Message Passing-Based Cooperative Localization with Embedded Particle Flow

Wielandner, Lukas; Leitinger, Erik; Meyer, Florian; Teague, Bryan; Witrisal, Klaus

doi:10.1109/icassp43922.2022.9747585

Cited by 9 publications

(5 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the cooperative localization problem, a method that relies on invertible PFL is presented in [46], [47]. This method is not suitable for the more challenging multiobject tracking problems since it can only be applied to problems without measurement origin uncertainty, known number of states to be estimated, and posterior pdfs with simple, unimodal shapes.…”

Section: A State-of-the-artmentioning

confidence: 99%

Multisensor Multiobject Tracking With Improved Sampling Efficiency

Zhang,

Meyer

2024

IEEE Trans. Signal Process.

Self Cite

View full text Add to dashboard Cite

Passive monitoring of acoustic or radio sources has important applications in modern convenience, public safety, and surveillance. A key task in passive monitoring is multiobject tracking (MOT). This paper presents a Bayesian method for multisensor MOT for challenging tracking problems where the object states are high-dimensional, and the measurements follow a nonlinear model. Our method is developed in the framework of factor graphs and the sum-product algorithm (SPA) and implemented using random samples or "particles". The multimodal probability density functions (pdfs) provided by the SPA are effectively represented by a Gaussian mixture model (GMM). To perform the operations of the SPA with improved sample efficiency, we make use of particle flow (PFL). Here, particles are migrated towards regions of high likelihood based on the solution of a partial differential equation. This makes it possible to obtain good object detection and tracking performance even in challenging multisensor MOT scenarios with single sensor measurements that have a lower dimension than the object positions. We perform a numerical evaluation in a passive acoustic monitoring scenario where multiple sources are tracked in 3-D from 1-D time-difference-of-arrival (TDOA) measurements provided by pairs of hydrophones. Our numerical results demonstrate favorable detection and estimation accuracy compared to state-of-the-art reference techniques.

show abstract

Section: A State-of-the-artmentioning

confidence: 99%

Multisensor Multiobject Tracking With Improved Sampling Efficiency

Zhang,

Meyer

2024

IEEE Trans. Signal Process.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The behavior of static networks can be analyzed by considering a single time step of the statistical model. This paper advances over the preliminary account of our method provided in the conference publication [48] by (i) also considering the uncertainties of cooperating neighbor agents in the PF-BP belief update equations, (ii) a detailed description of the proposed algorithm, (iii) an extension to higher state dimensions, (iv) a comprehensive comparison to established state-of-the-art algorithms and to the theoretical performance limit in terms of the PCRLB. The remainder of this paper is organized as follows.…”

Section: B Contributions and Organization Of The Papermentioning

confidence: 99%

Message Passing-Based 9-D Cooperative Localization and Navigation With Embedded Particle Flow

Wielandner

Leitinger

Meyer

et al. 2023

IEEE Trans. on Signal and Inf. Process. over Networks

View full text Add to dashboard Cite

Cooperative localization (CL) is an important technology for innovative services such as location-aware communication networks, modern convenience, and public safety. We consider wireless networks with mobile agents that aim to localize themselves by performing pairwise measurements amongst agents and exchanging their location information. Belief propagation (BP) is a state-of-the-art Bayesian method for CL. In CL, particle-based implementations of BP often are employed that can cope with non-linear measurement models and state dynamics. However, particle-based BP algorithms are known to suffer from particle degeneracy in large and dense networks of mobile agents with high-dimensional states.This paper derives the messages of BP for CL by means of particle flow, leading to the development of a distributed particle-based message-passing algorithm which avoids particle degeneracy. Our combined particle flow-based BP approach allows the calculation of highly accurate proposal distributions for agent states with a minimal number of particles. It outperforms conventional particle-based BP algorithms in terms of accuracy and runtime. Furthermore, we compare the proposed method to a centralized particle flow-based implementation, known as the exact Daum-Huang filter, and to sigma point BP in terms of position accuracy, runtime, and memory requirement versus the network size. We further contrast all methods to the theoretical performance limit provided by the posterior Cramér-Rao lower bound (PCRLB). Based on three different scenarios, we demonstrate the superiority of the proposed method.

show abstract

“…When the conditions of linearity and Gaussianity are not met, particle-based MPA can be employed, although this typically results in a notable increase of computational and communication expenses (i.e., due to particles' sharing and aggregation). Some works tried to improve performances of particle-based MPA implementations by reducing the particle degeneracy in dense and large networks [29], [30] or by autotuning the parameters of time-varying system models [31]. However, they did not resolve the main issue of MPA, which is related to the convergence of the beliefs.…”

Section: B Related Workmentioning

confidence: 99%

Message Passing Neural Network Versus Message Passing Algorithm for Cooperative Positioning

Camajori Tedeschini,

Brambilla,

Nicoli

2023

IEEE Trans. Cogn. Commun. Netw.

View full text Add to dashboard Cite

Cooperative Positioning (CP) relies on a network of connected agents equipped with sensing and communication technologies to improve the positioning performance of standalone solutions. In this paper, we develop a completely data-driven model combining Long Short-Term Memory (LSTM) and Message Passing Neural Network (MPNN) for CP, where agents estimate their state from inter-agent and state-dependent measurements. The proposed LSTM-MPNN model is derived from a parallelism with the probability-based Message Passing Algorithm (MPA) for CP, from which the graph-based structure of the problem and message passing scheme is inherited. In our solution, the LSTM block predicts the motion of the agents, while the MPNN elaborates the node and edge embeddings for an effective inference of the agent's state. We present numerical evidence that our approach can enhance position estimation, while being at the same time an order of magnitude less complex than typical particle-based implementations of MPA for non-linear problems. In particular, the presented LSTM-MPNN model can reduce the error on agents' positioning to one third compared to MPA-based CP, it holds a higher convergence speed and better exploits cooperation among agents.

show abstract

Message Passing-Based Cooperative Localization with Embedded Particle Flow

Cited by 9 publications

References 25 publications

Multisensor Multiobject Tracking With Improved Sampling Efficiency

Multisensor Multiobject Tracking With Improved Sampling Efficiency

Message Passing-Based 9-D Cooperative Localization and Navigation With Embedded Particle Flow

Message Passing Neural Network Versus Message Passing Algorithm for Cooperative Positioning

Contact Info

Product

Resources

About