When Humans Aren't Optimal Robots that Collaborate with Risk-Aware Humans
In order to collaborate safely and efficiently, robots need to anticipate how their human partners will behave. Some of today's robots model humans as if they were also robots, and assume users are always optimal. Other robots account for human limitations, and relax this assumption so that the...
Saved in:
| Published in: | 2020 15th ACM/IEEE International Conference on Human-Robot Interaction (HRI) pp. 43 - 52 |
|---|---|
| Main Authors: | , , , , , |
| Format: | Conference Proceeding |
| Language: | English |
| Published: |
New York, NY, USA
ACM
09.03.2020
|
| Series: | ACM Conferences |
| Subjects: | |
| ISBN: | 1450367461, 9781450367462 |
| ISSN: | 2167-2148 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | In order to collaborate safely and efficiently, robots need to anticipate how their human partners will behave. Some of today's robots model humans as if they were also robots, and assume users are always optimal. Other robots account for human limitations, and relax this assumption so that the human is noisily rational. Both of these models make sense when the human receives deterministic rewards: i.e., gaining either $100 or $130 with certainty. But in real-world scenarios, rewards are rarely deterministic. Instead, we must make choices subject to risk and uncertainty-and in these settings, humans exhibit a cognitive bias towards suboptimal behavior. For example, when deciding between gaining $100 with certainty or $130 only 80% of the time, people tend to make the risk-averse choice-even though it leads to a lower expected gain! In this paper, we adopt a well-known Risk-Aware human model from behavioral economics called Cumulative Prospect Theory and enable robots to leverage this model during human-robot interaction (HRI). In our user studies, we offer supporting evidence that the Risk-Aware model more accurately predicts suboptimal human behavior. We find that this increased modeling accuracy results in safer and more efficient human-robot collaboration. Overall, we extend existing rational human models so that collaborative robots can anticipate and plan around suboptimal human behavior during HRI. |
|---|---|
| AbstractList | In order to collaborate safely and efficiently, robots need to anticipate how their human partners will behave. Some of today's robots model humans as if they were also robots, and assume users are always optimal. Other robots account for human limitations, and relax this assumption so that the human is noisily rational. Both of these models make sense when the human receives deterministic rewards: i.e., gaining either \100 or \130 with certainty. But in real-world scenarios, rewards are rarely deterministic. Instead, we must make choices subject to risk and uncertainty-and in these settings, humans exhibit a cognitive bias towards suboptimal behavior. For example, when deciding between gaining \100 with certainty or \130 only 80% of the time, people tend to make the risk-averse choice-even though it leads to a lower expected gain! In this paper, we adopt a well-known Risk-Aware human model from behavioral economics called Cumulative Prospect Theory and enable robots to leverage this model during human-robot interaction (HRI). In our user studies, we offer supporting evidence that the Risk-Aware model more accurately predicts suboptimal human behavior. We find that this increased modeling accuracy results in safer and more efficient human-robot collaboration. Overall, we extend existing rational human models so that collaborative robots can anticipate and plan around suboptimal human behavior during HRI. CCS Concepts * Mathematics of computing → Probabilistic inference problems; * Computing methodologies → Cognitive robotics; Theory of mind. ACM Reference Format: Minae Kwon * , Erdem Biyik * , Aditi Talati † , Karan Bhasin ‡ , Dylan P. Losey * , Dorsa Sadigh * . 2020. When Humans Aren't Optimal: Robots that Collaborate with Risk-Aware Humans. In Proceedings of the 2020 ACM/IEEE International Conference on Human-Robot Interaction (HRI '20), March 23-26, 2020, Cambridge, United Kingdom. ACM, New York, NY, USA, 10 pages. https://doi.org/10.1145/3319502.3374832 In order to collaborate safely and efficiently, robots need to anticipate how their human partners will behave. Some of today's robots model humans as if they were also robots, and assume users are always optimal. Other robots account for human limitations, and relax this assumption so that the human is noisily rational. Both of these models make sense when the human receives deterministic rewards: i.e., gaining either $100 or $130 with certainty. But in real-world scenarios, rewards are rarely deterministic. Instead, we must make choices subject to risk and uncertainty-and in these settings, humans exhibit a cognitive bias towards suboptimal behavior. For example, when deciding between gaining $100 with certainty or $130 only 80% of the time, people tend to make the risk-averse choice-even though it leads to a lower expected gain! In this paper, we adopt a well-known Risk-Aware human model from behavioral economics called Cumulative Prospect Theory and enable robots to leverage this model during human-robot interaction (HRI). In our user studies, we offer supporting evidence that the Risk-Aware model more accurately predicts suboptimal human behavior. We find that this increased modeling accuracy results in safer and more efficient human-robot collaboration. Overall, we extend existing rational human models so that collaborative robots can anticipate and plan around suboptimal human behavior during HRI. |
| Author | Biyik, Erdem Kwon, Minae Talati, Aditi Losey, Dylan P. Bhasin, Karan Sadigh, Dorsa |
| Author_xml | – sequence: 1 givenname: Minae surname: Kwon fullname: Kwon, Minae email: minae@cs.stanford.edu organization: Stanford University, Stanford, CA, USA – sequence: 2 givenname: Erdem surname: Biyik fullname: Biyik, Erdem email: ebiyik@stanford.edu organization: Stanford University, Stanford, CA, USA – sequence: 3 givenname: Aditi surname: Talati fullname: Talati, Aditi email: talatiaditi02@gmail.com organization: American High School, Fremont, CA, USA – sequence: 4 givenname: Karan surname: Bhasin fullname: Bhasin, Karan email: karanbhasin03@gmail.com organization: The Harker School, San Jose, CA, USA – sequence: 5 givenname: Dylan P. surname: Losey fullname: Losey, Dylan P. email: dylan.p.losey@gmail.com organization: Stanford University, Stanford, CA, USA – sequence: 6 givenname: Dorsa surname: Sadigh fullname: Sadigh, Dorsa email: dorsa@cs.stanford.edu organization: Stanford University, Stanford, CA, USA |
| BookMark | eNqNkE1Lw0AQQNcvsK09C3rJTS-JOzv7lWMpaoVCL4rHZbOZxWiTlKQe_PeNNAePngbmPWbgTdl50zbE2DXwDECqB0TIFRcZopEWxQmbDluO2kgNp2wiQJtUgLRnf8Elm_f9J-dcWA0ccMJu3j-oSVbftW_6ZNFRc7dPNrt9VfvtFbuIftvTfJwz9vb0-LpcpevN88tysU69yNU-BRWtKVUIMbeUe8iDLkUhoiWlDBCUaIwhEdAoQiNCGNSgAwoRFZa8wBm7Pd6tiMjtuuF39-NyaSUCH-j9kfpQu6Jtv3oH3P0mcGMCNyYY1Oyfqiu6iiIeAE3eVsQ |
| ContentType | Conference Proceeding |
| Copyright | 2020 ACM |
| Copyright_xml | – notice: 2020 ACM |
| DBID | 6IE 6IL CBEJK RIE RIL |
| DOI | 10.1145/3319502.3374832 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Xplore POP ALL IEEE Xplore All Conference Proceedings IEEE/IET Electronic Library IEEE Proceedings Order Plans (POP All) 1998-Present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Economics Engineering |
| EISBN | 1450367461 9781450367462 |
| EISSN | 2167-2148 |
| EndPage | 52 |
| ExternalDocumentID | 9484310 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: Toyota Research Institute funderid: 10.13039/100015599 |
| GroupedDBID | 6IE 6IF 6IL 6IN ABLEC ACM ADPZR ALMA_UNASSIGNED_HOLDINGS APO BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK GUFHI IEGSK LHSKQ OCL RIE RIL AAWTH ADZIZ CHZPO |
| ID | FETCH-LOGICAL-a295t-15f87d5ccf98e9a19c6d2b2f8e5571e1d3777e2c375e372cc5ccc6c322f53d0b3 |
| IEDL.DBID | RIE |
| ISBN | 1450367461 9781450367462 |
| ISICitedReferencesCount | 63 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000570011000006&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| IngestDate | Wed Aug 27 02:40:05 EDT 2025 Sat Jun 15 16:36:36 EDT 2024 Wed Jan 31 06:40:59 EST 2024 |
| IsPeerReviewed | false |
| IsScholarly | false |
| Keywords | cognitive hri cumulative prospect theory human prediction |
| Language | English |
| License | Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from Permissions@acm.org |
| LinkModel | DirectLink |
| MeetingName | HRI '20: ACM/IEEE International Conference on Human-Robot Interaction |
| MergedId | FETCHMERGED-LOGICAL-a295t-15f87d5ccf98e9a19c6d2b2f8e5571e1d3777e2c375e372cc5ccc6c322f53d0b3 |
| PageCount | 10 |
| ParticipantIDs | acm_books_10_1145_3319502_3374832 acm_books_10_1145_3319502_3374832_brief ieee_primary_9484310 |
| PublicationCentury | 2000 |
| PublicationDate | 20200309 2020-March-23 |
| PublicationDateYYYYMMDD | 2020-03-09 2020-03-23 |
| PublicationDate_xml | – month: 03 year: 2020 text: 20200309 day: 09 |
| PublicationDecade | 2020 |
| PublicationPlace | New York, NY, USA |
| PublicationPlace_xml | – name: New York, NY, USA |
| PublicationSeriesTitle | ACM Conferences |
| PublicationTitle | 2020 15th ACM/IEEE International Conference on Human-Robot Interaction (HRI) |
| PublicationTitleAbbrev | HRI |
| PublicationYear | 2020 |
| Publisher | ACM |
| Publisher_xml | – name: ACM |
| SSID | ssj0002861013 ssj0003204102 |
| Score | 2.1393826 |
| Snippet | In order to collaborate safely and efficiently, robots need to anticipate how their human partners will behave. Some of today's robots model humans as if they... |
| SourceID | ieee acm |
| SourceType | Publisher |
| StartPage | 43 |
| SubjectTerms | cognitive HRI Collaboration Computational modeling Computing methodologies -- Artificial intelligence -- Knowledge representation and reasoning -- Cognitive robotics Computing methodologies -- Artificial intelligence -- Philosophical/theoretical foundations of artificial intelligence -- Theory of mind cumulative prospect theory Economics human prediction Human-robot interaction Mathematics of computing -- Probability and statistics -- Probabilistic inference problems Predictive models Probabilistic logic Robot sensing systems |
| Subtitle | Robots that Collaborate with Risk-Aware Humans |
| Title | When Humans Aren't Optimal |
| URI | https://ieeexplore.ieee.org/document/9484310 |
| WOSCitedRecordID | wos000570011000006&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1dS8MwFL1sIqgvfk2dX0QQfLHbmjRN45uIQ3zQMRR8K2lyg0O3ylr175t0dSoI4lsaEiiHJKf3NucegGNqFKKjoSCRigYRt7FrMRnEjGrHeGGU9WxlNiFubpKHBzlowOlcC4OI1eUz7Phm9S_f5PrVp8q6Mkoc37kAvSmEmGm15vkUmrgPgZqa_DOjvSj0l3e2ZwVxeZcxb3lKO8xXXPF2I02lxz9MVSpO6a_-723WoPUlziODOe2sQwMnG7D0KTAuNmDlW43BTbh2x-2EVLn6gpy76ScluXXnxFg9n5FhnuVlQcpHVZKL-YpA4rOzZDgqnoLzdzXFenoL7vuXdxdXQW2gECgqeRmE3CbCcK2tTFCqUOrY0IzaBDkXIYaGORyRaiY4MkG1dkN1rN0et5yZXsa2YGGST3AHSKwwVrGMDA9tJAxzcWFiUHObuS6GURuOHJqpjwyKdCZ25mmNeFoj3oaTP8ek2XSEtg2bHu_0ZVZxI62h3v29ew-WqY-CeyygbB8WyukrHsCifitHxfSwWiYfzy-2EQ |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3ZSsQwFL24gfriruMaQfDF6jRL0_gmoriOIgq-lTS5wUGdkWnV3zfp1FFBEN_SkEA5JDm9tzn3AGxRqxE9DUWp0jTiwiW-xVSUMGo848U8b7rKbEK2Wun9vboegp2BFgYRq8tnuBua1b982zWvIVW2p3jq-c4H6KOCcxr31VqDjApN_adATU7hmdEmj8P1ncV-SVyxx1gwPaW7LNRcCYYjw9o8_7BVqVjleOp_7zMN81_yPHI9IJ4ZGMLOLIx_SoyLWZj8VmVwDs78gdshVba-IAd--nZJrvxJ8ayf9slNN--WBSkfdEkOB2sCScjPkpt28RgdvOse1tPn4e746PbwJKotFCJNlSijWLhUWmGMUykqHSuTWJpTl6IQMsbYMiklUsOkQCapMX6oSYzf5U4w28zZAox0uh1cApJoTHSiuBWx49IyHxmmFo1wue9iyBuw6dHMQmxQZH25s8hqxLMa8QZs_zkmy3ttdA2YC3hnL_2aG1kN9fLv3RswfnJ7eZFdnLbOV2CChpi4ySLKVmGk7L3iGoyZt7Jd9NarJfMBee65WA |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Proceedings+of+the+2020+ACM%2FIEEE+International+Conference+on+Human-Robot+Interaction&rft.atitle=When+Humans+Aren%27t+Optimal&rft.au=Kwon%2C+Minae&rft.au=Biyik%2C+Erdem&rft.au=Talati%2C+Aditi&rft.au=Bhasin%2C+Karan&rft.series=ACM+Conferences&rft.date=2020-03-09&rft.pub=ACM&rft.isbn=1450367461&rft.spage=43&rft.epage=52&rft_id=info:doi/10.1145%2F3319502.3374832 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9781450367462/lc.gif&client=summon&freeimage=true |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9781450367462/mc.gif&client=summon&freeimage=true |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9781450367462/sc.gif&client=summon&freeimage=true |