{"id":{"repo_id":"nus","oai_identifier":"oai:scholarbank.nus.edu.sg:10635/164175"},"canonical_url":"https://search.dev.ndltd.org/etd/nus/oai:scholarbank.nus.edu.sg:10635/164175","repository":{"repo_id":"nus","name":"National University of Singapore","base_url":"https://scholarbank.nus.edu.sg/oai/request"},"display":{"title":"INFORMATION BASED ADAPTIVE PATH PLANNING AND SAMPLING FOR ENVIRONMENT MONITORING","abstract":"In this work, we present a comprehensive approach for both monitoring and physical sample collection for understanding the environmental processes. We first explain the two adaptive planning algorithms for estimating scalar environmental fields with bounds on the mission time. These algorithms adapt the path during the mission based on the recently collected information. We use Sparse Gaussian Processes for field estimation and our planning framework for coordinating a single robot or a team of robots. Moreover, we examine the biological relevance of the field estimated using such frameworks. This work also presents a solution to the problem of simultaneous sampling and monitoring of an environmental field. Finally, this work explains a data-driven framework for system identification of AUVs. The performance of all these algorithms are benchmarked against standard approaches in simulation and some are validated through field experiments. We show that all of our frameworks outperform the conventional methods.","abstract_html":"In this work, we present a comprehensive approach for both monitoring and physical sample collection for understanding the environmental processes. We first explain the two adaptive planning algorithms for estimating scalar environmental fields with bounds on the mission time. These algorithms adapt the path during the mission based on the recently collected information. We use Sparse Gaussian Processes for field estimation and our planning framework for coordinating a single robot or a team of robots. Moreover, we examine the biological relevance of the field estimated using such frameworks. This work also presents a solution to the problem of simultaneous sampling and monitoring of an environmental field. Finally, this work explains a data-driven framework for system identification of AUVs. The performance of all these algorithms are benchmarked against standard approaches in simulation and some are validated through field experiments. We show that all of our frameworks outperform the conventional methods.","abstract_has_math":false,"creators":["RAJAT MISHRA"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2019,"date_issued":"2019-08-22","date_published":"2019-08-22","updated_at":"2026-07-24T03:32:43Z","subjects":["informative path planning, multi-robot planning, sampling and monitoring, online adaptive planning, environmental monitoring, kernel based planning"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["RAJAT MISHRA"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.issued","label":"Date","values":["2019-08-22"]},{"key":"dc:relation.isreferencedby","label":"Dc Relation Isreferencedby","values":["https://scholarbank.nus.edu.sg/handle/10635/164175"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["informative path planning, multi-robot planning, sampling and monitoring, online adaptive planning, environmental monitoring, kernel based planning"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://scholarbank.nus.edu.sg/bitstreams/03208577-e225-4014-a276-27037b0968a8/download"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["In this work, we present a comprehensive approach for both monitoring and physical sample collection for understanding the environmental processes. We first explain the two adaptive planning algorithms for estimating scalar environmental fields with bounds on the mission time. These algorithms adapt the path during the mission based on the recently collected information. We use Sparse Gaussian Processes for field estimation and our planning framework for coordinating a single robot or a team of robots. Moreover, we examine the biological relevance of the field estimated using such frameworks. This work also presents a solution to the problem of simultaneous sampling and monitoring of an environmental field. Finally, this work explains a data-driven framework for system identification of AUVs. The performance of all these algorithms are benchmarked against standard approaches in simulation and some are validated through field experiments. We show that all of our frameworks outperform the conventional methods."]},{"key":"dc:format.checksum.md5","label":"Dc Format Checksum Md5","values":["862dd530b00af1e7308ff402740b4a40","faadd2c3c99eaa99f9bf16ec8a751f1d"]},{"key":"dc:title","label":"Title","values":["INFORMATION BASED ADAPTIVE PATH PLANNING AND SAMPLING FOR ENVIRONMENT MONITORING"]}]}],"canonical_facts":{"dc:creator":["RAJAT MISHRA"],"dc:date.issued":["2019-08-22"],"dc:description.abstract":["In this work, we present a comprehensive approach for both monitoring and physical sample collection for understanding the environmental processes. We first explain the two adaptive planning algorithms for estimating scalar environmental fields with bounds on the mission time. These algorithms adapt the path during the mission based on the recently collected information. We use Sparse Gaussian Processes for field estimation and our planning framework for coordinating a single robot or a team of robots. Moreover, we examine the biological relevance of the field estimated using such frameworks. This work also presents a solution to the problem of simultaneous sampling and monitoring of an environmental field. Finally, this work explains a data-driven framework for system identification of AUVs. The performance of all these algorithms are benchmarked against standard approaches in simulation and some are validated through field experiments. We show that all of our frameworks outperform the conventional methods."],"dc:format.checksum.md5":["862dd530b00af1e7308ff402740b4a40","faadd2c3c99eaa99f9bf16ec8a751f1d"],"dc:identifier.uri":["https://scholarbank.nus.edu.sg/bitstreams/03208577-e225-4014-a276-27037b0968a8/download"],"dc:relation.isreferencedby":["https://scholarbank.nus.edu.sg/handle/10635/164175"],"dc:subject":["informative path planning, multi-robot planning, sampling and monitoring, online adaptive planning, environmental monitoring, kernel based planning"],"dc:title":["INFORMATION BASED ADAPTIVE PATH PLANNING AND SAMPLING FOR ENVIRONMENT MONITORING"],"dc:type":["Thesis"]},"updated_at":"2026-07-24T03:32:43Z"}