Result: RoSSO: A High-Performance Python Package for Robotic Surveillance Strategy Optimization Using JAX

Title:
RoSSO: A High-Performance Python Package for Robotic Surveillance Strategy Optimization Using JAX
Authors:
John, Yohan, Hughes, Connor, Diaz-Garcia, Gilberto, Marden, Jason R., Bullo, Francesco
Publisher Information:
2023-09-15
Document Type:
Electronic Resource Electronic Resource
Index Terms:
Computer Science - Robotics, Mathematics - Optimization and Control, text
URL:
http://arxiv.org/abs/2309.08742
Availability:
Open access content. Open access content
Other Numbers:
COO oai:arXiv.org:2309.08742
1438480286
Contributing Source:
CORNELL UNIV
From OAIster®, provided by the OCLC Cooperative.
Accession Number:
edsoai.on1438480286
Database:
OAIster

Further Information

To enable the computation of effective randomized patrol routes for single- or multi-robot teams, we present RoSSO, a Python package designed for solving Markov chain optimization problems. We exploit machine-learning techniques such as reverse-mode automatic differentiation and constraint parametrization to achieve superior efficiency compared to general-purpose nonlinear programming solvers. Additionally, we supplement a game-theoretic stochastic surveillance formulation in the literature with a novel greedy algorithm and multi-robot extension. We close with numerical results for a police district in downtown San Francisco that demonstrate RoSSO's capabilities on our new formulations and the prior work.
Comment: 7 pages, 4 figures, 3 tables, submitted to the 2024 IEEE International Conference on Robotics and Automation. See https://github.com/conhugh/RoSSO for associated codebase