A Fast Exact Algorithm for the Resource Constrained Shortest Path Problem


  • Saman Ahmadi Monash University, Australia CSIRO Data61, Australia
  • Guido Tack Monash University, Australia
  • Daniel D. Harabor Monash University, Australia
  • Philip Kilby CSIRO Data61, Australia


Heuristic Search, Motion and Path Planning


Resource constrained path finding is a well studied topic in AI, with real-world applications in different areas such as transportation and robotics. This paper introduces several heuristics in the resource constrained path finding context that significantly improve the algorithmic performance of the initialisation phase and the core search. We implement our heuristics on top of a bidirectional A* algorithm and evaluate them on a set of large instances. The experimental results show that, for the first time in the context of constrained path finding, our fast and enhanced algorithm can solve all of the benchmark instances to optimality, and compared to the state of the art algorithms, it can improve existing runtimes by up to four orders of magnitude on large-size network graphs.




How to Cite

Ahmadi, S., Tack, G., Harabor, D. D., & Kilby, P. (2021). A Fast Exact Algorithm for the Resource Constrained Shortest Path Problem. Proceedings of the AAAI Conference on Artificial Intelligence, 35(14), 12217-12224. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17450



AAAI Technical Track on Search and Optimization