Simultaneous scene reconstruction and whole-body motion planning for safe operation in dynamic environments
Recent work has demonstrated real-time mapping and reconstruction from dense perception, while motion planning based on distance fields has been shown to achieve fast, collision-free motion synthesis with good convergence properties. However, demonstration of a fully integrated system that can safel...
| Principais autores: | , , |
|---|---|
| Formato: | Conference item |
| Idioma: | English |
| Publicado em: |
Institute of Electrical and Electronics Engineers
2021
|
| _version_ | 1826267757370408960 |
|---|---|
| author | Finean, MN Merkt, W Havoutis, I |
| author_facet | Finean, MN Merkt, W Havoutis, I |
| author_sort | Finean, MN |
| collection | OXFORD |
| description | Recent work has demonstrated real-time mapping and reconstruction from dense perception, while motion planning based on distance fields has been shown to achieve fast, collision-free motion synthesis with good convergence properties. However, demonstration of a fully integrated system that can safely re-plan in unknown environments, in the presence of static and dynamic obstacles, has remained an open challenge. In this work, we first study the impact that signed and unsigned distance fields have on optimisation convergence, and the resultant error cost in trajectory optimisation problems in 2D path planning, arm manipulator motion planning, and whole-body loco-manipulation planning. We further analyse the performance of three state-of-the-art approaches to generating distance fields (Voxblox, Fiesta, and GPU-Voxels) for use in realtime environment reconstruction. Finally, we use our findings to construct a practical hybrid mapping and motion planning system which uses GPU-Voxels and GPMP2 to perform receding- horizon whole-body motion planning that can smoothly avoid moving obstacles in 3D space using live sensor data. Our results are validated in simulation and on a real-world Toyota Human Support Robot (HSR).
|
| first_indexed | 2024-03-06T20:59:06Z |
| format | Conference item |
| id | oxford-uuid:3a4308a3-56ef-44b8-9281-f27229e16d14 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-06T20:59:06Z |
| publishDate | 2021 |
| publisher | Institute of Electrical and Electronics Engineers |
| record_format | dspace |
| spelling | oxford-uuid:3a4308a3-56ef-44b8-9281-f27229e16d142022-03-26T14:00:34ZSimultaneous scene reconstruction and whole-body motion planning for safe operation in dynamic environmentsConference itemhttp://purl.org/coar/resource_type/c_5794uuid:3a4308a3-56ef-44b8-9281-f27229e16d14EnglishSymplectic ElementsInstitute of Electrical and Electronics Engineers2021Finean, MNMerkt, WHavoutis, IRecent work has demonstrated real-time mapping and reconstruction from dense perception, while motion planning based on distance fields has been shown to achieve fast, collision-free motion synthesis with good convergence properties. However, demonstration of a fully integrated system that can safely re-plan in unknown environments, in the presence of static and dynamic obstacles, has remained an open challenge. In this work, we first study the impact that signed and unsigned distance fields have on optimisation convergence, and the resultant error cost in trajectory optimisation problems in 2D path planning, arm manipulator motion planning, and whole-body loco-manipulation planning. We further analyse the performance of three state-of-the-art approaches to generating distance fields (Voxblox, Fiesta, and GPU-Voxels) for use in realtime environment reconstruction. Finally, we use our findings to construct a practical hybrid mapping and motion planning system which uses GPU-Voxels and GPMP2 to perform receding- horizon whole-body motion planning that can smoothly avoid moving obstacles in 3D space using live sensor data. Our results are validated in simulation and on a real-world Toyota Human Support Robot (HSR). |
| spellingShingle | Finean, MN Merkt, W Havoutis, I Simultaneous scene reconstruction and whole-body motion planning for safe operation in dynamic environments |
| title | Simultaneous scene reconstruction and whole-body motion planning for safe operation in dynamic environments |
| title_full | Simultaneous scene reconstruction and whole-body motion planning for safe operation in dynamic environments |
| title_fullStr | Simultaneous scene reconstruction and whole-body motion planning for safe operation in dynamic environments |
| title_full_unstemmed | Simultaneous scene reconstruction and whole-body motion planning for safe operation in dynamic environments |
| title_short | Simultaneous scene reconstruction and whole-body motion planning for safe operation in dynamic environments |
| title_sort | simultaneous scene reconstruction and whole body motion planning for safe operation in dynamic environments |
| work_keys_str_mv | AT fineanmn simultaneousscenereconstructionandwholebodymotionplanningforsafeoperationindynamicenvironments AT merktw simultaneousscenereconstructionandwholebodymotionplanningforsafeoperationindynamicenvironments AT havoutisi simultaneousscenereconstructionandwholebodymotionplanningforsafeoperationindynamicenvironments |