“…14 through many experimentations. Even though the localization algorithms in [27] could enhance the accuracy of the ASC to some extent, through the enlarged rectangular region labeled by bright blue outline in Fig. 14 we can see that, the trace obtained by employing weighted probability algorithms and IEKF smooth the vibration in green dotted line and achieves more reasonable result.…”
Section: Experiments II (Zigbee-based Localization Of the Asc)mentioning
confidence: 98%
“…The objective of this experiment is to compare performance of ZigBee-based ASC localization method proposed in this paper with the ZigBee-based positioning method used in previous work [27]. In this experiment, the ASC follows the desired path, denoted by the (black) solid line in Fig.…”
Section: Experiments II (Zigbee-based Localization Of the Asc)mentioning
confidence: 99%
“…During the journey, the ASC received the measured ZigBee data of the blind node on the ASC every 1 s. The green dotted line in Fig. 14 shows the trace of ASC by utilizing the localization algorithms proposed in [27]. Based on the same raw ZigBee data, the red chain line in Fig.…”
Section: Experiments II (Zigbee-based Localization Of the Asc)mentioning
confidence: 99%
“…14 the ASC trace by employing the proposed weighted probability algorithm in this paper. Besides, an iterated extended Kalman filter, instead of EKF in [27], is used to reform the odometric position estimation when ZigBee data are received. The odometry trace, the (pink) dashed line in Fig.…”
Section: Experiments II (Zigbee-based Localization Of the Asc)mentioning
confidence: 99%
“…IR sensors [1] signals are limited in its available line of sight. Camera [2] is limited due to high sensitivity to light [27]. RF localization used in RADAR [3] is imprecise in locating targets.…”
This study investigates indoor localization problem of robot or a customer at shopping mall environment. To improve the localization accuracy, a sensor fusion-based approach is employed, which combines data from ZigBee, odometry of active shopping cart (ASC), and QR marker. The proposed algorithm employs Gaussian probability estimation method and thus it is adaptive to localization problem even at noisy environment such as the shopping mall. To implement the localization service, an ASC which is equipped with motors for navigation, a laser sensor for tracking, and a tablet computer for human-computer interaction is designed. Through experimental work, we corroborate the feasibility of the proposed localization algorithms.
“…14 through many experimentations. Even though the localization algorithms in [27] could enhance the accuracy of the ASC to some extent, through the enlarged rectangular region labeled by bright blue outline in Fig. 14 we can see that, the trace obtained by employing weighted probability algorithms and IEKF smooth the vibration in green dotted line and achieves more reasonable result.…”
Section: Experiments II (Zigbee-based Localization Of the Asc)mentioning
confidence: 98%
“…The objective of this experiment is to compare performance of ZigBee-based ASC localization method proposed in this paper with the ZigBee-based positioning method used in previous work [27]. In this experiment, the ASC follows the desired path, denoted by the (black) solid line in Fig.…”
Section: Experiments II (Zigbee-based Localization Of the Asc)mentioning
confidence: 99%
“…During the journey, the ASC received the measured ZigBee data of the blind node on the ASC every 1 s. The green dotted line in Fig. 14 shows the trace of ASC by utilizing the localization algorithms proposed in [27]. Based on the same raw ZigBee data, the red chain line in Fig.…”
Section: Experiments II (Zigbee-based Localization Of the Asc)mentioning
confidence: 99%
“…14 the ASC trace by employing the proposed weighted probability algorithm in this paper. Besides, an iterated extended Kalman filter, instead of EKF in [27], is used to reform the odometric position estimation when ZigBee data are received. The odometry trace, the (pink) dashed line in Fig.…”
Section: Experiments II (Zigbee-based Localization Of the Asc)mentioning
confidence: 99%
“…IR sensors [1] signals are limited in its available line of sight. Camera [2] is limited due to high sensitivity to light [27]. RF localization used in RADAR [3] is imprecise in locating targets.…”
This study investigates indoor localization problem of robot or a customer at shopping mall environment. To improve the localization accuracy, a sensor fusion-based approach is employed, which combines data from ZigBee, odometry of active shopping cart (ASC), and QR marker. The proposed algorithm employs Gaussian probability estimation method and thus it is adaptive to localization problem even at noisy environment such as the shopping mall. To implement the localization service, an ASC which is equipped with motors for navigation, a laser sensor for tracking, and a tablet computer for human-computer interaction is designed. Through experimental work, we corroborate the feasibility of the proposed localization algorithms.
Intellectualization of life is a general tendency due to the proliferation of technology and science. Based on this concept, this paper presents multi-group localization algorithms and detection algorithms for multi-group service robot system (MGSR). Shopping cart problem is considered as an exemplary multi-group service robot system. The MGSR is designed to provide users with co-service by multiple carts and allows multiple users operation simultaneously. In MGSR, a cart carrying personal belongings of the user follows the user automatically and provides real-time position information to the user. To fulfill estimating the location of MGSR, hybrid external localization algorithm based on combination of QR location information and ZigBee location estimate is proposed. To detect and track a cart by another cart with LRF, we define cart features in LRF data and employ a support vector data description method. Recognition of usercart groups in MGSR is realized by ZigBee blind nodes on the cart. We verified the feasibility of the proposed algorithms for MGSR through three experiment trials.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations鈥揷itations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.