Dynamic Patrolling Policy for Optimizing Urban Mobility Networks

A dynamic patrolling policy is presented for a fleet of service vehicles operating in response to incident requests in an urban transportation network. We modify an existing adaptive, informative path controller so that the fleet of vehicles is driven to locally optimal service configurations within the environment. These configurations, called patrolling loops, minimize the distance between the instantaneous vehicle position and incident customer request. Our patrolling algorithm is trained using one month of data from a fleet of 16,000 vehicles. This historical dataset is used to learn the parameters required to set up a representative urban mobility model. Using this model we conduct large-scale simulations to show the global stability of the patrolling policy and evaluate the performance of our system by comparing it against a greedy service policy and historical data.

[1]  Jorge Cortés,et al.  Adaptive Information Collection by Robotic Sensor Networks for Spatial Estimation , 2012, IEEE Transactions on Automatic Control.

[2]  Richard F. Hartl,et al.  A survey on pickup and delivery problems , 2008 .

[3]  Anthony Stentz,et al.  Optimal and efficient path planning for partially-known environments , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.

[4]  Mac Schwager,et al.  Generating informative paths for persistent sensing in unknown environments , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[5]  Geoffrey A. Hollinger,et al.  Multi-robot coordination with periodic connectivity , 2010, 2010 IEEE International Conference on Robotics and Automation.

[6]  Sonny Li,et al.  Multi-attribute taxi logistics optimization , 2006 .

[7]  Hari Balakrishnan,et al.  Stochastic motion planning and applications to traffic , 2011, Int. J. Robotics Res..

[8]  Gilbert Laporte,et al.  Dynamic pickup and delivery problems , 2010, Eur. J. Oper. Res..

[9]  J. G. Wardrop,et al.  Some Theoretical Aspects of Road Traffic Research , 1952 .

[10]  Randy S. Roberts,et al.  An adaptive path planning algorithm for cooperating unmanned air vehicles , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[11]  Daniela Rus,et al.  Markov-based redistribution policy model for future urban mobility networks , 2012, 2012 15th International IEEE Conference on Intelligent Transportation Systems.

[12]  George L. Nemhauser,et al.  Optimality Conditions for a Dynamic Traffic Assignment Model , 1978 .

[13]  Andreas Krause,et al.  Efficient Informative Sensing using Multiple Robots , 2014, J. Artif. Intell. Res..

[14]  C. Flavin,et al.  Reinventing the automobile , 1995 .

[15]  Mac Schwager,et al.  Persistent Robotic Tasks: Monitoring and Sweeping in Changing Environments , 2011, IEEE Transactions on Robotics.

[16]  William J. Mitchell,et al.  Reinventing the Automobile: Personal Urban Mobility for the 21st Century , 2010 .

[17]  Emilio Frazzoli,et al.  Robotic load balancing for mobility-on-demand systems , 2012, Int. J. Robotics Res..

[18]  Tim Roughgarden,et al.  How bad is selfish routing? , 2000, Proceedings 41st Annual Symposium on Foundations of Computer Science.

[19]  Sejoon Lim,et al.  City-scale traffic estimation from a roving sensor network , 2012, SenSys '12.

[20]  Mac Schwager,et al.  Decentralized, Adaptive Coverage Control for Networked Robots , 2009, Int. J. Robotics Res..

[21]  Athanasios K. Ziliaskopoulos,et al.  Foundations of Dynamic Traffic Assignment: The Past, the Present and the Future , 2001 .

[22]  Terry L. Friesz,et al.  Dynamic Network Traffic Assignment Considered as a Continuous Time Optimal Control Problem , 1989, Oper. Res..

[23]  Emilio Frazzoli,et al.  Load Balancing for Mobility-on-Demand Systems , 2011, Robotics: Science and Systems.