{"id":"https://openalex.org/W7165151423","doi":"https://doi.org/10.1007/s11370-026-00727-0","title":"Speech-to-trajectory: learning intuitive verbal guidance for robot motion","display_name":"Speech-to-trajectory: learning intuitive verbal guidance for robot motion","publication_year":2026,"publication_date":"2026-06-19","ids":{"openalex":"https://openalex.org/W7165151423","doi":"https://doi.org/10.1007/s11370-026-00727-0"},"language":"en","primary_location":{"id":"doi:10.1007/s11370-026-00727-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11370-026-00727-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11370-026-00727-0.pdf","source":{"id":"https://openalex.org/S145649206","display_name":"Intelligent Service Robotics","issn_l":"1861-2776","issn":["1861-2776","1861-2784"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligent Service Robotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11370-026-00727-0.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047551572","display_name":"Eran Bamani","orcid":"https://orcid.org/0000-0001-5007-3134"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Eran Beeri Bamani","raw_affiliation_strings":["Tel Aviv University, Iby and Aladar Fleischman Faculty of Engineering, Tel-Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tel Aviv University, Iby and Aladar Fleischman Faculty of Engineering, Tel-Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092427282","display_name":"Eden Nissinman","orcid":"https://orcid.org/0009-0006-4937-2675"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Eden Nissinman","raw_affiliation_strings":["Tel Aviv University, Iby and Aladar Fleischman Faculty of Engineering, Tel-Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tel Aviv University, Iby and Aladar Fleischman Faculty of Engineering, Tel-Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114658287","display_name":"Rotem Atari","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Rotem Atari","raw_affiliation_strings":["Tel Aviv University, Iby and Aladar Fleischman Faculty of Engineering, Tel-Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tel Aviv University, Iby and Aladar Fleischman Faculty of Engineering, Tel-Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097605576","display_name":"Nevo Heimann Saadon","orcid":"https://orcid.org/0009-0008-6573-9806"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Nevo Heimann Saadon","raw_affiliation_strings":["Tel Aviv University, Iby and Aladar Fleischman Faculty of Engineering, Tel-Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tel Aviv University, Iby and Aladar Fleischman Faculty of Engineering, Tel-Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030565378","display_name":"Avishai Sintov","orcid":"https://orcid.org/0000-0002-3320-3897"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Avishai Sintov","raw_affiliation_strings":["Tel Aviv University, Iby and Aladar Fleischman Faculty of Engineering, Tel-Aviv, Israel"],"raw_orcid":"https://orcid.org/0000-0002-3320-3897","affiliations":[{"raw_affiliation_string":"Tel Aviv University, Iby and Aladar Fleischman Faculty of Engineering, Tel-Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5030565378"],"corresponding_institution_ids":["https://openalex.org/I16391192"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94994458,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"19","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.3659000098705292,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.3659000098705292,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.30390000343322754,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.12399999797344208,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7077999711036682},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5813000202178955},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5644999742507935},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5062000155448914},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4535999894142151},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.3813000023365021},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.37880000472068787},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.375900000333786},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3691999912261963},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.3571000099182129}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8676999807357788},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7077999711036682},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5813000202178955},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5644999742507935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5583000183105469},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5062000155448914},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4535999894142151},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43230000138282776},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3813000023365021},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.37880000472068787},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3571000099182129},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.3441999852657318},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3278000056743622},{"id":"https://openalex.org/C2776228582","wikidata":"https://www.wikidata.org/wiki/Q7455797","display_name":"Service robot","level":3,"score":0.31349998712539673},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.29750001430511475},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2973000109195709},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.2957000136375427},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.2919999957084656},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.29170000553131104},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.2892000079154968},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.2606000006198883},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11370-026-00727-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11370-026-00727-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11370-026-00727-0.pdf","source":{"id":"https://openalex.org/S145649206","display_name":"Intelligent Service Robotics","issn_l":"1861-2776","issn":["1861-2776","1861-2784"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligent Service Robotics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11370-026-00727-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11370-026-00727-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11370-026-00727-0.pdf","source":{"id":"https://openalex.org/S145649206","display_name":"Intelligent Service Robotics","issn_l":"1861-2776","issn":["1861-2776","1861-2784"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligent Service Robotics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5801064372062683}],"awards":[{"id":"https://openalex.org/G1425584851","display_name":null,"funder_award_id":"77857","funder_id":"https://openalex.org/F4704393691","funder_display_name":"Israel Innovation Authority"}],"funders":[{"id":"https://openalex.org/F4320322596","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49"},{"id":"https://openalex.org/F4704393691","display_name":"Israel Innovation Authority","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7165151423.pdf","grobid_xml":"https://content.openalex.org/works/W7165151423.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W1534120332","https://openalex.org/W2001006503","https://openalex.org/W2019178608","https://openalex.org/W2110683152","https://openalex.org/W2236233024","https://openalex.org/W2906798544","https://openalex.org/W2963507484","https://openalex.org/W2963800628","https://openalex.org/W2963868408","https://openalex.org/W2964287316","https://openalex.org/W3094094526","https://openalex.org/W3128513378","https://openalex.org/W3146772526","https://openalex.org/W3153451655","https://openalex.org/W3165654247","https://openalex.org/W3197893554","https://openalex.org/W3206377389","https://openalex.org/W3208699867","https://openalex.org/W3214319339","https://openalex.org/W4205178067","https://openalex.org/W4285310604","https://openalex.org/W4293499155","https://openalex.org/W4313952519","https://openalex.org/W4327545654","https://openalex.org/W4366085321","https://openalex.org/W4383108296","https://openalex.org/W4383617059","https://openalex.org/W4385403811","https://openalex.org/W4386735629","https://openalex.org/W4387652952","https://openalex.org/W4389266910","https://openalex.org/W4389519448","https://openalex.org/W4391948801","https://openalex.org/W4394904126","https://openalex.org/W4399767172","https://openalex.org/W4400118870","https://openalex.org/W4401344867","https://openalex.org/W4401414621","https://openalex.org/W4401415075","https://openalex.org/W4403277141","https://openalex.org/W4404920389","https://openalex.org/W4405785122","https://openalex.org/W4405787555","https://openalex.org/W4406014676","https://openalex.org/W4407951437","https://openalex.org/W4408786008","https://openalex.org/W4414198610","https://openalex.org/W4416609185","https://openalex.org/W7128196075"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Enabling":[1],"intuitive,":[2],"low-level":[3,67],"robot":[4,68],"control":[5,89,202],"through":[6],"natural":[7],"spoken":[8,86],"language":[9,53,134],"is":[10,72,118],"essential":[11],"for":[12,31,156,199],"deploying":[13],"service":[14,204],"robots":[15,32,205],"in":[16,80,162],"everyday":[17],"environments.":[18],"However,":[19],"verbal":[20,64],"commands":[21],"are":[22],"inherently":[23],"variable":[24],"and":[25,36,88,124,142,165,184],"often":[26,143],"ambiguous,":[27],"making":[28],"it":[29],"difficult":[30],"to":[33,66,121],"consistently":[34],"interpret":[35],"execute":[37],"them":[38],"without":[39,187],"extensive":[40],"handcrafted":[41],"rules":[42],"or":[43,191],"predefined":[44],"templates.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49,99],"present":[50],"the":[51,90,110],"directive":[52],"model":[54,135],"(DLM),":[55],"a":[56,167,175],"novel":[57],"speech-to-trajectory":[58],"framework":[59],"that":[60,108,127,138,171],"directly":[61],"maps":[62],"unconstrained":[63],"instructions":[65],"motion":[69,92,150],"trajectories.":[70],"DLM":[71,147,172,197],"trained":[73],"using":[74],"behavior":[75],"cloning":[76],"(BC)":[77],"on":[78,166,189],"demonstrations":[79],"simulation,":[81],"where":[82],"human":[83],"participants":[84],"issue":[85],"guidance":[87],"robot\u2019s":[91],"accordingly.":[93],"To":[94],"improve":[95],"generalization":[96],"across":[97],"phrasings,":[98],"apply":[100],"semantic":[101],"augmentation":[102],"via":[103],"GPT-4,":[104],"generating":[105],"diverse":[106],"paraphrases":[107],"share":[109],"same":[111],"trajectory":[112],"labels.":[113],"A":[114],"text-conditioned":[115],"diffusion":[116],"policy":[117],"then":[119],"employed":[120],"generate":[122],"smooth":[123],"flexible":[125],"trajectories":[126],"align":[128],"with":[129,152,207],"user":[130,179],"intent.":[131],"Unlike":[132],"large":[133],"(LLM)-based":[136],"approaches":[137],"require":[139],"prompt":[140],"engineering":[141],"yield":[144],"unpredictable":[145],"responses,":[146],"ensures":[148],"consistent":[149],"generation":[151],"efficient":[153],"inference":[154],"suitable":[155],"onboard":[157],"deployment.":[158],"Our":[159],"results,":[160],"validated":[161],"both":[163],"simulation":[164],"quadruped":[168],"robot,":[169],"show":[170],"robustly":[173],"interprets":[174],"wide":[176],"range":[177],"of":[178,203],"commands,":[180],"including":[181],"paraphrased,":[182],"truncated,":[183],"implicit":[185],"instructions,":[186],"relying":[188],"perception":[190],"symbolic":[192],"planning.":[193],"These":[194],"capabilities":[195],"make":[196],"well-suited":[198],"natural,":[200],"speech-based":[201],"interacting":[206],"untrained":[208],"users.":[209]},"counts_by_year":[],"updated_date":"2026-06-20T20:08:15.867695","created_date":"2026-06-19T00:00:00"}
