Visibility-Aware Navigation Among Movable Obstacles
We examine the problem of visibility-aware robot navigation among movable obstacles (VANAMO). A variant of the well-known NAMO robotic planning problem, VANAMO puts additional visibility constraints on robot motion and object movability. This new problem formulation lifts the restrictive assumption...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Published: |
Massachusetts Institute of Technology
2023
|
| Online Access: | https://hdl.handle.net/1721.1/150289 |
| _version_ | 1826203821235240960 |
|---|---|
| author | Muguira Iturralde, Jose |
| author2 | Lozano-Pérez, Tomás |
| author_facet | Lozano-Pérez, Tomás Muguira Iturralde, Jose |
| author_sort | Muguira Iturralde, Jose |
| collection | MIT |
| description | We examine the problem of visibility-aware robot navigation among movable obstacles (VANAMO). A variant of the well-known NAMO robotic planning problem, VANAMO puts additional visibility constraints on robot motion and object movability. This new problem formulation lifts the restrictive assumption that the map is fully visible and the object positions are fully known. We provide a formal definition of the VANAMO problem and propose the Look and Manipulate Backchaining (LaMB) algorithm for solving such problems. LaMB has a simple vision-based API that makes it more easily transferable to real-world robot applications and scales to large 3D environments. To evaluate LaMB, we construct a set of tasks that illustrate the complex interplay between visibility and object movability that can arise in mobile base manipulation problems in unknown environments. We show that LaMB outperforms NAMO and visibility-aware motion planning approaches as well as simple combinations of them on complex manipulation problems with partial observability. |
| first_indexed | 2024-09-23T12:43:41Z |
| format | Thesis |
| id | mit-1721.1/150289 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T12:43:41Z |
| publishDate | 2023 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/1502892023-04-01T03:32:29Z Visibility-Aware Navigation Among Movable Obstacles Muguira Iturralde, Jose Lozano-Pérez, Tomás Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science We examine the problem of visibility-aware robot navigation among movable obstacles (VANAMO). A variant of the well-known NAMO robotic planning problem, VANAMO puts additional visibility constraints on robot motion and object movability. This new problem formulation lifts the restrictive assumption that the map is fully visible and the object positions are fully known. We provide a formal definition of the VANAMO problem and propose the Look and Manipulate Backchaining (LaMB) algorithm for solving such problems. LaMB has a simple vision-based API that makes it more easily transferable to real-world robot applications and scales to large 3D environments. To evaluate LaMB, we construct a set of tasks that illustrate the complex interplay between visibility and object movability that can arise in mobile base manipulation problems in unknown environments. We show that LaMB outperforms NAMO and visibility-aware motion planning approaches as well as simple combinations of them on complex manipulation problems with partial observability. M.Eng. 2023-03-31T14:45:24Z 2023-03-31T14:45:24Z 2023-02 2023-02-27T18:43:11.006Z Thesis https://hdl.handle.net/1721.1/150289 In Copyright - Educational Use Permitted Copyright MIT http://rightsstatements.org/page/InC-EDU/1.0/ application/pdf Massachusetts Institute of Technology |
| spellingShingle | Muguira Iturralde, Jose Visibility-Aware Navigation Among Movable Obstacles |
| title | Visibility-Aware Navigation Among Movable
Obstacles |
| title_full | Visibility-Aware Navigation Among Movable
Obstacles |
| title_fullStr | Visibility-Aware Navigation Among Movable
Obstacles |
| title_full_unstemmed | Visibility-Aware Navigation Among Movable
Obstacles |
| title_short | Visibility-Aware Navigation Among Movable
Obstacles |
| title_sort | visibility aware navigation among movable obstacles |
| url | https://hdl.handle.net/1721.1/150289 |
| work_keys_str_mv | AT muguiraiturraldejose visibilityawarenavigationamongmovableobstacles |