Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Recruiting Heterogeneous Crowdsource Vehicles for Updating a High-definition Map

Wentao Ye, Yuan Luo, Bo Liu, Jianwei Huang

Abstract

The high-definition map is a cornerstone of autonomous driving. Unlike constructing a costly fleet of mapping vehicles, the crowdsourcing paradigm is a cost-effective way to keep an HD map up to date. Achieving practical success for crowdsourcing-based HD maps is contingent on addressing two critical issues: freshness and recruitment costs. Given that crowdsource vehicles are often heterogeneous in terms of operational costs and sensing capabilities, it is practical to recruit heterogeneous crowdsource vehicles to achieve the tradeoff between freshness and recruitment costs. However, existing works neglect this aspect. To solve it, we formulate this problem as a Markov decision process. We demonstrate that the optimal policy is threshold-type age-dependent. Additionally, our findings reveal some counter-intuitive insights. In some cases, the company should initiate vehicle recruitment earlier when vehicles arrive more frequently, or have higher operational costs or sensing capabilities.} Besides, we propose an efficient algorithm, called the bound-based relative value iteration (BRVI) algorithm, to overcome the technical challenge that finding an optimal policy is time-consuming. Numerical simulations show that (i) the optimal policy reduces the average cost by $19.04\%$ compared to the state-of-the-art mechanism}, and (ii) the proposed algorithm can reduce the convergence time by $13.66\%$ on average compared to the existing algorithm.

Recruiting Heterogeneous Crowdsource Vehicles for Updating a High-definition Map

Abstract

The high-definition map is a cornerstone of autonomous driving. Unlike constructing a costly fleet of mapping vehicles, the crowdsourcing paradigm is a cost-effective way to keep an HD map up to date. Achieving practical success for crowdsourcing-based HD maps is contingent on addressing two critical issues: freshness and recruitment costs. Given that crowdsource vehicles are often heterogeneous in terms of operational costs and sensing capabilities, it is practical to recruit heterogeneous crowdsource vehicles to achieve the tradeoff between freshness and recruitment costs. However, existing works neglect this aspect. To solve it, we formulate this problem as a Markov decision process. We demonstrate that the optimal policy is threshold-type age-dependent. Additionally, our findings reveal some counter-intuitive insights. In some cases, the company should initiate vehicle recruitment earlier when vehicles arrive more frequently, or have higher operational costs or sensing capabilities.} Besides, we propose an efficient algorithm, called the bound-based relative value iteration (BRVI) algorithm, to overcome the technical challenge that finding an optimal policy is time-consuming. Numerical simulations show that (i) the optimal policy reduces the average cost by compared to the state-of-the-art mechanism}, and (ii) the proposed algorithm can reduce the convergence time by on average compared to the existing algorithm.

Paper Structure

This paper contains 23 sections, 11 theorems, 39 equations, 7 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Works
  3. System Model
  4. Overview of crowdsourcing in the HD map
  5. Company's cost function
  6. AoI loss
  7. Company's cost function
  8. Problem Formulation
  9. Main Results
  10. Characterization of the optimality
  11. The impact of arrival probabilities on thresholds
  12. The impact of operational costs on thresholds
  13. Bound-based Relative Value Iteration Algorithm
  14. Simulation Results
  15. Performance of the optimal policy
  16. ...and 8 more sections

Key Result

Lemma 1

Consider the LH structure of the optimal policy in Theorem theorem: 1, the optimal thresholds $\delta_L$, $\delta_H$, $\delta_B$ are upper bounded by the following values, respectively.

Figures (7)

  • Figure 1: The crowdsourcing workflow for the HD map.
  • Figure 2: Four possible structures of the optimal policy.
  • Figure 3: The distribution of the optimal policy structures.
  • Figure 4: The thresholds in LH structure vary as the arrival probability increases. Fig. \ref{['fig: p_L']} and \ref{['fig: p_H']} manipulate the arrival probability $p_L$ and $p_H$ of Low-type and High-type vehicles, respectively.
  • Figure 5: The thresholds vary as the operational cost increases. Fig. \ref{['fig: c_L']} and \ref{['fig: c_H']} depict the optimal policy transitioning between None-H to LH to None-L and None-L to LH to None-H structures, respectively.
  • ...and 2 more figures

Theorems & Definitions (18)

  • Lemma 1
  • Lemma 2
  • proof
  • Lemma 3
  • Lemma 4
  • proof
  • Lemma 5
  • proof
  • Lemma 6
  • proof
  • ...and 8 more