Robust Tracking of Soccer Robots Using Random Finite Sets

Cano, Pablo; Ruiz‐del‐Solar, Javier

doi:10.1109/mis.2017.4531220

Cited by 8 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, the simulated central processing merges these distributions, obtaining the final solution in a distributed and cooperative way. Similarly to [ 62 ], the merging process is:

where

is the intensity estimated by i th distributed sensor, and R is the number of distributed sensors. Merge operation is a clustering technique.…”

Section: Application For Tracking Maritime Surveillancementioning

confidence: 99%

Cooperative-PHD Tracking Based on Distributed Sensors for Naval Surveillance Area

Lima¹,

Costa²

2022

Sensors

View full text Add to dashboard Cite

Brazil has an extensive coastline and Exclusive Economic Zone (EEZ) area, which are of high economic and strategic importance. A Maritime Surveillance System becomes necessary to provide information and data to proper authorities, and target tracking is crucial. This paper focuses on a multitarget tracking application to a large-scale maritime surveillance system. The system is composed of a sensor network distributed over an area of interest. Due to the limited computational capabilities of nodes, the sensors send their tracking data to a central station, which is responsible for gathering and processing information obtained by the distributed components. The local Multitarget Tracking (MTT) algorithm employs a random finite set approach, which adopts a Gaussian mixture Probability Hypothesis Density (PHD) filter. The proposed data fusion scheme, utilized in the central station, consists of an additional step of prune & merge to the original GM PHD filter algorithm, which is the main contribution of this work. Through simulations, this study illustrates the performance of the proposed algorithm with a network composed of two stationary sensors providing the data. This solution yields a better tracking performance when compared to individual trackers, which is attested by the Optimal Subpattern Assignment (OSPA) metric and its location and cardinality components. The presented results illustrate the overall performance improvement attained by the proposed solution. Moreover, they also stress the need to resort to a distributed sensor network to tackle real problems related to extended targets.

show abstract

“…Then, the simulated central processing merges these distributions, obtaining the final solution in a distributed and cooperative way. Similarly to [ 62 ], the merging process is:

where

is the intensity estimated by i th distributed sensor, and R is the number of distributed sensors. Merge operation is a clustering technique.…”

Section: Application For Tracking Maritime Surveillancementioning

confidence: 99%

Cooperative-PHD Tracking Based on Distributed Sensors for Naval Surveillance Area

Lima¹,

Costa²

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…The commonly used approaches in RoboCup are particle filter-based MCL 18,19 and EKF-based localization. 20,21 They can address the localization problem in competition scenario efficiently. In ref.…”

Section: Introductionmentioning

confidence: 99%

Self-Localization in Highly Dynamic Environments Based on Dual-Channel Unscented Particle Filter

2020

View full text Add to dashboard Cite

SUMMARY Self-localization in highly dynamic environments is still a challenging problem for humanoid robots with limited computation resource. In this paper, we propose a dual-channel unscented particle filter (DC-UPF)-based localization method to address it. A key novelty of this approach is that it employs a dual-channel switch mechanism in measurement updating procedure of particle filter, solving for sparse vision feature in motion, and it leverages data from a camera, a walking odometer, and an inertial measurement unit. Extensive experiments with an NAO robot demonstrate that DC-UPF outperforms UPF and Monte–Carlo localization with regard to accuracy.

show abstract

“…Within these restrictions, a relevant application is miniaturized terrestrial robotics. Examples are presented by Cano et al [17], who apply the Gaussian mixture PHD filter to track several robots with a single camera, and Farazi et al [18], who apply a neural network pipeline in real-time on an observer robot without existing environmental knowledge. Although both methods display promising accuracy, there is reliance on more detailed, higher-frequency imagery than what is typical for space-borne cameras [4].…”

Section: Introductionmentioning

confidence: 99%

Autonomous Angles-Only Multi-Target Tracking for Spacecraft Swarms

Kruger,

D'Amico

2020

Preprint

View full text Add to dashboard Cite

Autonomous angles-only relative navigation is a key enabler towards operating spacecraft swarms in deep space. However, current architectures for angles-only relative navigation do not consider the measurement assignment problem and simply assume that measurements are correctly assigned to targets. Consequently, there is a need for new algorithms which accurately and robustly assign measurements to multiple target space objects in view, without requiring existing relative orbit knowledge. This paper presents the Spacecraft Angles-Only Multi-Target Tracking Software algorithm that performs this task using only sequential camera images and under autonomous spacecraft limitations, applying 1) kinematic knowledge of target behavior in the observer's reference frame, and 2) principles of multi-hypothesis tracking to treat ambiguous measurement assignments. A measurement transform is introduced to ensure consistent elliptical target motion, and kinematically-derived track prediction, gating and scoring criteria are applied to greatly improve tracking efficiency and performance. Monte-Carlo testing demonstrates nearly 100% precision and strong recall in measurement assignment across a variety of multispacecraft formations, using both synthetic measurements and hardware-in-the-loop imagery. The algorithm can track across large data gaps and with significant measurement noise, and can cooperate with an angles-only navigation filter to improve accuracy in challenging cases.

show abstract

Robust Tracking of Soccer Robots Using Random Finite Sets

Cited by 8 publications

References 10 publications

Cooperative-PHD Tracking Based on Distributed Sensors for Naval Surveillance Area

Cooperative-PHD Tracking Based on Distributed Sensors for Naval Surveillance Area

Self-Localization in Highly Dynamic Environments Based on Dual-Channel Unscented Particle Filter

Autonomous Angles-Only Multi-Target Tracking for Spacecraft Swarms

Contact Info

Product

Resources

About