{"id":246818,"date":"2016-06-30T21:02:46","date_gmt":"2016-07-01T04:02:46","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&#038;p=246818"},"modified":"2018-10-16T21:57:06","modified_gmt":"2018-10-17T04:57:06","slug":"towards-fast-safe-mission-planning-2","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/towards-fast-safe-mission-planning-2\/","title":{"rendered":"Towards Fast Safe Mission Planning"},"content":{"rendered":"<div>Robotic and cyber-physical systems are proliferating at a\u00a0breakneck pace. A key technological hurdle is to ensure safety\u00a0of such systems especially within proximity of humans. While\u00a0there has been a push in identifying obstacles and unsafe situations via sensors and machine learned predictors, the\u00a0task of embedding such information to determine safe course\u00a0while obeying rules-of-the-road is non-trivial. Further, the uncertainty and noise in prediction together with near real-time\u00a0requirements under bounded computation resources makes this\u00a0problem very challenging.\u00a0This work proposes an architecture for fast, safe planning of autonomous missions. We build upon the recent work in Probabilistic Signal Temporal Logic (PrSTL) that synthesizes\u00a0provably safe controllers that take into account noisy sensors\u00a0and associated uncertainty in learned classifier\/regressor predictions. Currently, solution for PrSTL requires solving Mixed\u00a0Integer Semi-Definite Programs (MISDPs), which quickly\u00a0become infeasible to solve in reasonable time as the number of constraints grow. Further, PrSTL needs the description\u00a0of the mission goal and the required safety invariants as\u00a0logical formulations and often expressing such objectives and\u00a0constraints for long horizons and complicated rules-of-the-road remain non-trivial at best.\u00a0We alleviate these problems by combining PrSTL with\u00a0random sampling based planners. We propose using Rapidly-exploring Random Trees (RRT) and associated variants\u00a0like RRT* to simplify computation by first efficiently\u00a0sampling feasible points in the robot\u2019s configuration space\u00a0and then generating trajectories by connecting them via safe\u00a0control. Such fast sampling of the feasible trajectories effectively reduces the optimization from a MISDP to a sequence\u00a0of Second Order Cone Programs (SOCP), which being convex,\u00a0can be solved much more efficiently.<\/div>\n","protected":false},"excerpt":{"rendered":"<p>Robotic and cyber-physical systems are proliferating at a\u00a0breakneck pace. A key technological hurdle is to ensure safety\u00a0of such systems especially within proximity of humans. While\u00a0there has been a push in identifying obstacles and unsafe situations via sensors and machine learned predictors, the\u00a0task of embedding such information to determine safe course\u00a0while obeying rules-of-the-road is non-trivial. Further, [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13556],"msr-publication-type":[193718],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-246818","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us"],"msr_publishername":"","msr_edition":"2016","msr_affiliation":"","msr_published_date":"2016-06-30","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"MSR-TR-2016-18","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"Technical Report","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"246815","msr_publicationurl":"https:\/\/www.dropbox.com\/s\/q64b63ql6a587y7\/safe_mission_planning_workshop.pdf?dl=0","msr_doi":"","msr_publication_uploader":[{"type":"file","title":"ijcai_submitted","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/06\/ijcai_submitted.pdf","id":246815,"label_id":0},{"type":"url","title":"https:\/\/www.dropbox.com\/s\/q64b63ql6a587y7\/safe_mission_planning_workshop.pdf?dl=0","viewUrl":false,"id":false,"label_id":0}],"msr_related_uploader":"","msr_attachments":[{"id":0,"url":"https:\/\/www.dropbox.com\/s\/q64b63ql6a587y7\/safe_mission_planning_workshop.pdf?dl=0"}],"msr-author-ordering":[{"type":"user_nicename","value":"dedey","user_id":31594,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=dedey"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[237595,144633],"msr_project":[],"publication":[],"video":[],"download":[],"msr_publication_type":"techreport","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/246818"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":3,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/246818\/revisions"}],"predecessor-version":[{"id":540583,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/246818\/revisions\/540583"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=246818"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=246818"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=246818"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=246818"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=246818"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=246818"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=246818"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=246818"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=246818"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=246818"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=246818"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=246818"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=246818"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=246818"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=246818"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}