Stream-based perception for cognitive agents in mobile ecosystems
Jeremias Dötterl, Ralf Bruns, Jürgen Dunkel, Sascha Ossowski
TL;DR
The paper tackles the mismatch between low-level sensor data and high-level agent perception in mobile multi-agent systems. It introduces Agents with Enhanced Perception (AEP), a stream-based layer that uses data-stream concepts, expectations, and interpretations to derive situations from percept sequences and feed beliefs and plans in a Jason-based framework. Through a crowdshipping case study, it demonstrates how situation-driven auctions can allocate tasks among self-interested mobile agents, with interpretation rules and CEP-based processing enabling complex spatio-temporal pattern matching and reduced deliberation load. Experimental evaluation on real GPS data shows that the approach produces meaningful context and situations while limiting the deliberation burden, highlighting practical impact for adaptive, sensor-aware mobile ecosystems.
Abstract
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.