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.

Keywords:

• Intelligent transport system
• machine learning techniques in ITS
• SARSA algorithm
• dynamic programming
• route guidance system
• travel time prediction
• traveller information system

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Notes on contributors

Roopa Ravish

Roopa Ravish received the bachelor's degree in Instrumentation Technology from Kuvempu University, the master's and Ph.D. degree in Computer Science and Engineering from Visvesvaraya Technological University, India. She is currently working as an Associate Professor with the Department of Computer Science and Engineering at PES University, Bangalore, India. Her research domain is ITS and areas of interest are RL, ML, and IoT.

Shanta Rangaswamy

Shanta Rangaswamy is working as a Professor with the Department of Computer Science and Engineering at RV College of Engineering, Bengaluru. She was awarded a Ph.D. degree in Computer Science in the year 2014. She is a Senior IEEE member, CSI Life Member, and ISTE Life Member. She has been handling various consultancy and research projects. Her research interests include data mining, ML, ITS, image processing, and health care systems.

Arpitha V

V. Arpitha received the bachelor's and master's degree in Computer Science and Engineering from Visvesvaraya Technological University, India. She is currently working in Information Technology industry as a web developer. Her current research interest includes ML and ITS.

Vasuprada U

U. Vasuprada received the bachelor's and master's degree in Computer Science and Engineering from Visvesvaraya Technological University, India. She has received gold medal for securing the highest marks in master's degree. She is currently working in Information Technology industry as a hardware engineer. Her current research interest includes ML and ITS.