Data Association with Gaussian Processes

Kaiser, Markus; Otte, Clemens; Runkler, Thomas A.; Ek, Carl Henrik

doi:10.1007/978-3-030-46147-8_33

Cited by 2 publications

(7 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [44], GP priors are placed on the different generative processes and the associations are modelled via a latent association matrix and inference is carried out using an expectation-maximization algorithm. [45] extends GPbased data association into the non-stationary process where a different number of generative processes can be activated in different locations in the input space. GP has been also combined with state-space models to solve the tracking problem.…”

Section: Related Workmentioning

confidence: 99%

Gaussian Process Upper Confidence Bounds in Distributed Point Target Tracking Over Wireless Sensor Networks

Liu

Mihaylova

George

et al. 2023

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

Uncertainty quantification plays a key role in the development of autonomous systems, decision-making, and tracking over wireless sensor networks (WSNs). However, there is a need of providing uncertainty confidence bounds, especially for distributed machine learning-based tracking, dealing with different volumes of data collected by sensors. This paper aims to fill in this gap and proposes a distributed Gaussian process (DGP) approach for point target tracking and derives upper confidence bounds (UCBs) of the state estimates. A unique aspect of the proposed approach consists in the theoretical results are derived that prove its maximum accuracy for tracking with and without clutter measurements. Particularly, the developed approaches with uncertainty bounds are generic and can provide trustworthy solutions with an increased level of reliability. A novel hybrid Bayesian filtering method is proposed to enhance the DGP approach by adopting a Poisson measurement likelihood model. The proposed approaches are validated over a WSN case study, whose sensors have limited sensing ranges. Numerical results demonstrate the tracking accuracy and robustness of the proposed approaches. The derived UCBs constitute a tool for trustworthiness evaluation of DGP approaches and the simulation results reveal that it characterizes the presence of the target states in the error bound with 88% and 42% higher probability in X and Y coordinates, respectively, than the confidence intervalbased method.

show abstract

Section: Related Workmentioning

confidence: 99%

Gaussian Process Upper Confidence Bounds in Distributed Point Target Tracking Over Wireless Sensor Networks

Liu

Mihaylova

George

et al. 2023

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

show abstract

“…We formulate a graphical model in Fig. 2 using the data association with GPs (DAGP) model [14], which allows us to handle the multi-modality introduced by falling down the waterfall. We specify this separation via the marginal likelihood p(s t+1 |ŝ t ) = p(s t+1 | σ t , f t , l t ) p(l t |ŝ t ) p(σ t |ŝ t ) p(f t |ŝ t ) dσ t dl t df t , (5) where f t = f (1) t , .…”

Section: An Interpretable Transition Modelmentioning

confidence: 99%

“…which introduces variational inducing inputs and outputs U as described in [14][15][16]. These inducing inputs independently characterize the respective model parts and enable us to do inference via stochastic optimization.…”

Section: An Interpretable Transition Modelmentioning

confidence: 99%

“…Based on a temperature parameter, concrete random variables yield samples which are almost discrete but which still yield informative gradients. For details we refer to [14].…”

Section: An Interpretable Transition Modelmentioning

confidence: 99%

“…We formulate a probabilistic model which contains such explicit models by interpreting the Wet-Chicken benchmark as a data association problem [10,11]. While many probabilistic interpretations of this problem assume that the relative importance of different modes is constant [12,13], we base our formulation on the DAGP model [14] which learns a non-parametric model of each mode and where the associations between the modes themselves is further controlled by a non-stationary stochastic process.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Bayesian decomposition of multi-modal dynamical systems for reinforcement learning

et al. 2020

Self Cite

View full text Add to dashboard Cite

In this paper, we present a model-based reinforcement learning system where the transition model is treated in a Bayesian manner. The approach naturally lends itself to exploit expert knowledge by introducing priors to impose structure on the underlying learning task. The additional information introduced to the system means that we can learn from small amounts of data, recover an interpretable model and, importantly, provide predictions with an associated uncertainty. To show the benefits of the approach, we use a challenging data set where the dynamics of the underlying system exhibit both operational phase shifts and heteroscedastic noise. Comparing our model to NFQ and BNN+LV, we show how our approach yields human-interpretable insight about the underlying dynamics while also increasing data-efficiency.

show abstract

Data Association with Gaussian Processes

Cited by 2 publications

References 5 publications

Gaussian Process Upper Confidence Bounds in Distributed Point Target Tracking Over Wireless Sensor Networks

Gaussian Process Upper Confidence Bounds in Distributed Point Target Tracking Over Wireless Sensor Networks

Bayesian decomposition of multi-modal dynamical systems for reinforcement learning

Contact Info

Product

Resources

About