Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Distributed Kalman--Consensus Filtering with Adaptive Uncertainty Weighting for Multi-Object Tracking in Mobile Robot Networks

Niusha Khosravi, Rodrigo Ventura, Meysam Basiri

Abstract

This paper presents an implementation and evaluation of a Distributed Kalman--Consensus Filter (DKCF) for Multi-Object Tracking (MOT) in mobile robot networks operating under partial observability and heterogeneous localization uncertainty. A key challenge in such systems is the fusion of information from agents with differing localization quality, where frame misalignment can lead to inconsistent estimates, track duplication, and ghost tracks. To address this issue, we build upon the MOTLEE framework and retain its frame-alignment methodology, which uses consistently tracked dynamic objects as transient landmarks to improve relative pose estimates between robots. On top of this framework, we propose an uncertainty-aware adaptive consensus weighting mechanism that dynamically adjusts the influence of neighbor information based on the covariance of the transmitted estimates, thereby reducing the impact of unreliable data during distributed fusion. Local tracking is performed using a Kalman Filter (KF) with a Constant Velocity Model (CVM) and Global Nearest Neighbor (GNN) data association. simulation results demonstrate that adaptive weighting effectively protects local estimates from inconsistent data, yielding a MOTA improvement of 0.09 for agents suffering from localization drift, although system performance remains constrained by communication latency.

Distributed Kalman--Consensus Filtering with Adaptive Uncertainty Weighting for Multi-Object Tracking in Mobile Robot Networks

Abstract

This paper presents an implementation and evaluation of a Distributed Kalman--Consensus Filter (DKCF) for Multi-Object Tracking (MOT) in mobile robot networks operating under partial observability and heterogeneous localization uncertainty. A key challenge in such systems is the fusion of information from agents with differing localization quality, where frame misalignment can lead to inconsistent estimates, track duplication, and ghost tracks. To address this issue, we build upon the MOTLEE framework and retain its frame-alignment methodology, which uses consistently tracked dynamic objects as transient landmarks to improve relative pose estimates between robots. On top of this framework, we propose an uncertainty-aware adaptive consensus weighting mechanism that dynamically adjusts the influence of neighbor information based on the covariance of the transmitted estimates, thereby reducing the impact of unreliable data during distributed fusion. Local tracking is performed using a Kalman Filter (KF) with a Constant Velocity Model (CVM) and Global Nearest Neighbor (GNN) data association. simulation results demonstrate that adaptive weighting effectively protects local estimates from inconsistent data, yielding a MOTA improvement of 0.09 for agents suffering from localization drift, although system performance remains constrained by communication latency.
Paper Structure (21 sections, 14 equations, 4 figures, 1 table)

This paper contains 21 sections, 14 equations, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Single-View Multi-Object Tracking with Uncertain Localization
  4. Multi-Robot Multi-Object Tracking with Uncertain Localization
  5. Adaptive and Weighted Consensus Filtering
  6. Local Detection and Tracking
  7. Object Detection and Clustering
  8. Dynamic Model and Kalman Filter
  9. Data Association with Global Nearest Neighbor and Hungarian Algorithm
  10. Distributed Kalman--Consensus Filter with Adaptive Weighting
  11. System Overview
  12. Information-Form Fusion with Frame Alignment
  13. Proposed Adaptive Uncertainty Weighting
  14. Frame Alignment and Track Management
  15. Simulation Results
  16. ...and 6 more sections

Figures (4)

  • Figure 1: Comparison of estimated tracks (dashed) and ground-truth trajectories (solid) for single-robot KF.
  • Figure 2: Position error over time for single-robot KF.
  • Figure 3: MOTA distribution box plots. The adaptive weighting strategy (right) improves the consistency of Robot 1 by rejecting noise, but reduces the peak performance of Robot 2, highlighting a trade-off between robustness and cooperative gain.
  • Figure 4: Real-time Gmapping and object tracking by two robots in a partially constructed map.