The impact of complexity in the built environment on vehicular routing behavior: Insights from an empirical study of taxi mobility in Beijing, China

• URL: http://arxiv.org/abs/2404.15589v1
• Date: Wed, 24 Apr 2024 01:45:11 GMT
• Title: The impact of complexity in the built environment on vehicular routing behavior: Insights from an empirical study of taxi mobility in Beijing, China
• Authors: Chaogui Kang, Zheren Liu,
• Abstract summary: We propose a vehicular route choice model that mimics anchoring effect and exposure preference while driving. Results show that the proposed model performs 12% better than the conventional vehicular route choice model based on the shortest path principle.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The modeling of disaggregated vehicular mobility and its associations with the ambient urban built environment is essential for developing operative transport intervention and urban optimization plans. However, established vehicular route choice models failed to fully consider the bounded behavioral rationality and the complex characteristics of the urban built environment affecting drivers' route choice preference. Therefore, the spatio-temporal characteristics of vehicular mobility patterns were not fully explained, which limited the granular implementation of relevant transport interventions. To address this limitation, we proposed a vehicular route choice model that mimics the anchoring effect and the exposure preference while driving. The proposed model enables us to quantitatively examine the impact of the built environment on vehicular routing behavior, which has been largely neglected in previous studies. Results show that the proposed model performs 12% better than the conventional vehicular route choice model based on the shortest path principle. Our empirical analysis of taxi drivers' routing behavior patterns in Beijing, China uncovers that drivers are inclined to choose routes with shorter time duration and with less loss at traversal intersections. Counterintuitively, we also found that drivers heavily rely on circuitous ring roads and expressways to deliver passengers, which are unexpectedly longer than the shortest paths. Moreover, characteristics of the urban built environment including road eccentricity, centrality, average road length, land use diversity, sky visibility, and building coverage can affect drivers' route choice behaviors, accounting for about 5% of the increase in the proposed model's performance. We also refine the above explorations according to the modeling results of trips that differ in departure time, travel distance, and occupation status.

Related papers

• Parameterized Decision-making with Multi-modal Perception for Autonomous Driving [12.21578713219778]
  We propose a parameterized decision-making framework with multi-modal perception based on deep reinforcement learning, called AUTO. A hybrid reward function takes into account aspects of safety, traffic efficiency, passenger comfort, and impact to guide the framework to generate optimal actions.
  arXiv  Detail & Related papers  (2023-12-19T08:27:02Z)
• iPLAN: Intent-Aware Planning in Heterogeneous Traffic via Distributed Multi-Agent Reinforcement Learning [57.24340061741223]
  We introduce a distributed multi-agent reinforcement learning (MARL) algorithm that can predict trajectories and intents in dense and heterogeneous traffic scenarios. Our approach for intent-aware planning, iPLAN, allows agents to infer nearby drivers' intents solely from their local observations.
  arXiv  Detail & Related papers  (2023-06-09T20:12:02Z)
• Studying the Impact of Semi-Cooperative Drivers on Overall Highway Flow [76.38515853201116]
  Semi-cooperative behaviors are intrinsic properties of human drivers and should be considered for autonomous driving. New autonomous planners can consider the social value orientation (SVO) of human drivers to generate socially-compliant trajectories. We present study of implicit semi-cooperative driving where agents deploy a game-theoretic version of iterative best response.
  arXiv  Detail & Related papers  (2023-04-23T16:01:36Z)
• Decision Making for Autonomous Driving in Interactive Merge Scenarios via Learning-based Prediction [39.48631437946568]
  This paper focuses on the complex task of merging into moving traffic where uncertainty emanates from the behavior of other drivers. We frame the problem as a partially observable Markov decision process (POMDP) and solve it online with Monte Carlo tree search. The solution to the POMDP is a policy that performs high-level driving maneuvers, such as giving way to an approaching car, keeping a safe distance from the vehicle in front or merging into traffic.
  arXiv  Detail & Related papers  (2023-03-29T16:12:45Z)
• Urban traffic dynamic rerouting framework: A DRL-based model with fog-cloud architecture [0.7046417074932257]
  This study proposes a two-stage model that combines GAQ (Graph Attention Network - Deep Q Learning) and EBkSP (Entropy Based k Shortest Path) First, GAQ analyzes the traffic conditions on each road and for each fog area, and then assigns a road index based on the information attention from both local and neighboring areas. Second, EBkSP assigns the route for each vehicle based on the vehicle priority and route popularity.
  arXiv  Detail & Related papers  (2021-10-11T18:15:44Z)
• Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers [126.81938540470847]
  We propose Euro-PVI, a dataset of pedestrian and bicyclist trajectories. In this work, we develop a joint inference model that learns an expressive multi-modal shared latent space across agents in the urban scene. We achieve state of the art results on the nuScenes and Euro-PVI datasets demonstrating the importance of capturing interactions between ego-vehicle and pedestrians (bicyclists) for accurate predictions.
  arXiv  Detail & Related papers  (2021-06-22T15:40:21Z)
• Calibration of Human Driving Behavior and Preference Using Naturalistic Traffic Data [5.926030548326619]
  We show how the model can be inverted to estimate driver preferences from naturalistic traffic data. One distinct advantage of our approach is the drastically reduced computational burden.
  arXiv  Detail & Related papers  (2021-05-05T01:20:03Z)
• Multi-Modal Fusion Transformer for End-to-End Autonomous Driving [59.60483620730437]
  We propose TransFuser, a novel Multi-Modal Fusion Transformer, to integrate image and LiDAR representations using attention. Our approach achieves state-of-the-art driving performance while reducing collisions by 76% compared to geometry-based fusion.
  arXiv  Detail & Related papers  (2021-04-19T11:48:13Z)
• Deep Structured Reactive Planning [94.92994828905984]
  We propose a novel data-driven, reactive planning objective for self-driving vehicles. We show that our model outperforms a non-reactive variant in successfully completing highly complex maneuvers.
  arXiv  Detail & Related papers  (2021-01-18T01:43:36Z)
• Emergent Road Rules In Multi-Agent Driving Environments [84.82583370858391]
  We analyze what ingredients in driving environments cause the emergence of road rules. We find that two crucial factors are noisy perception and agents' spatial density. Our results add empirical support for the social road rules that countries worldwide have agreed on for safe, efficient driving.
  arXiv  Detail & Related papers  (2020-11-21T09:43:50Z)
• Decoding pedestrian and automated vehicle interactions using immersive virtual reality and interpretable deep learning [6.982614422666432]
  This study investigates pedestrian crossing behaviour, as an important element of urban dynamics that is expected to be affected by the presence of automated vehicles. Pedestrian wait time behaviour is then analyzed using a data-driven Cox Proportional Hazards (CPH) model. Results show that the presence of automated vehicles on roads, wider lane widths, high density on roads, limited sight distance, and lack of walking habits are the main contributing factors to longer wait times.
  arXiv  Detail & Related papers  (2020-02-18T01:30:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.