Stream-based perception for cognitive agents in mobile ecosystems
Cognitive agent abstractions can help to engineer intelligent systems across mobile devices. On smartphones, the data obtained from onboard sensors can give valuable insights into the user’s current situation. Unfortunately, today’s cognitive agent frameworks cannot cope well with the challenging ch...
| Authors: | ; ; ; |
|---|---|
| Format: | Article |
| Publication date: | 2019 |
| Country: | España |
| Institution: | Universidad Rey Juan Carlos |
| Repository: | BURJC-Digital. Repositorio Institucional de la Universidad Rey Juan Carlos |
| OAI Identifier: | oai:burjcdigital.urjc.es:10115/28550 |
| Online Access: | https://hdl.handle.net/10115/28550 |
| Access Level: | Open access |
| Keyword: | Multi-agent systems data stream processing mobile computing Agent perception |
| _version_ | 1878732426328408064 |
|---|---|
| author | Dötterl, Jeremias |
| author2 | Bruns, Ralf Dunkel, Jürgen Ossowski, Sascha |
| author2_role | author author author |
| author_browse | Bruns, Ralf Dunkel, Jürgen Dötterl, Jeremias Ossowski, Sascha |
| author_facet | Dötterl, Jeremias Bruns, Ralf Dunkel, Jürgen Ossowski, Sascha |
| author_role | author |
| collection | BURJC-Digital. Repositorio Institucional de la Universidad Rey Juan Carlos |
| description | Cognitive agent abstractions can help to engineer intelligent systems across mobile devices. On smartphones, the data obtained from onboard sensors can give valuable insights into the user’s current situation. Unfortunately, today’s cognitive agent frameworks cannot cope well with the challenging characteristics of sensor data. Sensor data is located on a low abstraction level and the individual data elements are not meaningful when observed in isolation. In contrast, cognitive agents operate on high-level percepts and lack the means to effectively detect complex spatio-temporal patterns in sequences of multiple percepts. In this paper, we present a stream-based perception approach that enables the agents to perceive meaningful situations in low-level sensor data streams. We present a crowdshipping case study where autonomous, self-interested agents collaborate to deliver parcels to their destinations. We show how situations derived from smartphone sensor data can trigger and guide auctions, which the agents use to reach agreements. Experiments with real smartphone data demonstrate the benefits of stream-based agent perception. |
| eu_rights_str_mv | openAccess |
| format | article |
| id | ES_42c97a3afcd797c3a5b3ff9e9e2caabc |
| institution | Universidad Rey Juan Carlos |
| instname_str | Universidad Rey Juan Carlos |
| network_acronym_str | ES |
| network_name_str | España |
| oai_identifier_str | oai:burjcdigital.urjc.es:10115/28550 |
| publishDate | 2019 |
| publishDateSort | 2019 |
| publisher | IOS Press |
| publisherStr | IOS Press |
| reponame_str | BURJC-Digital. Repositorio Institucional de la Universidad Rey Juan Carlos |
| spelling | Stream-based perception for cognitive agents in mobile ecosystems Dötterl, Jeremias Bruns, Ralf Dunkel, Jürgen Ossowski, Sascha Multi-agent systems data stream processing mobile computing Agent perception Cognitive agent abstractions can help to engineer intelligent systems across mobile devices. On smartphones, the data obtained from onboard sensors can give valuable insights into the user’s current situation. Unfortunately, today’s cognitive agent frameworks cannot cope well with the challenging characteristics of sensor data. Sensor data is located on a low abstraction level and the individual data elements are not meaningful when observed in isolation. In contrast, cognitive agents operate on high-level percepts and lack the means to effectively detect complex spatio-temporal patterns in sequences of multiple percepts. In this paper, we present a stream-based perception approach that enables the agents to perceive meaningful situations in low-level sensor data streams. We present a crowdshipping case study where autonomous, self-interested agents collaborate to deliver parcels to their destinations. We show how situations derived from smartphone sensor data can trigger and guide auctions, which the agents use to reach agreements. Experiments with real smartphone data demonstrate the benefits of stream-based agent perception. IOS Press https://hdl.handle.net/10115/28550 |
| spellingShingle | Stream-based perception for cognitive agents in mobile ecosystems Dötterl, Jeremias Multi-agent systems data stream processing mobile computing Agent perception |
| title | Stream-based perception for cognitive agents in mobile ecosystems |
| title_full | Stream-based perception for cognitive agents in mobile ecosystems |
| title_fullStr | Stream-based perception for cognitive agents in mobile ecosystems |
| title_full_unstemmed | Stream-based perception for cognitive agents in mobile ecosystems |
| title_short | Stream-based perception for cognitive agents in mobile ecosystems |
| title_sort | Stream-based perception for cognitive agents in mobile ecosystems |
| topic | Multi-agent systems data stream processing mobile computing Agent perception |
| topic_facet | Multi-agent systems data stream processing mobile computing Agent perception |
| url | https://hdl.handle.net/10115/28550 |