Prediction of 90-Degree Turn Using Kinematic Parameters for Implementation of Home Robot

Takeda, Kanako; Ogawa, Akihiro; Mita, Akira

doi:10.3130/aije.85.1027

Cited by 3 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…・Data Analysis Based on the previous studies' judgment criterion, we predicted targets' turning motions if the predictive parameters exceeded the thresholds pre-calculated. Previous studies adopted the predicted time to evaluate their prediction system of turning motion [11] [12]. The predicted time is defined as the time from when the predictive parameters exceeded the threshold value to the start time of the turning motion.…”

Section: Materials and Methods ・Experimental Setup And Subjectsmentioning

confidence: 99%

“…The problem with existing systems for predicting turning is that the participants' motions are limited by the experimental conditions. Specifically, the systems have been verified in an experimental environment [11] specially prepared to ensure reproducibility [12],and have not been verified in daily living environments [13]. Moreover, few studies have focused on architectural space design and the prediction of turning motions.…”

Section: Introductionmentioning

confidence: 99%

“…Moreover, few studies have focused on architectural space design and the prediction of turning motions. Takeda [12] compared the predictability of turning motions in a space with poor visibility and a large pillarless space, and they concluded that the prediction time was longer in a space with poor visibility and that head rotation was a parameter that depended on environmental factors. However, they used wearable sensors and did not measure natural motion.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Effects of architectural space design on predicting turning in daily life

Matsunami

2023

Materials Research Proceedings

View full text Add to dashboard Cite

Abstract. In recent years, the diversification of lifestyles and the increase in the number of elderly single-person households have increased the need to introduce robots and sensors into living spaces to control living spaces appropriately for individuals. To realize these goals, it is necessary to predict people’s non-steady motions which is one of the challenges in introducing robots into living spaces. In response, we have conducted research on motion prediction systems using robots and sensors. These studies will contribute to the realization of safe and comfortable architectural spaces by introducing robots into living spaces and collaborating with various space controls such as automatic doors and lighting. In this study, we focused on turning related to walking, which is the most basic motion in activities of daily living. As turning is a non-steady motion greatly affected by aging and disease, it is difficult to predict while is highly useful as a health indicator. Previous studies have suggested that architectural space design can influence the prediction of turning, but the actual effects are not clear because these studies were conducted only under highly constrained conditions in a laboratory environment. Thus, existing systems for predicting turning have not been validated in daily living environments due to issues such as instructions of motions to participants, limitations of natural motions because of contact sensors, and validation in experimental environments that are specially prepared to ensure reproducibility. Therefore, the purpose of this study was to introduce our sensing systems into actual living spaces and to validate our turning prediction system using acquired data on participants’ natural motion. In addition, the influence of architectural space design on predicting turning was clarified by conducting an experiment at a T-junction with an open space and a crossroad with poor visibility. In this study, an office space was selected as the experimental field as a living space to verify the feasibility of our turning prediction system.

show abstract

Section: Materials and Methods ・Experimental Setup And Subjectsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Effects of architectural space design on predicting turning in daily life

Matsunami

2023

Materials Research Proceedings

View full text Add to dashboard Cite

show abstract

生活空間を想定した歩行時90度方向転換動作の解析とリアルタイム予測

MOTOYAMA,

KONDO,

OGAWA

et al. 2024

Nihon Kenchiku Gakkai Kankyokei Ronbunshu

View full text Add to dashboard Cite

When introducing robots and sensors into living spaces, predicting turning movements while walking is an important element to ensure safety.In this study, we assumed a living space, set experimental conditions that did not interfere with the subjects' free movement, and measured natural turning movements.First, the parameters used for prediction were selected from the measured data. Then, using those parameters, he built a system that predicted 90-degree turning movements in real time. Finally, we verified the system. This research will contribute to the development and practical application of an analysis and prediction system for turning movements during walking.

show abstract

Prediction of Walking Turns Focusing on the Center of Gravity

SUGIMOTO

OGAWA

Mita

2022

Aij Journal of TECHNOLOGY and Design

View full text Add to dashboard Cite

This study revealed proper parameters to predict walking turns tosupport the residents as a built environment function. We used a non contact sensor that did not disturb everyday life and aimed to extract highly versatile prediction parameters by considering the movement strategy and the rotation direction. After carefully examining the prediction accuracy for the center-of-gravity shift and the head and upper body rotation parameters, we found the position of the head's center-of-gravity (Left-Right) and the head rotation (Yaw) were valuable indicators. The time needed for prediction was between 0.18 to 0.48 steps with a prediction accuracy of 70%.

show abstract

Prediction of 90-Degree Turn Using Kinematic Parameters for Implementation of Home Robot

Cited by 3 publications

References 15 publications

Effects of architectural space design on predicting turning in daily life

Effects of architectural space design on predicting turning in daily life

生活空間を想定した歩行時90度方向転換動作の解析とリアルタイム予測

Prediction of Walking Turns Focusing on the Center of Gravity

Contact Info

Product

Resources

About