Robots that Learn to Safely Influence via Prediction-Informed Reach-Avoid Dynamic Games Article Swipe
Ravi Pandya
,
Changliu Liu
,
Andrea Bajcsy
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2409.12153
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2409.12153
Robots can influence people to accomplish their tasks more efficiently: autonomous cars can inch forward at an intersection to pass through, and tabletop manipulators can go for an object on the table first. However, a robot's ability to influence can also compromise the safety of nearby people if naively executed. In this work, we pose and solve a novel robust reach-avoid dynamic game which enables robots to be maximally influential, but only when a safety backup control exists. On the human side, we model the human's behavior as goal-driven but conditioned on the robot's plan, enabling us to capture influence. On the robot side, we solve the dynamic game in the joint physical and belief space, enabling the robot to reason about how its uncertainty in human behavior will evolve over time. We instantiate our method, called SLIDE (Safely Leveraging Influence in Dynamic Environments), in a high-dimensional (39-D) simulated human-robot collaborative manipulation task solved via offline game-theoretic reinforcement learning. We compare our approach to a robust baseline that treats the human as a worst-case adversary, a safety controller that does not explicitly reason about influence, and an energy-function-based safety shield. We find that SLIDE consistently enables the robot to leverage the influence it has on the human when it is safe to do so, ultimately allowing the robot to be less conservative while still ensuring a high safety rate during task execution.
Related Topics
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2409.12153
- https://arxiv.org/pdf/2409.12153
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4403746711
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4403746711Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2409.12153Digital Object Identifier
- Title
-
Robots that Learn to Safely Influence via Prediction-Informed Reach-Avoid Dynamic GamesWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-09-18Full publication date if available
- Authors
-
Ravi Pandya, Changliu Liu, Andrea BajcsyList of authors in order
- Landing page
-
https://arxiv.org/abs/2409.12153Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2409.12153Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2409.12153Direct OA link when available
- Concepts
-
Computer science, Robot, Artificial intelligence, Human–computer interactionTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4403746711 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2409.12153 |
| ids.doi | https://doi.org/10.48550/arxiv.2409.12153 |
| ids.openalex | https://openalex.org/W4403746711 |
| fwci | |
| type | preprint |
| title | Robots that Learn to Safely Influence via Prediction-Informed Reach-Avoid Dynamic Games |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10462 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9818999767303467 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Reinforcement Learning in Robotics |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.5359744429588318 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C90509273 |
| concepts[1].level | 2 |
| concepts[1].score | 0.4637155532836914 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q11012 |
| concepts[1].display_name | Robot |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.3891848921775818 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C107457646 |
| concepts[3].level | 1 |
| concepts[3].score | 0.3596900403499603 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q207434 |
| concepts[3].display_name | Human–computer interaction |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.5359744429588318 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/robot |
| keywords[1].score | 0.4637155532836914 |
| keywords[1].display_name | Robot |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.3891848921775818 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/human–computer-interaction |
| keywords[3].score | 0.3596900403499603 |
| keywords[3].display_name | Human–computer interaction |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2409.12153 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2409.12153 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2409.12153 |
| locations[1].id | doi:10.48550/arxiv.2409.12153 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2409.12153 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5055091245 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-0258-4604 |
| authorships[0].author.display_name | Ravi Pandya |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Pandya, Ravi |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5040156274 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-3767-5517 |
| authorships[1].author.display_name | Changliu Liu |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Liu, Changliu |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5050279893 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-7969-9376 |
| authorships[2].author.display_name | Andrea Bajcsy |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Bajcsy, Andrea |
| authorships[2].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2409.12153 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2024-10-25T00:00:00 |
| display_name | Robots that Learn to Safely Influence via Prediction-Informed Reach-Avoid Dynamic Games |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10462 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9818999767303467 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Reinforcement Learning in Robotics |
| related_works | https://openalex.org/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W2390279801, https://openalex.org/W4391913857, https://openalex.org/W2358668433, https://openalex.org/W4396701345, https://openalex.org/W2376932109, https://openalex.org/W2001405890, https://openalex.org/W4396696052 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2409.12153 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2409.12153 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2409.12153 |
| primary_location.id | pmh:oai:arXiv.org:2409.12153 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2409.12153 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2409.12153 |
| publication_date | 2024-09-18 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 34, 57, 73, 145, 164, 172, 175, 225 |
| abstract_inverted_index.In | 50 |
| abstract_inverted_index.On | 78, 100 |
| abstract_inverted_index.We | 132, 159, 190 |
| abstract_inverted_index.an | 16, 27, 186 |
| abstract_inverted_index.as | 87, 171 |
| abstract_inverted_index.at | 15 |
| abstract_inverted_index.be | 67, 219 |
| abstract_inverted_index.do | 212 |
| abstract_inverted_index.go | 25 |
| abstract_inverted_index.if | 47 |
| abstract_inverted_index.in | 109, 125, 141, 144 |
| abstract_inverted_index.is | 209 |
| abstract_inverted_index.it | 202, 208 |
| abstract_inverted_index.of | 44 |
| abstract_inverted_index.on | 29, 91, 204 |
| abstract_inverted_index.to | 4, 18, 37, 66, 97, 119, 163, 198, 211, 218 |
| abstract_inverted_index.us | 96 |
| abstract_inverted_index.we | 53, 82, 104 |
| abstract_inverted_index.and | 21, 55, 113, 185 |
| abstract_inverted_index.but | 70, 89 |
| abstract_inverted_index.can | 1, 12, 24, 39 |
| abstract_inverted_index.for | 26 |
| abstract_inverted_index.has | 203 |
| abstract_inverted_index.how | 122 |
| abstract_inverted_index.its | 123 |
| abstract_inverted_index.not | 180 |
| abstract_inverted_index.our | 134, 161 |
| abstract_inverted_index.so, | 213 |
| abstract_inverted_index.the | 30, 42, 79, 84, 92, 101, 106, 110, 117, 169, 196, 200, 205, 216 |
| abstract_inverted_index.via | 154 |
| abstract_inverted_index.also | 40 |
| abstract_inverted_index.cars | 11 |
| abstract_inverted_index.does | 179 |
| abstract_inverted_index.find | 191 |
| abstract_inverted_index.game | 62, 108 |
| abstract_inverted_index.high | 226 |
| abstract_inverted_index.inch | 13 |
| abstract_inverted_index.less | 220 |
| abstract_inverted_index.more | 8 |
| abstract_inverted_index.only | 71 |
| abstract_inverted_index.over | 130 |
| abstract_inverted_index.pass | 19 |
| abstract_inverted_index.pose | 54 |
| abstract_inverted_index.rate | 228 |
| abstract_inverted_index.safe | 210 |
| abstract_inverted_index.task | 152, 230 |
| abstract_inverted_index.that | 167, 178, 192 |
| abstract_inverted_index.this | 51 |
| abstract_inverted_index.when | 72, 207 |
| abstract_inverted_index.will | 128 |
| abstract_inverted_index.SLIDE | 137, 193 |
| abstract_inverted_index.about | 121, 183 |
| abstract_inverted_index.human | 80, 126, 170, 206 |
| abstract_inverted_index.joint | 111 |
| abstract_inverted_index.model | 83 |
| abstract_inverted_index.novel | 58 |
| abstract_inverted_index.plan, | 94 |
| abstract_inverted_index.robot | 102, 118, 197, 217 |
| abstract_inverted_index.side, | 81, 103 |
| abstract_inverted_index.solve | 56, 105 |
| abstract_inverted_index.still | 223 |
| abstract_inverted_index.table | 31 |
| abstract_inverted_index.tasks | 7 |
| abstract_inverted_index.their | 6 |
| abstract_inverted_index.time. | 131 |
| abstract_inverted_index.which | 63 |
| abstract_inverted_index.while | 222 |
| abstract_inverted_index.work, | 52 |
| abstract_inverted_index.(39-D) | 147 |
| abstract_inverted_index.Robots | 0 |
| abstract_inverted_index.backup | 75 |
| abstract_inverted_index.belief | 114 |
| abstract_inverted_index.called | 136 |
| abstract_inverted_index.during | 229 |
| abstract_inverted_index.evolve | 129 |
| abstract_inverted_index.first. | 32 |
| abstract_inverted_index.nearby | 45 |
| abstract_inverted_index.object | 28 |
| abstract_inverted_index.people | 3, 46 |
| abstract_inverted_index.reason | 120, 182 |
| abstract_inverted_index.robots | 65 |
| abstract_inverted_index.robust | 59, 165 |
| abstract_inverted_index.safety | 43, 74, 176, 188, 227 |
| abstract_inverted_index.solved | 153 |
| abstract_inverted_index.space, | 115 |
| abstract_inverted_index.treats | 168 |
| abstract_inverted_index.(Safely | 138 |
| abstract_inverted_index.Dynamic | 142 |
| abstract_inverted_index.ability | 36 |
| abstract_inverted_index.capture | 98 |
| abstract_inverted_index.compare | 160 |
| abstract_inverted_index.control | 76 |
| abstract_inverted_index.dynamic | 61, 107 |
| abstract_inverted_index.enables | 64, 195 |
| abstract_inverted_index.exists. | 77 |
| abstract_inverted_index.forward | 14 |
| abstract_inverted_index.human's | 85 |
| abstract_inverted_index.method, | 135 |
| abstract_inverted_index.naively | 48 |
| abstract_inverted_index.offline | 155 |
| abstract_inverted_index.robot's | 35, 93 |
| abstract_inverted_index.shield. | 189 |
| abstract_inverted_index.However, | 33 |
| abstract_inverted_index.allowing | 215 |
| abstract_inverted_index.approach | 162 |
| abstract_inverted_index.baseline | 166 |
| abstract_inverted_index.behavior | 86, 127 |
| abstract_inverted_index.enabling | 95, 116 |
| abstract_inverted_index.ensuring | 224 |
| abstract_inverted_index.leverage | 199 |
| abstract_inverted_index.physical | 112 |
| abstract_inverted_index.tabletop | 22 |
| abstract_inverted_index.through, | 20 |
| abstract_inverted_index.Influence | 140 |
| abstract_inverted_index.executed. | 49 |
| abstract_inverted_index.influence | 2, 38, 201 |
| abstract_inverted_index.learning. | 158 |
| abstract_inverted_index.maximally | 68 |
| abstract_inverted_index.simulated | 148 |
| abstract_inverted_index.Leveraging | 139 |
| abstract_inverted_index.accomplish | 5 |
| abstract_inverted_index.adversary, | 174 |
| abstract_inverted_index.autonomous | 10 |
| abstract_inverted_index.compromise | 41 |
| abstract_inverted_index.controller | 177 |
| abstract_inverted_index.execution. | 231 |
| abstract_inverted_index.explicitly | 181 |
| abstract_inverted_index.influence, | 184 |
| abstract_inverted_index.influence. | 99 |
| abstract_inverted_index.ultimately | 214 |
| abstract_inverted_index.worst-case | 173 |
| abstract_inverted_index.conditioned | 90 |
| abstract_inverted_index.goal-driven | 88 |
| abstract_inverted_index.human-robot | 149 |
| abstract_inverted_index.instantiate | 133 |
| abstract_inverted_index.reach-avoid | 60 |
| abstract_inverted_index.uncertainty | 124 |
| abstract_inverted_index.conservative | 221 |
| abstract_inverted_index.consistently | 194 |
| abstract_inverted_index.efficiently: | 9 |
| abstract_inverted_index.influential, | 69 |
| abstract_inverted_index.intersection | 17 |
| abstract_inverted_index.manipulation | 151 |
| abstract_inverted_index.manipulators | 23 |
| abstract_inverted_index.collaborative | 150 |
| abstract_inverted_index.reinforcement | 157 |
| abstract_inverted_index.Environments), | 143 |
| abstract_inverted_index.game-theoretic | 156 |
| abstract_inverted_index.high-dimensional | 146 |
| abstract_inverted_index.energy-function-based | 187 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile |