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

Robotica ◽  
2020 ◽  
pp. 1-14
Author(s):  
Chen Hao ◽  
Liu Chengju ◽  
Chen Qijun

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.

2014 ◽  
Vol 556-562 ◽  
pp. 2266-2269
Author(s):  
Jiang Xue Fei ◽  
Song Yu

For mobile robot localization in known environment, the 5th-order Conjugate Unscented Particle Filter Monte Carlo Localization (CUPF-MCL) algorithm is proposed. CUPF-MCL combines the 5th-order Conjugate Unscented Transform (5th CUT) with Kalman Filter to generate more accuracy particle filter proposal distribution, calculating the transition density up to the 5th-order nonlinearity. In simulation, the performance of CUPF-MCL is compared with that of dead reckoning, PF-MCL, EPF-MCL and UPF-MCL. Results show that CUPF-MCL improves the accuracy of localization.


2019 ◽  
Vol 13 (1) ◽  
pp. 14-20 ◽  
Author(s):  
Xiao‐Hang Wu ◽  
Shen‐Min Song

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 2236
Author(s):  
Sichun Du ◽  
Qing Deng

Unscented particle filter (UPF) struggles to completely cover the target state space when handling the maneuvering target tracing problem, and the tracking performance can be affected by the low sample diversity and algorithm redundancy. In order to solve this problem, the method of divide-and-conquer sampling is applied to the UPF tracking algorithm. By decomposing the state space, the descending dimension processing of the target maneuver is realized. When dealing with the maneuvering target, particles are sampled separately in each subspace, which directly prevents particles from degeneracy. Experiments and a comparative analysis were carried out to comprehensively analyze the performance of the divide-and-conquer sampling unscented particle filter (DCS-UPF). The simulation result demonstrates that the proposed algorithm can improve the diversity of particles and obtain higher tracking accuracy in less time than the particle swarm algorithm and intelligent adaptive filtering algorithm. This algorithm can be used in complex maneuvering conditions.


2017 ◽  
Vol 14 (5) ◽  
pp. 172988141773275 ◽  
Author(s):  
Francisco J Perez-Grau ◽  
Fernando Caballero ◽  
Antidio Viguria ◽  
Anibal Ollero

This article presents an enhanced version of the Monte Carlo localization algorithm, commonly used for robot navigation in indoor environments, which is suitable for aerial robots moving in a three-dimentional environment and makes use of a combination of measurements from an Red,Green,Blue-Depth (RGB-D) sensor, distances to several radio-tags placed in the environment, and an inertial measurement unit. The approach is demonstrated with an unmanned aerial vehicle flying for 10 min indoors and validated with a very precise motion tracking system. The approach has been implemented using the robot operating system framework and works smoothly on a regular i7 computer, leaving plenty of computational capacity for other navigation tasks such as motion planning or control.


10.28945/4749 ◽  
2021 ◽  
Vol 20 ◽  
pp. 245-261
Author(s):  
Mariam Alawi Alhashmi ◽  
Omar Mubin ◽  
Rama Bassam Baroud

Aim/Purpose: This study sought to understand the views of both teachers and students on the usage of humanoid robots as teaching assistants in a specifically Arab context. Background: Social robots have in recent times penetrated the educational space. Although prevalent in Asia and some Western regions, the uptake, perception and acceptance of educational robots in the Arab or Emirati region is not known. Methodology: A total of 20 children and 5 teachers were randomly selected to comprise the sample for this study, which was a qualitative exploration executed using focus groups after an NAO robot (pronounced now) was deployed in their school for a day of revision sessions. Contribution: Where other papers on this topic have largely been based in other countries, this paper, to our knowledge, is the first to examine the potential for the integration of educational robots in the Arab context. Findings: The students were generally appreciative of the incorporation of humanoid robots as co-teachers, whereas the teachers were more circumspect, expressing some concerns and noting a desire to better streamline the process of bringing robots to the classroom. Recommendations for Practitioners: We found that the malleability of the robot’s voice played a pivotal role in the acceptability of the robot, and that generally students did well in smaller groups with the robot; teachers expressed concern that the children would become easily distracted should too many children be privy to one robot. Recommendation for Researchers: Our results provide valuable recommendations for researchers in the area. We believe, there needs to be continued efforts in devising suitable methodological assessment tools to evaluate student and teacher attitudes in the classroom particularly in the Arab world. We also advise researchers to focus on providing adaptive behavior in the context of educational robots. There are different distinct areas that need further clarifications and study based on our review. Impact on Society: On a wider scale, the findings of this paper have a huge implication for the educational technology as the integration of robotics in education is one of the emerging trends in the area, particularly in the UAE. This study allows to answer questions related to attitudes and perceptions of both teachers and students toward educational robots in the UAE. Future Research: Possible avenues of research in the area include focusing on the adaptive and natural behavior of robots in disciplines other than Mathematics as a means of successfully integrating robots in the classroom.


Sign in / Sign up

Export Citation Format

Share Document