic>Predictive control</topic><topic>Real-time programming</topic><topic>Robot control</topic><topic>Robot dynamics</topic><topic>Robots</topic><topic>Robust control</topic><topic>Run time (computers)</topic><topic>Safety critical</topic><topic>Shielding</topic><topic>Trajectory planning</topic><topic>Uncertainty</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Hu, Haimin</creatorcontrib><creatorcontrib>Isele, David</creatorcontrib><creatorcontrib>Bae, Sangjae</creatorcontrib><creatorcontrib>Fisac, Jaime F</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Mechanical &amp; Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>The International journal of robotics research</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Hu, Haimin</au><au>Isele, David</au><au>Bae, Sangjae</au><au>Fisac, Jaime F</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Active uncertainty reduction for safe and efficient interaction planning: A shielding-aware dual control approach</atitle><jtitle>The International journal of robotics research</jtitle><date>2024-08-01</date><risdate>2024</risdate><volume>43</volume><issue>9</issue><spage>1382</spage><epage>1408</epage><pages>1382-1408</pages><issn>0278-3649</issn><eissn>1741-3176</eissn><abstract>The ability to accurately predict others’ behavior is central to the safety and efficiency of robotic systems in interactive settings, such as human–robot interaction and multi-robot teaming tasks. Unfortunately, robots often lack access to key information on which these predictions may hinge, such as other agents’ goals, attention, and willingness to cooperate. Dual control theory addresses this challenge by treating unknown parameters of a predictive model as stochastic hidden states and inferring their values at runtime using information gathered during system operation. While able to optimally and automatically trade off exploration and exploitation, dual control is computationally intractable for general interactive motion planning, mainly due to the fundamental coupling between the robot’s trajectory plan and its prediction of other agents’ intent. In this paper, we present a novel algorithmic approach to enable active uncertainty reduction for interactive motion planning based on the implicit dual control paradigm. Our approach relies on sampling-based approximation of stochastic dynamic programming, leading to a model predictive control problem that can be readily solved by real-time gradient-based optimization methods. The resulting policy is shown to preserve the dual control effect for a broad class of predictive models with both continuous and categorical uncertainty. To ensure the safe operation of the interacting agents, we use a runtime safety filter (also referred to as a “shielding” scheme), which overrides the robot’s dual control policy with a safety fallback strategy when a safety-critical event is imminent. We then augment the dual control framework with an improved variant of the recently proposed shielding-aware robust planning scheme, which proactively balances the nominal planning performance with the risk of high-cost emergency maneuvers triggered by low-probability agent behaviors. We demonstrate the efficacy of our approach with both simulated driving studies and hardware experiments using 1/10 scale autonomous vehicles.</abstract><cop>London, England</cop><pub>SAGE Publications</pub><doi>10.1177/02783649231215371</doi><tpages>27</tpages><orcidid>https://orcid.org/0000-0002-2676-5090</orcidid><orcidid>https://orcid.org/0000-0001-9749-6951</orcidid><orcidid>https://orcid.org/0000-0001-7974-8203</orcidid><orcidid>https://orcid.org/0000-0002-4217-4776</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 0278-3649
ispartof The International journal of robotics research, 2024-08, Vol.43 (9), p.1382-1408
issn 0278-3649
1741-3176
language eng
recordid cdi_proquest_journals_3110919063
source SAGE Journals
subjects Automation
Control theory
Dynamic programming
Interactive control
Interactive systems
Motion planning
Multiple robots
Planning
Prediction models
Predictive control
Real-time programming
Robot control
Robot dynamics
Robots
Robust control
Run time (computers)
Safety critical
Shielding
Trajectory planning
Uncertainty
title Active uncertainty reduction for safe and efficient interaction planning: A shielding-aware dual control approach
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-01T07%3A09%3A19IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Active%20uncertainty%20reduction%20for%20safe%20and%20efficient%20interaction%20planning:%20A%20shielding-aware%20dual%20control%20approach&rft.jtitle=The%20International%20journal%20of%20robotics%20research&rft.au=Hu,%20Haimin&rft.date=2024-08-01&rft.volume=43&rft.issue=9&rft.spage=1382&rft.epage=1408&rft.pages=1382-1408&rft.issn=0278-3649&rft.eissn=1741-3176&rft_id=info:doi/10.1177/02783649231215371&rft_dat=%3Cproquest_cross%3E3110919063%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3110919063&rft_id=info:pmid/&rft_sage_id=10.1177_02783649231215371&rfr_iscdi=true