Robotic load balancing for mobility-on-demand systems

By Marco Pavone, Stephen L. Smith, Emilio Frazzoli, Daniela Rus. Int. J. Robotics Res., 2012

305 citations recorded by the source corpus.

In this paper we develop methods for maximizing the throughput of a mobility-on-demand urban transportation system. We consider a finite group of shared vehicles, located at a set of stations. Users arrive at the stations, pickup vehicles, and drive (or are driven) to their destination station where they drop-off the vehicle. When some origins and destinations are more popular than others, the system will inevitably become out of balance: vehicles will build up at some stations, and become depleted at others. We propose a robotic solution to this rebalancing problem that involves empty robotic vehicles autonomously driving between stations. Specifically, we utilize a fluid model for the customers and vehicles in the system. Then, we develop a rebalancing policy that lets every station reach an equilibrium in which there are excess vehicles and no waiting customers and that minimizes the number of robotic vehicles performing rebalancing trips. We show that the optimal rebalancing policy can be found as the solution to a linear program. We use this solution to develop a real-time rebalancing policy which can operate in highly variable environments. Finally, we verify policy performance in a simulated mobility-on-demand environment and in hardware experiments.

Subfields: Automotive Engineering, Control and Systems Engineering, Transportation

View Paper: https://www.semanticscholar.org/paper/268923650c6d03a21dfe003920cf7f7a0d252fbc

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Automotive Engineering

In Control and Systems Engineering

In Transportation

Citations in the corpus

On-demand high-capacity ride-sharing via dynamic trip-vehicle assignment (2017, background): “With the growing interest and rapid developments in autonomous vehicles, there is also an increasing focus on autonomous MoD systems (6, 9, 10).”
Planning and Decision-Making for Autonomous Vehicles (2018, background): “Much of the fleet management literature for mobility-on-demand systems considers the case of ride sharing without pooling requests, focusing on fluid approximations (136), queuing-based formulations (137), and case studies in specific regions.”
Flow: A Modular Learning Framework for Mixed Autonomy Traffic (2017, background): “On a large-scale network, ﬂeets of AVs have been studied for shared-mobility systems, such as autonomous mobility-on-demand [59], [5], [60], which abstracts out the low-level vehicle dynamics and considers a queuing theoretic model.”
Control of robotic mobility-on-demand systems: A queueing-theoretical perspective (2014, methodology): “In this respect, the analysis of our paper provides a theoretical foundation for the fluidic approximation performed in [19].”
Toward a Systematic Approach to the Design and Evaluation of Automated Mobility-on-Demand Systems: A Case Study in Singapore (2014, background): “, [17] and [18] for similar problems defined with regard to a system of stations embedded in a road network, instead of a compact region in the Euclidean plane.”
Flow: Architecture and Benchmarking for Reinforcement Learning in Traffic Control (2017, background): “The breakthrough results [4], [7] are part of a broader core set of robotics challenges concerning the deployment of multi-agent automation systems, such as ﬂeets of self-driving cars [8], [9], coordinated trafﬁc lights [10], [11], or other coordinated infrastructure.”