Route recommendation for driver is a knowledge-rich problem where the criteria for making decisions (the attributes of the edges) and the relative weight of the attributes (cost function) can be personalized. The Adaptive Route Advisor serves as a intermediary agent between the driver and the complex digital map. The agent and the driver interact to generate multiple route options, giving the driver a more satisfactory route than he or she would receive from a single-option route planner, and providing feedback from the driver that reflects his or her route preferences. The agent encodes these preferences in a user model that the agent uses to predict which route the driver will find most appealing.
Although interaction is in the driver's best interest if he or she wants a satisfactory route, the agent does not require it, and ideally interaction will become less necessary as the agent better approximates the driver's cost function. This low interaction requirement is crucial for in-car decision making where the driver's attention is necessarily focused elsewhere.
In general, our approach to developing advice agents is to automatically and unobtrusively acquire value judgments by observing the user's actions in a domain, and to utilize interaction as an additional source of value judgments. The agent generates a solution using its current user model, receives feedback from the user if its model is inaccurate, and corrects its model in areas relevant to the problem being solved.