Multi-objective Journey Planning under Uncertainty: A Genetic Approach

Multi-modal journey planning, which allows multiple modes of transport to be used within a single trip, is becoming increasingly popular, due to a strong practical interest and an increasing availability of data. In real life situations, transport networks often involve uncertainty, and yet, most approaches assume a deterministic environment, making plans more prone to failures such as major delays in the arrival or waiting for a long time at stations. In this paper, we tackle the multi-objective stochastic journey planning problem in multi-modal transportation networks. The problem is modeled as a Markov decision process with two objective functions: expected arrival time and journey convenience. We develop a GA-based MDP solver as a baseline search method for producing optimal policies for traveling from a given origin to a given destination. Our empirical evaluation uses Melbourne transportation network using probabilistic density functions for estimated departure/arrival time of the trips. Numerical results suggest that the proposed method is effective for practical purposes and provide strong evidence in favor of switching from deterministic to non-deterministic planning