Sensor-based reactive symbolic planning in partially known environments
This paper considers the problem of completing assemblies of passive objects in nonconvex environments, cluttered with convex obstacles of unknown position, shape and size that satisfy a specific separation assumption. A differential drive robot equipped with a gripper and a LIDAR sensor, capable of...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2020
|
| Online Access: | https://hdl.handle.net/1721.1/125881 |
| _version_ | 1826200349007937536 |
|---|---|
| author | Vasilopoulos, Vasileios Vega-Brown, William R Arslan, Omur Roy, Nicholas Koditschek, Daniel E. |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Vasilopoulos, Vasileios Vega-Brown, William R Arslan, Omur Roy, Nicholas Koditschek, Daniel E. |
| author_sort | Vasilopoulos, Vasileios |
| collection | MIT |
| description | This paper considers the problem of completing assemblies of passive objects in nonconvex environments, cluttered with convex obstacles of unknown position, shape and size that satisfy a specific separation assumption. A differential drive robot equipped with a gripper and a LIDAR sensor, capable of perceiving its environment only locally, is used to position the passive objects in a desired configuration. The method combines the virtues of a deliberative planner generating high-level, symbolic commands, with the formal guarantees of convergence and obstacle avoidance of a reactive planner that requires little onboard computation and is used online. The validity of the proposed method is verified both with formal proofs and numerical simulations. |
| first_indexed | 2024-09-23T11:35:05Z |
| format | Article |
| id | mit-1721.1/125881 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T11:35:05Z |
| publishDate | 2020 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1258812022-10-01T04:37:02Z Sensor-based reactive symbolic planning in partially known environments Vasilopoulos, Vasileios Vega-Brown, William R Arslan, Omur Roy, Nicholas Koditschek, Daniel E. Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory This paper considers the problem of completing assemblies of passive objects in nonconvex environments, cluttered with convex obstacles of unknown position, shape and size that satisfy a specific separation assumption. A differential drive robot equipped with a gripper and a LIDAR sensor, capable of perceiving its environment only locally, is used to position the passive objects in a desired configuration. The method combines the virtues of a deliberative planner generating high-level, symbolic commands, with the formal guarantees of convergence and obstacle avoidance of a reactive planner that requires little onboard computation and is used online. The validity of the proposed method is verified both with formal proofs and numerical simulations. ARL/GDRS RCTA project (agreement no. W911NF-1020016) AFRL (grant no. FA865015D1845) 2020-06-19T14:35:30Z 2020-06-19T14:35:30Z 2018 2019-10-31T13:48:49Z Article http://purl.org/eprint/type/ConferencePaper 2577-087X https://hdl.handle.net/1721.1/125881 Vasilopoulos, Vasileios, et al., "Sensor-based reactive symbolic planning in partially known environments." 2018 IEEE International Conference on Robotics and Automation (ICRA 2018), Brisbane, Australia, 2018 (Piscataway, N.J.: IEEE, 2018): p. 5683-90 doi 10.1109/ICRA.2018.8460861 en 10.1109/ICRA.2018.8460861 IEEE International Conference on Robotics and Automation 2018 (ICRA 2018) Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) other univ website |
| spellingShingle | Vasilopoulos, Vasileios Vega-Brown, William R Arslan, Omur Roy, Nicholas Koditschek, Daniel E. Sensor-based reactive symbolic planning in partially known environments |
| title | Sensor-based reactive symbolic planning in partially known environments |
| title_full | Sensor-based reactive symbolic planning in partially known environments |
| title_fullStr | Sensor-based reactive symbolic planning in partially known environments |
| title_full_unstemmed | Sensor-based reactive symbolic planning in partially known environments |
| title_short | Sensor-based reactive symbolic planning in partially known environments |
| title_sort | sensor based reactive symbolic planning in partially known environments |
| url | https://hdl.handle.net/1721.1/125881 |
| work_keys_str_mv | AT vasilopoulosvasileios sensorbasedreactivesymbolicplanninginpartiallyknownenvironments AT vegabrownwilliamr sensorbasedreactivesymbolicplanninginpartiallyknownenvironments AT arslanomur sensorbasedreactivesymbolicplanninginpartiallyknownenvironments AT roynicholas sensorbasedreactivesymbolicplanninginpartiallyknownenvironments AT koditschekdaniele sensorbasedreactivesymbolicplanninginpartiallyknownenvironments |