Enabling intelligent energy management for robots using publicly available maps
Energy consumption represents one of the most basic constraints for mobile robot autonomy. We propose a new framework to predict energy consumption using information extracted from publicly available maps. This method avoids having to model internal robot configurations, which are often unavailable,...
| Autors principals: | , , , |
|---|---|
| Format: | Conference item |
| Publicat: |
Institute of Electrical and Electronics Engineers
2016
|
| _version_ | 1826301112751226880 |
|---|---|
| author | Bartlett, O Gurau, C Marchegiani, L Posner, I |
| author_facet | Bartlett, O Gurau, C Marchegiani, L Posner, I |
| author_sort | Bartlett, O |
| collection | OXFORD |
| description | Energy consumption represents one of the most basic constraints for mobile robot autonomy. We propose a new framework to predict energy consumption using information extracted from publicly available maps. This method avoids having to model internal robot configurations, which are often unavailable, while still providing invaluable predictions for both explored and unexplored trajectories. Our approach uses a heteroscedastic Gaussian Process to model the power consumption, which explicitly accounts for variance due to exogenous latent factors such as traffic and weather conditions. We evaluate our framework on 30km of data collected from a city centre environment with a mobile robot travelling on pedestrian walkways. Results across five different test routes show an average difference between predicted and measured power consumption of 3:3%, leading to an average error of 6:6% on predictions of energy consumption. The distinct advantage of our model is our ability to predict measurement variance. The variance predictions improved by 84:3% over a benchmark. |
| first_indexed | 2024-03-07T05:27:27Z |
| format | Conference item |
| id | oxford-uuid:e10e9d1e-ae37-47fc-aa39-fe43f9e75a86 |
| institution | University of Oxford |
| last_indexed | 2024-03-07T05:27:27Z |
| publishDate | 2016 |
| publisher | Institute of Electrical and Electronics Engineers |
| record_format | dspace |
| spelling | oxford-uuid:e10e9d1e-ae37-47fc-aa39-fe43f9e75a862022-03-27T09:51:42ZEnabling intelligent energy management for robots using publicly available mapsConference itemhttp://purl.org/coar/resource_type/c_5794uuid:e10e9d1e-ae37-47fc-aa39-fe43f9e75a86Symplectic Elements at OxfordInstitute of Electrical and Electronics Engineers2016Bartlett, OGurau, CMarchegiani, LPosner, IEnergy consumption represents one of the most basic constraints for mobile robot autonomy. We propose a new framework to predict energy consumption using information extracted from publicly available maps. This method avoids having to model internal robot configurations, which are often unavailable, while still providing invaluable predictions for both explored and unexplored trajectories. Our approach uses a heteroscedastic Gaussian Process to model the power consumption, which explicitly accounts for variance due to exogenous latent factors such as traffic and weather conditions. We evaluate our framework on 30km of data collected from a city centre environment with a mobile robot travelling on pedestrian walkways. Results across five different test routes show an average difference between predicted and measured power consumption of 3:3%, leading to an average error of 6:6% on predictions of energy consumption. The distinct advantage of our model is our ability to predict measurement variance. The variance predictions improved by 84:3% over a benchmark. |
| spellingShingle | Bartlett, O Gurau, C Marchegiani, L Posner, I Enabling intelligent energy management for robots using publicly available maps |
| title | Enabling intelligent energy management for robots using publicly available maps |
| title_full | Enabling intelligent energy management for robots using publicly available maps |
| title_fullStr | Enabling intelligent energy management for robots using publicly available maps |
| title_full_unstemmed | Enabling intelligent energy management for robots using publicly available maps |
| title_short | Enabling intelligent energy management for robots using publicly available maps |
| title_sort | enabling intelligent energy management for robots using publicly available maps |
| work_keys_str_mv | AT bartletto enablingintelligentenergymanagementforrobotsusingpubliclyavailablemaps AT gurauc enablingintelligentenergymanagementforrobotsusingpubliclyavailablemaps AT marchegianil enablingintelligentenergymanagementforrobotsusingpubliclyavailablemaps AT posneri enablingintelligentenergymanagementforrobotsusingpubliclyavailablemaps |