Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Collaborative State Fusion in Partially Known Multi-agent Environments

Tianlong Zhou, Jun Shang, Weixiong Rao

TL;DR

This paper proposes a two-stage collaborative fusion framework, namely \underline{Learnable Weighted R\underline{o}bust \underline{F}usion (\textsf{LoF}), and develops a time-series soft medoid(TSM) scheme to perform robust fusion given observation outliers.

Abstract

In this paper, we study the collaborative state fusion problem in a multi-agent environment, where mobile agents collaborate to track movable targets. Due to the limited sensing range and potential errors of on-board sensors, it is necessary to aggregate individual observations to provide target state fusion for better target state estimation. Existing schemes do not perform well due to (1) impractical assumption of the fully known prior target state-space model and (2) observation outliers from individual sensors. To address the issues, we propose a two-stage collaborative fusion framework, namely \underline{L}earnable Weighted R\underline{o}bust \underline{F}usion (\textsf{LoF}). \textsf{LoF} combines a local state estimator (e.g., Kalman Filter) with a learnable weight generator to address the mismatch between the prior state-space model and underlying patterns of moving targets. Moreover, given observation outliers, we develop a time-series soft medoid(TSM) scheme to perform robust fusion. We evaluate \textsf{LoF} in a collaborative detection simulation environment with promising results. In an example setting with 4 agents and 2 targets, \textsf{LoF} leads to a 9.1\% higher fusion gain compared to the state-of-the-art.

Collaborative State Fusion in Partially Known Multi-agent Environments

TL;DR

This paper proposes a two-stage collaborative fusion framework, namely \underline{Learnable Weighted R\underline{o}bust \underline{F}usion (\textsf{LoF}), and develops a time-series soft medoid(TSM) scheme to perform robust fusion given observation outliers.

Abstract

In this paper, we study the collaborative state fusion problem in a multi-agent environment, where mobile agents collaborate to track movable targets. Due to the limited sensing range and potential errors of on-board sensors, it is necessary to aggregate individual observations to provide target state fusion for better target state estimation. Existing schemes do not perform well due to (1) impractical assumption of the fully known prior target state-space model and (2) observation outliers from individual sensors. To address the issues, we propose a two-stage collaborative fusion framework, namely \underline{L}earnable Weighted R\underline{o}bust \underline{F}usion (\textsf{LoF}). \textsf{LoF} combines a local state estimator (e.g., Kalman Filter) with a learnable weight generator to address the mismatch between the prior state-space model and underlying patterns of moving targets. Moreover, given observation outliers, we develop a time-series soft medoid(TSM) scheme to perform robust fusion. We evaluate \textsf{LoF} in a collaborative detection simulation environment with promising results. In an example setting with 4 agents and 2 targets, \textsf{LoF} leads to a 9.1\% higher fusion gain compared to the state-of-the-art.

Paper Structure

This paper contains 31 sections, 2 theorems, 28 equations, 8 figures, 5 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work and Preliminaries
  3. Related Work
  4. Preliminaries
  5. State Space Model
  6. Soft Medoid
  7. Problem Formulation
  8. Solution Detail
  9. Overall Framework
  10. Local Estimation
  11. Local State Estimator
  12. Local Weight Generator
  13. Robust Fusion
  14. Baseline Approach
  15. Robust Fusion Solution
  16. ...and 16 more sections

Key Result

Theorem 1

We solve the collaborative state estimation by

Figures (8)

  • Figure 1: Collaborative Detection. A team of three agents (blue) exploits range-bearing sensors with limited sensing ranges to track four movable targets (red) by state estimates (green) with the mean and uncertainty.
  • Figure 2: Overall framework
  • Figure 3: (a) Local Weight Generator, (b) Robust Fusion
  • Figure 4: Effect of Partial Known Observation Model.
  • Figure 5: Effect of Partial Known State-Evolution Model.
  • ...and 3 more figures

Theorems & Definitions (5)

  • Theorem 1
  • Theorem 2
  • proof
  • proof
  • proof