Litcius/Paper detail

Context-Aware Taxi Dispatching at City-Scale Using Deep Reinforcement Learning

Zhidan Liu, Jiangzhou Li, Kaishun Wu

2020IEEE Transactions on Intelligent Transportation Systems95 citationsDOI

Abstract

Proactive taxi dispatching is of great importance to balance taxi demand-supply gaps among different locations in a city. Recent advances primarily rely on deep reinforcement learning (DRL) to directly learn the optimal dispatching policy. These works, however, are still not sufficiently efficient because they overlook several pieces of valuable context information. As a result, they may generate quite a few improper actions and introduce unnecessary coordination costs. To improve existing works, we present <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">COX</i> – a context-aware taxi dispatching approach that incorporates rich contexts into DRL modeling for more efficient taxi reallocations. Specifically, rather than simply dividing the service area into grids, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">COX</i> proposes a road connectivity aware clustering algorithm to divide the road network graph into zones for practical taxi dispatching. In addition, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">COX</i> comprehensively analyzes zone-level taxi demands and supplies through accurate taxi demand prediction and timely updates of taxi statuses. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">COX</i> improves the DRL modeling by integrating these derived contexts, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g.</i> , state representation with complete demand/supply data and sequential action generation with full coordination among idle taxis. In particular, we implement an environment simulator to train and evaluate <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">COX</i> using a large real-world taxi dataset. Extensive experiments show that <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">COX</i> outperforms state-of-the-art approaches on various performance metrics, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g.</i> , on average improving the total order values by 6.74%, while reducing the number of unserved taxi orders and passengers’ waiting time by 4.92% and 44.84%, respectively.

Topics & Concepts

Reinforcement learningScale (ratio)Context (archaeology)Computer scienceArtificial intelligenceMachine learningGeographyCartographyArchaeologyTransportation and Mobility InnovationsSmart Parking Systems ResearchHuman Mobility and Location-Based Analysis
Context-Aware Taxi Dispatching at City-Scale Using Deep Reinforcement Learning | Litcius