User preference-based intelligent road route recommendation using SARSA and dynamic programming

Abstract

Traffic congestion is one of the main challenges in transportation engineering. It directly impacts the economy by increasing travel time and affecting the environment by excessive fuel consumption and emission. Road route recommendation to overcome the congestion by alternative route suggestions has gained high importance. The existing route recommendation systems are proposed using the reinforcement learning algorithm (Q-learning). The techniques suggested in this paper are state-action-reward-state-action (SARSA) algorithm and dynamic programming (DP) to guide the commuters to reach the destination with an optimal solution. The algorithm considers travel time, cost, flexibility, and traffic intensity as the user preference attributes to recommend an optimal route. The recommended system is implemented by building a road network graph. We assign values to each user preference attribute along the edges, which can take high(1) or low(0) values. By considering these values, the system recommends the route. The proposed system performance is evaluated based on computation time, cumulative reward, and accuracy. The results show that DP outperforms the SARSA algorithm.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 7 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.