{"id":"https://openalex.org/W2127680665","doi":"https://doi.org/10.1109/ivs.2011.5940478","title":"A case study on learning a steering controller from scratch with reinforcement learning","display_name":"A case study on learning a steering controller from scratch with reinforcement learning","publication_year":2011,"publication_date":"2011-06-01","ids":{"openalex":"https://openalex.org/W2127680665","doi":"https://doi.org/10.1109/ivs.2011.5940478","mag":"2127680665"},"language":"en","primary_location":{"id":"doi:10.1109/ivs.2011.5940478","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ivs.2011.5940478","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008189468","display_name":"Martin Lauer","orcid":"https://orcid.org/0000-0003-4414-5722"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Martin Lauer","raw_affiliation_strings":["Institute of Measurement and Control, Karlsruhe Institute of Technology, Karlsruhe, Germany","Institute of Measurement and Control, Karlsruhe Institute of Technology, 76131, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Measurement and Control, Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Institute of Measurement and Control, Karlsruhe Institute of Technology, 76131, Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5008189468"],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":null,"apc_paid":null,"fwci":0.8552,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.80431381,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"6","issue":null,"first_page":"260","last_page":"265"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9962999820709229,"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"}},{"id":"https://openalex.org/T11236","display_name":"Control Systems and Identification","score":0.9769999980926514,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8586412668228149},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.851306676864624},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.6962504386901855},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6790178418159485},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5773789882659912},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.4773716628551483},{"id":"https://openalex.org/keywords/feedback-control","display_name":"Feedback control","score":0.4435453414916992},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4071149230003357},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3102034330368042},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2185913324356079}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8586412668228149},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.851306676864624},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6962504386901855},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6790178418159485},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5773789882659912},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.4773716628551483},{"id":"https://openalex.org/C3018651601","wikidata":"https://www.wikidata.org/wiki/Q183635","display_name":"Feedback control","level":2,"score":0.4435453414916992},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4071149230003357},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3102034330368042},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2185913324356079},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ivs.2011.5940478","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ivs.2011.5940478","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W166862392","https://openalex.org/W1521322332","https://openalex.org/W1569512666","https://openalex.org/W1949804828","https://openalex.org/W1986014385","https://openalex.org/W2035116228","https://openalex.org/W2036713095","https://openalex.org/W2041225042","https://openalex.org/W2042882799","https://openalex.org/W2096744569","https://openalex.org/W2120346334","https://openalex.org/W2121863487","https://openalex.org/W2125612430","https://openalex.org/W2144304287","https://openalex.org/W2151361137","https://openalex.org/W6606719070","https://openalex.org/W6631124552","https://openalex.org/W6640712829","https://openalex.org/W6677737365"],"related_works":["https://openalex.org/W2475116013","https://openalex.org/W2770018148","https://openalex.org/W2358308169","https://openalex.org/W2385135707","https://openalex.org/W2140315382","https://openalex.org/W2059109728","https://openalex.org/W322691623","https://openalex.org/W2494989134","https://openalex.org/W2509444723","https://openalex.org/W2000675896"],"abstract_inverted_index":{"In":[0],"this":[1],"case":[2,64],"study":[3],"we":[4,61],"show":[5],"how":[6],"reinforcement":[7],"learning":[8,36],"can":[9],"be":[10],"applied":[11],"successfully":[12],"for":[13],"low":[14],"level":[15],"control":[16,23,31,42],"tasks":[17],"in":[18,53],"autonomous":[19],"driving":[20,66,72],"like":[21],"steering":[22],"as":[24,68,70],"an":[25],"alternative":[26],"to":[27],"controllers":[28],"from":[29],"classical":[30,46],"theory.":[32],"We":[33],"describe":[34],"the":[35,40,63],"procedure":[37],"and":[38,55,60],"compare":[39],"resulting":[41],"policies":[43],"with":[44],"a":[45,57],"controller.":[47],"The":[48],"experiments":[49],"are":[50],"made":[51],"both":[52],"simulation":[54],"on":[56],"real":[58],"car":[59],"discuss":[62],"of":[65,71],"forwards":[67],"well":[69],"backwards.":[73]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}