{"id":{"repo_id":"bu","oai_identifier":"oai:open.bu.edu:2144/53015"},"canonical_url":"https://search.ndltd.org/etd/bu/oai:open.bu.edu:2144/53015","repository":{"repo_id":"bu","name":"Boston University","base_url":"https://open.bu.edu/oai/request"},"display":{"title":"DriveMind: a vision-based end-to-end autonomous defensive driver","abstract":"Defensive driving aims to increase the safety of drivers on the road and decrease their likelihood of being involved in an accident. However, autonomous defensive driving remains an under-researched area today, especially in vision-based E2E driving models. This thesis aims to determine if making these models follow defensive driving practices will increase their safety and lower the chances of getting into an accident. This work aims to fill this gap by firstly establishing metrics and thresholds to define a model as a defensive driver. Secondly, I will collect a defensive driving dataset based on the thresholds defined previously. Lastly, I will train and test these models for increased safety and decreased likelihood of getting into an accident based on these metrics. In addition, I will test them on the Bench2drive benchmark to ensure a comprehensive evaluation of the experiments. This work makes extensive use of the CARLA simulator for all data, experiments, benchmarking and tests, making it a closed-loop scenario. Results from the experiments show that there is a considerable increase in the safety of the model “DriveTransformer”. This shows that defensive driving can contribute to the increased safety of autonomous drivers and further highlights the need for these models to prioritize safety.","abstract_html":"Defensive driving aims to increase the safety of drivers on the road and decrease their likelihood of being involved in an accident. However, autonomous defensive driving remains an under-researched area today, especially in vision-based E2E driving models. This thesis aims to determine if making these models follow defensive driving practices will increase their safety and lower the chances of getting into an accident. This work aims to fill this gap by firstly establishing metrics and thresholds to define a model as a defensive driver. Secondly, I will collect a defensive driving dataset based on the thresholds defined previously. Lastly, I will train and test these models for increased safety and decreased likelihood of getting into an accident based on these metrics. In addition, I will test them on the Bench2drive benchmark to ensure a comprehensive evaluation of the experiments. This work makes extensive use of the CARLA simulator for all data, experiments, benchmarking and tests, making it a closed-loop scenario. Results from the experiments show that there is a considerable increase in the safety of the model “DriveTransformer”. This shows that defensive driving can contribute to the increased safety of autonomous drivers and further highlights the need for these models to prioritize safety.","abstract_has_math":false,"creators":["Kingsly, Sujayanand"],"institution":"Boston University","degree_name":"Master of Science","degree_level":"masters","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":["Xiao, Chang"],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026","date_published":"2026","updated_at":"2026-11-18T20:21:28Z","subjects":["Artificial intelligence","Computer science","Autonomous driving","Defensive driving","Simulated driving","Vision-based end-to-end driving"],"languages":["en_US"],"rights":["Attribution-NonCommercial-ShareAlike 4.0 International"],"rights_urls":["http://creativecommons.org/licenses/by-nc-sa/4.0/"],"identifier_entries":[],"person_identifier_entries":[{"key":"dc:identifier.orcid","label":"ORCID","values":["0009-0008-3442-3868"],"render_values":[{"text":"0009-0008-3442-3868","href":"https://orcid.org/0009-0008-3442-3868","code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/2144/53015","outbound_label":"Handle","outbound_source":"dc:identifier.uri","record_url":"https://hdl.handle.net/2144/53015","record_label":"Repository record","record_kind":"handle","record_source":"dc:identifier.uri","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://open.bu.edu/oai/request?verb=GetRecord&metadataPrefix=dim&identifier=oai%3Aopen.bu.edu%3A2144%2F53015","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Xiao, Chang"]},{"key":"dc:creator","label":"Author","values":["Kingsly, Sujayanand"]},{"key":"dc:identifier.orcid","label":"ORCID","values":["0009-0008-3442-3868"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2026-06-02T12:51:18Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2026-06-02T12:51:18Z"]},{"key":"dc:date.issued","label":"Date","values":["2026"]},{"key":"dc:date.updated","label":"Dc Date Updated","values":["2026-06-02T01:09:35Z"]},{"key":"dc:type","label":"Dc Type","values":["Thesis/Dissertation"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Boston University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Artificial intelligence","Computer science","Autonomous driving","Defensive driving","Simulated driving","Vision-based end-to-end driving"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en_US"]},{"key":"dc:rights","label":"Dc Rights","values":["Attribution-NonCommercial-ShareAlike 4.0 International"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://creativecommons.org/licenses/by-nc-sa/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/2144/53015"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["2026"]},{"key":"dc:description.abstract","label":"Abstract","values":["Defensive driving aims to increase the safety of drivers on the road and decrease their likelihood of being involved in an accident. However, autonomous defensive driving remains an under-researched area today, especially in vision-based E2E driving models. This thesis aims to determine if making these models follow defensive driving practices will increase their safety and lower the chances of getting into an accident. This work aims to fill this gap by firstly establishing metrics and thresholds to define a model as a defensive driver. Secondly, I will collect a defensive driving dataset based on the thresholds defined previously. Lastly, I will train and test these models for increased safety and decreased likelihood of getting into an accident based on these metrics. In addition, I will test them on the Bench2drive benchmark to ensure a comprehensive evaluation of the experiments. This work makes extensive use of the CARLA simulator for all data, experiments, benchmarking and tests, making it a closed-loop scenario. Results from the experiments show that there is a considerable increase in the safety of the model “DriveTransformer”. This shows that defensive driving can contribute to the increased safety of autonomous drivers and further highlights the need for these models to prioritize safety."]},{"key":"dc:title","label":"Title","values":["DriveMind: a vision-based end-to-end autonomous defensive driver"]}]}],"canonical_facts":{"dc:contributor.advisor":["Xiao, Chang"],"dc:creator":["Kingsly, Sujayanand"],"dc:date.accessioned":["2026-06-02T12:51:18Z"],"dc:date.available":["2026-06-02T12:51:18Z"],"dc:date.issued":["2026"],"dc:date.updated":["2026-06-02T01:09:35Z"],"dc:description":["2026"],"dc:description.abstract":["Defensive driving aims to increase the safety of drivers on the road and decrease their likelihood of being involved in an accident. However, autonomous defensive driving remains an under-researched area today, especially in vision-based E2E driving models. This thesis aims to determine if making these models follow defensive driving practices will increase their safety and lower the chances of getting into an accident. This work aims to fill this gap by firstly establishing metrics and thresholds to define a model as a defensive driver. Secondly, I will collect a defensive driving dataset based on the thresholds defined previously. Lastly, I will train and test these models for increased safety and decreased likelihood of getting into an accident based on these metrics. In addition, I will test them on the Bench2drive benchmark to ensure a comprehensive evaluation of the experiments. This work makes extensive use of the CARLA simulator for all data, experiments, benchmarking and tests, making it a closed-loop scenario. Results from the experiments show that there is a considerable increase in the safety of the model “DriveTransformer”. This shows that defensive driving can contribute to the increased safety of autonomous drivers and further highlights the need for these models to prioritize safety."],"dc:identifier.orcid":["0009-0008-3442-3868"],"dc:identifier.uri":["https://hdl.handle.net/2144/53015"],"dc:language.iso":["en_US"],"dc:rights":["Attribution-NonCommercial-ShareAlike 4.0 International"],"dc:rights.uri":["http://creativecommons.org/licenses/by-nc-sa/4.0/"],"dc:subject":["Artificial intelligence","Computer science","Autonomous driving","Defensive driving","Simulated driving","Vision-based end-to-end driving"],"dc:title":["DriveMind: a vision-based end-to-end autonomous defensive driver"],"dc:type":["Thesis/Dissertation"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["masters"],"thesis:degree_name":["Master of Science"],"thesis:institution_name":["Boston University"]},"updated_at":"2026-11-18T20:21:28Z"}