...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>International Journal of Innovative Computing Information and Control >A NEW FALL DETECTION METHOD BASED ON FUZZY REASONING FOR AN OMNI-DIRECTIONAL WALKING TRAINING ROBOT
【24h】

A NEW FALL DETECTION METHOD BASED ON FUZZY REASONING FOR AN OMNI-DIRECTIONAL WALKING TRAINING ROBOT

机译：一种基于模糊推理的全向步行训练机器人跌倒检测新方法

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

To regain and then improve the walking ability for the people with lower limb disabled, the authors have been developing a new type of omnidirectional walking training robot (WTR). This WTR can help physical therapist to conduct the walking training for lower limb disabled by performing specific training course designed by the physical therapist. To ensure the training effect, a path tracking controller was proposed to enable the WTR to precisely track the designed path. However, there is the risk of the fall while carrying out walking training by the WTR, which lead the second damage to users. In order to improve the functionality and reliability of the WTR, a fall detection method is proposed based on the fuzzy reasoning method. In detail, a posture sensor and a two-dimensional (2D) laser sensor are used to detect the body's posture and positions of two legs for user in the WTR. Then, a fuzzy knowledge base differentiating the normal walking state and one kind of falling state is set up based on the fusion information of the two sensors. Furthermore, a fall detection strategy based on the combination of upper body posture and gait information is proposed, while the user's fall state is analyzed by a novel fuzzy reasoning mechanism. Finally, the effectiveness of the proposed method is verified by a series of experiments.
机译：为了恢复并提高下肢残疾者的步行能力，作者已经开发出一种新型的全向步行训练机器人（WTR）。该WTR通过执行物理治疗师设计的特定培训课程，可以帮助物理治疗师进行下肢残疾的步行训练。为了确保训练效果，提出了一种路径跟踪控制器，以使WTR能够精确跟踪设计的路径。但是，在WTR进行步行训练时，有跌倒的危险，这会对使用者造成第二次伤害。为了提高WTR的功能性和可靠性，提出了一种基于模糊推理方法的跌倒检测方法。详细地，在WTR中，姿势传感器和二维（2D）激光传感器用于检测用户的身体姿势和两条腿的位置。然后，基于两个传感器的融合信息，建立了区分正常行走状态和跌倒状态的模糊知识库。此外，提出了一种结合上半身姿势和步态信息的跌倒检测策略，并通过一种新型的模糊推理机制对用户的跌倒状态进行了分析。最后，通过一系列实验验证了该方法的有效性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号