• Title/Summary/Keyword: Electric scooter

Search Result 45, Processing Time 0.047 seconds

Development of segmentation-based electric scooter parking/non-parking zone classification technology (Segmentation 기반 전동킥보드 주차/비주차 구역 분류 기술의 개발)

  • Yong-Hyeon Jo;Jin Young Choi
    • Convergence Security Journal
    • /
    • v.23 no.5
    • /
    • pp.125-133
    • /
    • 2023
  • This paper proposes an AI model that determines parking and non-parking zones based on return authentication photos to address parking issues that may arise in shared electric scooter systems. In this study, we used a pre-trained Segformer_b0 model on ADE20K and fine-tuned it on tactile blocks and electric scooters to extract segmentation maps of objects related to parking and non-parking areas. We also presented a method to perform binary classification of parking and non-parking zones using the Swin model. Finally, after labeling a total of 1,689 images and fine-tuning the SegFomer model, it achieved an mAP of 81.26%, recognizing electric scooters and tactile blocks. The classification model, trained on a total of 2,817 images, achieved an accuracy of 92.11% and an F1-Score of 91.50% for classifying parking and non-parking areas.

Improvement on safety of an upright motor scooter driving (직립식 전동 스쿠터의 주행 안전성 개선)

  • Park, Lee-Su;Seo, Hwa-Seong;Kim, Jun-Seong;Ha, Sang-Hun
    • Proceedings of the KIEE Conference
    • /
    • 2009.07a
    • /
    • pp.1733_1734
    • /
    • 2009
  • 직립식 전동 스쿠터는 전동기를 이용한 근거리 이동 수단으로 일종의 1인용 스쿠터이다. 현재 여러가지 마이크로프로세서를 이용하여 주행을제어하는 직립식 전동 스쿠터가 개발되고 있다. 본 연구에서는 PIC16F877A와 자이로 및 가속도 센서를 이용하여 스쿠터의 운행 시 안정성을 개선할 수 있는 방법을 제시 하였다.

  • PDF

The Proposal of System Structure for Using Safe Personal Mobility Devices (안전한 개인형 이동장치 사용을 위한 시스템 구조 제안)

  • Kim, Wantae;Park, Byungjoon;Kim, Hyunsik
    • Journal of Korea Society of Digital Industry and Information Management
    • /
    • v.18 no.3
    • /
    • pp.33-41
    • /
    • 2022
  • Recently the use of personal mobility devices is rapidly increasing, and the businesses related to personal mobility devices are quickly growing as well. Although the use of personal mobility devices provides convenience for short distance movements, many problems occur due to the lack of safety devices and the absence of associated road traffic laws. The number of accidents caused by using personal mobility devices continues increasing every year, and the injuries or deaths are seriously happening with those accidents. When using personal mobility devices, there are basic safety precautions such as wearing a helmet, prohibiting boarding with more than two people, prohibiting boarding with more than 100kg, prohibiting using after drinking alcohol, and so on. However, it is exposed to traffic accidents because there is no way to check before using the system. Therefore, to ensure the user's safety in using the electric kickboard among personal mobility devices, this paper proposes a system that can check the user's safety state before using the electric kickboard. It is possible to safely use personal mobility devices and prevent accidents by proposing a system structure of the electric kickboard that can be used after checking for the use of more than two people, overweight, wearing a helmet, and drinking alcohol.

An Efficient Urban Outdoor Localization and Navigation System for Car-like Mobile Robots (자동차형 로봇의 도시 실외에서의 효율적인 위치 추정 및 네비게이션 시스템의 구현)

  • Yoon, Gun Woo;Kim, Jin Baek;Kim, Byung Kook
    • Journal of Institute of Control, Robotics and Systems
    • /
    • v.19 no.8
    • /
    • pp.745-754
    • /
    • 2013
  • An efficient urban outdoor localization and navigation system is proposed for car-like robots. First an accurate outdoor localization method is suggested using line/arc features and 2.5D map matching with LRFs (Laser Range Finders), which can reduce the number of singular cases and increase accuracy. Also, path generation, path tracking, and path modification algorithms are proposed for navigation. All these algorithms are implemented on an electric scooter to construct an autonomous urban outdoor localization and navigation system. Experiments reveal the practicality of the proposed system.

Study of IPMSM characteristic for electric scooter according to the shape of permanent magnet (영구자석 형상에 따른 전기 스쿠터용 IPMSM 특성 고찰)

  • Kim, Mi-Jung;Kim, Won-Ho;Jang, Ik-Sang;Lee, Ki-Doek;Lee, Jae-Jun;Han, Jeong-Ho;Jeong, Tae-Chul;Chae, Woong-Chan;Lee, Ju
    • Proceedings of the KIEE Conference
    • /
    • 2011.07a
    • /
    • pp.856-857
    • /
    • 2011
  • 최근 레저와 이동수단으로 전기를 이용한 스쿠터와 자전거가 많이 연구 개발되고 있다. 이러한 어플리케이션에 사용되는 모터의 경우은 설계 및 제어 비용이 저렴하면서도 소음이 작고, 출력밀도와 효율이 요구가 된다. 대부분의 경우 BLDC가 전동기 및 제어기 제작 단가가 저렴하여 자전거 및 스쿠터의 전기 추진용으로 많이 사용되었지만 소음 및 효율등의 성능면에서는 요구사항을 만족하지 못하고 있다. 이러한 단점을 보완하기 위해서 현재 출력밀도와 효율이 높은 IPMSM이 많이 연구 개발되고 있다. 본 논문에서는 전기 스쿠터용 IPMSM의 영구자석 형상에 따른 특성을 연구하였다.

  • PDF

Detection of Helmet on Electric Scooter (전동 킥보드 헬멧 착용 탐지)

  • Lee, Seon-yeop;Fu, Shirong;Park, Jong-il
    • Proceedings of the Korean Society of Broadcast Engineers Conference
    • /
    • fall
    • /
    • pp.201-204
    • /
    • 2021
  • 최근 전동 킥보드 사용량이 크게 늘었으나, 다른 이동수단 대비 낮은 안정성과 사용자들의 헬멧 착용에 대한 인식 부족으로 인해 사고의 위험성이 큰 상황이다. 이에 대하여 정부는 헬멧 착용을 강제하는 법률을 제정하였으나, 경찰력의 한계에 따른 단속 미비로 여전히 헬멧 착용율은 낮다. 본 연구는 YOLO v3 알고리즘을 통해 학습시킨 딥러닝 모델을 활용하여 도로 상황을 촬영한 동영상 내에서 헬멧 착용자와 미착용자를 구분하고 미착용자 탐지 시 알람을 제공하는 시스템을 제시한다. 기존 YOLO 알고리즘 및 신경망을 적용하되, 전동 킥보드 데이터를 새로 수집하고 클래스를 구분하여 학습시켰다. 소수의 탐지 및 분류 오류를 보정하기 위해, 히스토그램 간 유사도를 측정해 최종적으로 객체를 추적 및 확정하고, 객체에 대한 헬멧 착용 여부를 통계적으로 확인한다.

  • PDF

A Survey Study on the development of Omni-Wheel Drive Rider Robot with autonomous driving systems for Disabled People and Senior Citizens (자율주행 탑승용 옴니 드라이브 라이더 로봇 개발에 대한 장애인과 고령자의 욕구조사)

  • Rhee, G.M.;Kim, D.O.;Lee, S.C.
    • Journal of rehabilitation welfare engineering & assistive technology
    • /
    • v.6 no.1
    • /
    • pp.17-27
    • /
    • 2012
  • This study provides development information on Omni-Wheel Drive Rider Robot, futuristic electric scooters, with autonomous driving systems that are used for people including the disabled and senior. Also, it is meaningful in suggesting alternatives to replace motorized wheelchairs or electric scooters for the future. Prior to development of Omni-Wheel Drive Rider Robot with autonomous driving systems, it surveyed 49 people, including 18 people who own electric scooters and 31 senior people who have not. The summary of the survey is as follows. First, inconveniences during riding and exiting and short mileage due and safety driving to problems of recharging batteries are the most urgent task. For these problems, the study shows that charging time of batteries, mileage, armrests, footrests, angle of a seat are the primary considerations. Second, drivers prefer joystick over steering wheels because of convenience in one-handed driving against dangers from footrest and carriageways sloping roads, paving blocks. One-handed driving can reduce driving fatigues with automatic stop systems. Moreover, the study suggests many design factors related to navigation systems, obstacle avoidance systems, omni-wheels, automatic cover-opening systems in rainy.

  • PDF

A Study on Effective Floor Area for Wheelchair Users to Use Toilet (휠체어 사용자의 대변기 이용을 위한 화장실 유효바닥면적에 대한 연구)

  • Ryu, Sang-oh;Kim, Bo-hee;Park, Ji-young
    • Journal of The Korea Institute of Healthcare Architecture
    • /
    • v.24 no.2
    • /
    • pp.79-87
    • /
    • 2018
  • Purpose: The purpose of this paper is to provide logical basis on enlargement of toilet floor space for the disabled by "ACT ON GUARANTEE OF PROMOTION OF CONVENIENCE OF PERSONS WITH DISABILITIES, THE AGED, PREGNANT WOMEN. ETC" Revised Enforcement regulation [Asterisk 1] (2018.2.10.) and to help with making plans, designs and establishing policies by conducting experimental study with the enhanced floor area regulations. Methods: We conduct Experimental study, field work and interview for this paper. In experimental study, verification of the effective floor area was proceeded by measuring activity space for people in manual wheelchair, electric wheel chair and electric scooter and also reviewed useable area with the space expanded 0.2m both width and depth. In filed work, conducted an observation what other things (ex. sanitary equipment, hand rail and so on) can also affect the active space as well as effective floor space. In the interview, other problems and requirements that were not revealed were experimental study and observation of field work. Results : it's expected to provide better access to toilets for the disabled with the law revision of effective floor area. But, with the usage increasement of enlarged wheel chair and electric wheel chair, expanding side areas of toilet is also highly likely to be required going forward. Implications : Additional research is required on locations of exists and internal arrangement that effect the usage of toilet. It should be led to Universal design by making additional investigation and verification of the users patterns.

Current Revision Control according to Temperature of IPMSM in Electric Scooter (전기 스쿠터용 매입형 영구자석 동기전동기의 온도보상에 의한 전류 보정 제어)

  • Im, Jong-Bin;Ham, Sang-Hwan;Cho, Su-Yeon;Oh, Se-Young;Ryu, Gwang-Hyeon;Ahn, Han-Woong;Lee, Ju
    • Proceedings of the KIEE Conference
    • /
    • 2011.07a
    • /
    • pp.802-803
    • /
    • 2011
  • 매입형 영구자석 동기전동기는 강건한 회전자 구조와 릴럭턴스 토크를 사용할 수 있다는 점, 악계자 제어를 하기 쉽다는 점에서 넓은 속도와 토크를 필요로하는 하이브리드 차량이나 전기 차량에 적합한 전동기이다. 영구자석의 감자곡선은 온도에도 의존하기 때문에 온도에 따라 전동기의 자속과 토크가 변하게 된다. 이 논문은 전기 스쿠터에 사용되는 매입형 영구자석 동기전동기의 온도에 따른 지령 전류 보정에 의한 제어법에 대해 연구하였다. 토크 리플을 줄이기 위해서 속도-토크 곡선과 감자곡선을 이용하여 구하였으며, 보정된 지령 전류를 구하기 위해 Lagrange 보간법과 재귀 최소자승(Recursive Least Square : RLS) 법을사용하여 전류맵을 만들었다.이 지령 전류는 토크와 인버터 출력 전류값을 계산하는데 사용된다. 전류맵을 만들기 위해서 측정한 온도는 20, 80, 100도이다. 본 논문에서 제안한 제어법을 이용하여 토크 리플이 줄어듬을 시뮬레이션과 실험을 통해서 확인할 수 있었다.

  • PDF

Prediction Method of End of Charge Voltage using Battery Parameter Measurement (배터리 파라미터 측정을 이용한 충전종지전압 예측기법)

  • Kim, Ho-Yong;Wang, Yi-Pei;Park, Seong-Mi;Park, Sung-Jun;Son, Gyung-Jong
    • Journal of the Korean Society of Industry Convergence
    • /
    • v.25 no.3
    • /
    • pp.387-396
    • /
    • 2022
  • Recently, e-Mobility, which is a personal mobility device such as an electric bicycle or an electric scooter, is rapidly emerging. However, since E-Mobility has various voltage systems due to the characteristics of its products, it is essential for companies that operate them to use multiple dedicated chargers. A universal charger capable of charging batteries of various voltage systems with one charger is required to reduce the cost of purchasing and managing multiple dedicated chargers. For this, information on the EOC(End of Charge) is essential. In order to know the EOC, it is necessary to detect the internal impedance of the battery. However, the internal impedance of the battery changes according to various conditions such as SOH(State Of Health), SOC(State Of Charge), and ambient temperature. By observing the change in these parameters, the state of the battery can be diagnosed and the EOC can be predicted. In this paper, we propose an algorithm to analyze the battery's internal impedance and to predict the EOC, in order to acquire information on the EOC of the battery, which is an essential requirement of a universal charger.