阅读说明：本技术 用于控制行动装置的方法和装置 (Method and device for controlling mobile device ) 是由 张恂杰 阿南德·卡帕迪亚 于 2018-07-09 设计创作，主要内容包括：本申请公开一种行动装置的控制系统,包括控制器,控制器用于分析来自行动装置上的至少一个传感器的数据,其中数据用于确定用户的步态。然后,步态数据用于提供动作指令至行动装置上的电动马达。(A control system for a mobile device includes a controller for analyzing data from at least one sensor on the mobile device, wherein the data is used to determine a gait of a user. The gait data is then used to provide movement instructions to an electric motor on the mobility device.)

1. A method of controlling a mobile device having a motor, the system comprising:

receiving gait data from at least one inertial measurement unit;

determining a gait of the user based on the gait data and a preconfigured machine learning model; and

generating motion instructions using the determined gait.

2. The method of claim 1, wherein the gait data is selected from the group consisting of acceleration, gyroscope data, and quaternion data.

3. The method of claim 1, wherein said determining a gait of the user comprises detecting the gait of the user through a machine learning model.

4. The method of claim 3, further comprising:

the machine learning model is trained by a plurality of different modalities performed by a user on the mobile device and signaling various gaits to a control system.

5. The method of claim 1, further comprising cross-validating motion instructions between two mobile devices worn by the user.

6. The method of claim 5, wherein the step of cross-validating the action instructions comprises:

and if the action command of the first action device is similar to the action command of the second action device, converting the action command into a motor driving signal.

7. The method of claim 5, wherein the step of cross-validating the action instructions comprises:

and if the action command of the first action device is not similar to the action command of the second action device, converting the action command into a brake signal.

8. The method of claim 1, further comprising:

checking for user input from a remote control, an

An action instruction is rewritten based on the user input.

Background

The present invention relates to a mobile device (mobile device). More particularly, the present invention relates to a control system and a control method for a mobility device having an electric motor worn on a user's foot to provide mobility assistance.

Commuters and other travelers often must walk the last leg of the journey, whether they are traveling by car, bus, train or other means. The time required to complete the last leg of the journey depends on distance and may take up a considerable amount of the total duration of the journey. Although a bicycle or scooter may be used, the bicycle or scooter is bulky and requires skill and a minimum level of fitness to operate. Powered systems, such as moving walks, lack mobility. Other action solutions are limited by the same deficiencies or lack the ability to adapt to a particular user. It would therefore be advantageous to develop a control system for a mobile device that does not require any special skills or user training and that can be adapted to the individual needs of a specific user.

Disclosure of Invention

Embodiments of the present invention are systems and methods of controlling a mobile device, wherein the mobile device is worn on each foot of a user. The sensor obtains data related to a gait (gait) of the user and transmits the data to the processor. The processor analyzes the gait of the user and then generates motion instructions for each mobile device using the gait data. Each mobility device may include a motor, a gear arrangement, and a roller. When worn on the user's foot, the mobile device allows the user to walk at an increased speed for a given frequency and step size compared to the user's speed when the mobile device is not worn. Moreover, the control system has a high user adaptability, and the user does not need to learn or perform other control inputs.

Drawings

FIG. 1 depicts a mobile device with an embedded controller according to one embodiment of the present application.

FIG. 2 is a block diagram of a control system according to one embodiment of the present application.

Fig. 3 shows a flow chart of a control method using the controller depicted in fig. 2.

Detailed Description

As shown in fig. 1, a mobile device 100 according to an embodiment of the present invention includes a plurality of rollers 101, and at least one of the rollers 101 is connected to an electric motor 102. Fig. 1 also shows an onboard controller 111 and an optional remote controller 112. In normal use, a user will wear two mobile devices 100, one on each foot. The mobility device 100 enables a walker to walk faster than normal walking speed by adding torque to the rollers 101 of the mobility device 100 worn on the foot when contacting the ground. In this way, the user experiences an effect similar to walking on a moving sidewalk. More particularly, the control system 110 of the present invention allows the user to maintain normal walking motion by adjusting the control of the motor 102 to the user's movements. The wheel 101 is rotated by torque applied by a motor 102, and the rotational speed of the wheel 101 is controlled in part by analyzing the gait of the user, as will be described in more detail below.

Fig. 2 depicts elements of an onboard controller 111. The onboard controller 111 includes at least one inertial measurement unit 113, a processor 114, a motor driver 115, and a wireless communication module 116. Two on-board controllers 111 are shown in fig. 2, as each mobile device (i.e. one for each foot of the user) is equipped with one on-board controller 111. In another alternative embodiment, the control system 110 further includes a remote controller 112 capable of sending instructions to each of the onboard controllers 111. In this particular embodiment, both left and right mobile devices 100 receive a commanded speed from remote control 112, and drive the mobile device in accordance with the commanded speed, where remote control 112 may be in the form of a hand-held controller, computer, or cell phone.

The control system 110 is used to collect data and analyze the gait of the user. For example, the onboard processor 114 reads dynamic gait data from the inertial measurement unit 113, which includes acceleration, gyroscope data, and quaternion (quaternion) data for each mobile device 100. In one embodiment, both onboard controllers 111 send dynamic gait data to remote controller 112 and, in turn, receive motion commands from remote controller 112. The motion commands include, for example, acceleration to a set speed, braking, deceleration to a set speed, and holding at a constant speed. In alternative embodiments, other data may be included in the action instructions. Alternatively, the action instructions may be generated by the onboard controller 111. Upon receiving the motion command, the onboard processor 114, along with the motor driver 115, converts the motion command into a motor drive signal and drives the motor system 102, thereby affecting the speed of the scroll wheel 101. In one embodiment, the motor driver 115 is controlled via a feedback loop, receives a speed command and drives the motor 102 in accordance with the commanded speed.

Fig. 3 is a block diagram illustrating a method of gait-based motion control according to one embodiment, including the steps of receiving dynamic gait data 301, determining a user gait 302, and determining motion instructions 303.

In step 301, the remote controller receives dynamic gait data from two onboard controllers 111. The dynamic gait data includes data collected from the inertial measurement unit 113. Next, at step 302, a user gait is determined using machine learning model test data. Specifically, the remote controller receives gait data and predicts the gait of the user based on the trained model. In one embodiment, step 302 includes feeding back the dynamic gait data from the previous step to the beginning of a fixed size data buffer. When new data is received, the oldest data is discarded from the data buffer. The size of the buffer may be large enough to cover at least one full gait cycle of the dynamic gait data. The data buffer is then fed back to the pre-trained machine learning model to determine the user gait. According to an exemplary embodiment, the machine learning model may be a support vector machine (support vector machine). Further, alternative machine learning models may also be used. The user trains the machine learning model based on performing various gaits on mobile device 100 and sending their current gait signals to control system 110 via inputs on remote controller 112. At step 303, motion instructions are generated based on the determined gait.

Additionally, at optional step 304, remote controller 112 detects whether a user input has been registered. The user input may be in various forms, such as pressing a button or moving the remote controller 112 along a certain trajectory (trajectory). For example, the user input may press a button indicating that the user wants to move forward. In this way, receipt of forward motion instructions from the user may overwrite the motion instructions provided by the machine learning model-based controller 112. After detecting the user input at step 304, the remote controller 112 generates and sends action instructions to the two onboard controllers 111. However, if user input is received from step 304, the final action instruction is replaced by the user input before being sent to the on-board controller 111.

In another alternative embodiment, each on-board controller 111 generates a motion command and sends the motion command signal to another on-board controller 111 for cross-validation in step 305. The motion commands include accelerating to a set speed, braking, decelerating to a set speed, and maintaining at a constant speed. After verifying the motion command, the processor 114 together with the motor driver 115 converts the motion command into a motor driving signal and drives the motor system. In other words, in step 305, the cross validation compares the generated motion commands for each of the two mobile devices 100. For example, the motor driver 115 will only command the motor speed when the two commands are similar, and the motor driver 115 will apply the brake when the speed commands do not coincide.

While the present disclosure has been described in detail and with reference to specific embodiments thereof, it will be apparent to one skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the embodiments. Thus, it is intended that the present disclosure cover the modifications and variations of this disclosure provided they come within the scope of the appended claims and their equivalents.