Walking training system, control method thereof, and control program

Abstract

To provide a walking training system capable of offering effective training to a trainee, a control method thereof and a control program.SOLUTION: A walking training device includes: an estimation unit which estimates a ground contact position of a sole of one leg attached with a robot leg with a belt on the basis of a position of a hip joint portion of one leg specified from a photographed image of a camera and a posture angle of a thigh part and a bending angle of a knee joint of the one leg detected by a sensor part; a walking state determination unit which determines the shift from a standing state to a swinging state of the one leg on the basis of a state of a change in a load received from one leg of a trainee during a walking training specified on the basis of an estimation result by the estimation unit or a load received from the other leg among the loads detected by a load distribution sensor; and a control unit which starts bending control for the swinging state of the one leg by the robot leg when the walking state determination unit determines that the one leg has shifted from the standing state to the swinging state.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a walking training system, a control method thereof, and a control program thereof. [Background technology]

[0002] Patent Document 1 discloses a walking training system that includes a dynamic balance ability evaluation device for evaluating a user's dynamic balance ability based on changes over time in a specific body part caused by the user's walking, and a treadmill for the user to train in walking. For example, this walking training system has a pressure sensor attached to the belt of the treadmill, and detects the force (floor reaction force) with which the user kicks the belt from the measured value of the pressure sensor. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2016-73525 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, as in the related art, a pressure sensor attached to the belt of a treadmill alone cannot accurately determine which leg of the user (trainee) is bearing the load, and therefore cannot accurately detect the timing at which a specific leg of the user switches from a stance state to a swing state during walking training. In other words, the related art cannot accurately determine the walking state of the user. As a result, the related art has a problem in that it cannot provide effective walking training to the user.

[0005] The present invention has been made in consideration of the above background, and aims to provide a walking training system, a control method thereof, and a control program that are capable of providing effective training to a trainee by improving the accuracy of determining the walking state of the trainee. [Means for solving the problem]

[0006] A walking training system according to one embodiment of the present invention includes a robot leg attached to one leg of a trainee, a treadmill, a load distribution sensor attached to the treadmill and detecting a distribution of a load received from the sole of the foot of the trainee standing on the belt of the treadmill, a camera installed so as to be able to photograph at least a hip joint portion of the one leg, a sensor unit attached to the robot leg and detecting at least a posture angle of a thigh and a flexion angle of a knee joint of the one leg, and a position of a hip joint portion of the one leg identified from an image captured by the camera and a detection result by the sensor unit. The walking training system includes an estimation unit that estimates the contact position of the sole of the one leg attached to the leg on the belt, a walking state determination unit that determines whether the one leg has switched from a stance state to a swing state based on a change in the load received from the one leg of the trainee during walking training, or the load received from the other leg, among the loads detected by the load distribution sensor, which is specified based on the estimation result by the estimation unit, and a control unit that starts bending control of the one leg toward the swing state by the robot leg when the walking state determination unit determines that the one leg has switched from the stance state to the swing state. This walking training system estimates the contact position of the sole of the one leg of the trainee attached to the robot leg on the belt based on the image captured by the camera and the detection result of the sensor unit, thereby accurately determining the load received from the one leg among the loads detected by the load distribution sensor, and therefore accurately detecting the timing of the switch of the one leg from the stance state to the swing state. In other words, this walking training system can accurately determine the walking state of the trainee. As a result, this walking training system can flex and extend the robot legs at appropriate times, thereby providing the trainee with effective walking training.

[0007] The estimation unit may specify a position of a hip joint portion of the one leg from skeletal information of the one leg extracted from an image captured by the camera.

[0008] A marker may be attached to a hip joint portion of the one leg, and the estimation unit may identify a position of the hip joint portion of the one leg from a position of the marker extracted from the image captured by the camera.

[0009] The walking state determination unit may determine that the one leg has switched from a stance state to a swing state when a load received from the one leg changes from a first predetermined load or more to less than the first predetermined load.

[0010] The walking state determination unit determines that the one leg has switched from a stance state to a swing state when the load received from the other leg changes from less than a second predetermined load to equal to or greater than the second predetermined load.

[0011] A control method for a walking training system according to one embodiment of the present invention includes the steps of: detecting a distribution of a load received from the soles of the feet of a trainee standing on the belt of a treadmill using a load distribution sensor attached to the treadmill; photographing at least a hip joint portion of one leg to which a robot leg is attached using a camera; detecting at least a posture angle of the thigh and a flexion angle of the knee joint of the one leg using a sensor unit attached to the robot leg; and calculating a forward motion based on the position of the hip joint portion of the one leg identified from the image captured by the camera and the detection result by the sensor unit. The method includes the steps of: estimating a ground contact position of the sole of the one leg to which the robot leg is attached on the belt; determining whether the one leg has switched from a stance state to a swing state based on a change in the load received from the one leg of the trainee during walking training, which is determined based on the estimation result in the estimating step, among the loads detected by the load distribution sensor; and starting a flexion control for the swing state of the one leg by the robot leg when it is determined that the one leg has switched from the stance state to the swing state. This walking training system control method estimates a ground contact position of the sole of the one leg to which the robot leg is attached on the belt based on the image captured by the camera and the detection result of the sensor unit, thereby accurately determining the load received from the one leg among the loads detected by the load distribution sensor, and thus accurately detecting the timing of the switch from the stance state to the swing state of the one leg. In other words, this walking training system control method can accurately determine the walking state of the trainee. As a result, this control method for a walking training system can flex and extend the robot legs at appropriate timing, thereby providing the trainee with effective walking training.

[0012] A control program according to one embodiment of the present invention includes a process for detecting a distribution of a load received from the soles of the feet of a trainee standing on the belt of a treadmill using a load distribution sensor attached to a treadmill, a process for taking an image of at least a hip joint portion of one of the legs to which a robot leg is attached using a camera, a process for detecting at least a posture angle of a thigh and a flexion angle of a knee joint of the one of the legs using a sensor unit attached to the robot leg, and a process for detecting the position of the hip joint portion of the one of the legs specified from the image captured by the camera and a detection result by the sensor unit. The control program causes a computer to execute a process of estimating a contact position of the sole of the one leg to which the robot leg is attached on the belt, a process of determining whether the one leg has switched from a stance state to a swing state based on a change in the load received from the one leg of the trainee during walking training, or the load received from the other leg, among the loads detected by the load distribution sensor, which change is determined based on the estimation result of the estimation process, and a process of starting a flexion control for the swing state of the one leg by the robot leg when it is determined that the one leg has switched from the stance state to the swing state. This control program estimates a contact position of the sole of the one leg to which the robot leg is attached on the belt based on the image captured by the camera and the detection result of the sensor unit, thereby accurately determining the load received from the one leg among the loads detected by the load distribution sensor, and therefore accurately detecting the timing of the switch of the one leg from the stance state to the swing state. In other words, this control program can accurately determine the walking state of the trainee. As a result, this control program can flex and extend the robot legs at appropriate timing, thereby providing the trainee with effective walking training. Effect of the Invention

[0013] According to the present invention, it is possible to provide a walking training system, a control method, and a control program thereof that can provide effective training to a trainee by improving the accuracy of determining the walking state of the trainee. [Brief description of the drawings]

[0014] [Figure 1] 1 is an overall conceptual diagram showing an example of the configuration of a walking training device according to a first embodiment. [Diagram 2] 2 is a schematic side view of a portion of a treadmill provided in the walking training apparatus shown in FIG. 1. [Diagram 3] 2 is a schematic perspective view showing one configuration example of a walking assistance device (robot legs) provided in the walking training device shown in FIG. 1. FIG. [Figure 4] 2 is a block diagram showing an example of a system configuration of the walking training device shown in FIG. 1. [Diagram 5] FIG. 2 is a schematic perspective view for explaining an example of a method for estimating a contact position of a leg, to which a walking assistance device is attached, on a belt, using the walking training device shown in FIG. [Figure 6] 2 is a schematic plan view for explaining an example of a method for determining, by the walking training apparatus shown in FIG. 1, the load applied from the leg to which the walking assist device is attached. FIG. [Figure 7] 4 is a timing chart showing an example of a method for determining the walking state of a trainee by the walking training apparatus shown in FIG. [Figure 8] 1. FIG. 4 is a schematic plan view for explaining another example of the method for determining the walking condition of a trainee using the walking training apparatus shown in FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] The present invention will be described below through embodiments of the invention, but the invention according to the claims is not limited to the following embodiments. In addition, not all of the configurations described in the embodiments are necessarily essential as means for solving the problems. For clarity of explanation, the following description and drawings are omitted and simplified as appropriate. In each drawing, the same elements are given the same reference numerals, and repeated explanations are omitted as necessary.

[0016] <Embodiment 1> FIG. 1 is an overall conceptual diagram showing an example of a configuration of a walking training device according to the first embodiment. The walking training device 100 according to this embodiment is a specific example of a rehabilitation support device that supports the rehabilitation of a trainee (user) 900, and in particular, is a specific example of a walking training device that supports walking training. The walking training device 100 is a device for a trainee 900, who is a hemiplegic patient suffering from paralysis in one leg, to perform walking training under the guidance of a training staff member 901. Here, the training staff member 901 can be, for example, a therapist (physiotherapist) or a doctor, and can also be called a training instructor, training assistant, or training assistant, since the training staff member assists the trainee in training by guidance or assistance. The walking training device 100 can also be called a walking training system. Note that the up-down direction, left-right direction, and front-back direction in the following description are directions based on the orientation of the trainee 900.

[0017] The walking training device 100 mainly comprises a control panel 133 attached to a frame 130 that forms the overall skeleton, a treadmill 131 on which the trainee 900 walks, and a walking assistance device (robot leg) 120 that is attached to the affected leg, which is the paralyzed leg, of the trainee 900.

[0018] The treadmill 131 is a device that encourages the trainee 900 to walk, and the trainee 900 who is undergoing walking training gets on a belt 1311 and attempts to walk in accordance with the movement of the belt 1311. Note that the training staff 901 can stand on the belt 1311 behind the trainee 900 as shown in FIG. 1, for example, and walk together with the trainee, but it is usually preferable for the training staff 901 to be in a position that makes it easy to assist the trainee 900, such as standing astride the belt 1311.

[0019] FIG. 2 is a schematic side view of a portion of the treadmill 131. 2, the treadmill 131 at least includes a ring-shaped belt 1311, a pulley 1312, and a motor (not shown). A load distribution sensor 222 is provided on the inside of the belt 1311 (below the belt 1311 on which the trainee 900 sits) so as not to move in conjunction with the belt 1311. However, the load distribution sensor 222 may also be provided on the upper side of the belt 1311 so as to move in conjunction with the belt 1311.

[0020] The load distribution sensor 222 is composed of a plurality of sensors, which are arranged in a matrix on the underside of the belt 1311 supporting the soles of the trainee 900. By using these multiple sensors, the load distribution sensor 222 can detect the magnitude and distribution of the surface pressure (load) received from the soles of the trainee 900. For example, the load distribution sensor 222 is a resistance change detection type load detection sheet in which a plurality of electrodes are arranged in a matrix. The walking state of the trainee 900 (whether each leg is in a standing state or a swing state, etc.) can be determined based on the detection result of the load distribution sensor 222. A method for determining the walking state of the trainee 900 based on the detection result of the load distribution sensor 222 will be described later in detail.

[0021] In the treadmill 131, for example, the overall control unit 210 described later determines the walking state of the trainee 900 based on the detection result of the load distribution sensor 222, and rotates (moves) the ring-shaped belt 1311 by rotating the pulley 1312 using a motor (not shown) according to the walking state. This allows the trainee 900 to perform walking training without going beyond the belt 1311.

[0022] The frame 130 is erected on a treadmill 131 placed on the floor, and supports a control panel 133 that houses an overall control unit 210 that controls the motor and sensors, a training monitor 138 that is, for example, a liquid crystal panel that displays the progress of training to the trainee 900, and the like. The frame 130 also supports a front pulling unit 135 near the front of the upper part of the trainee 900's head, a harness pulling unit 112 near the upper part of the head, and a rear pulling unit 137 near the rear of the upper part of the head. The frame 130 also includes handrails 130a for the trainee 900 to grasp.

[0023] The handrails 130a are arranged on both the left and right sides of the trainee 900. Each handrail 130a is arranged in a direction parallel to the walking direction of the trainee 900. The handrails 130a are adjustable in vertical and horizontal positions. In other words, the handrails 130a can include a mechanism for changing their height and width. Furthermore, the handrails 130a can be configured so that their inclination angle can be changed, for example, by adjusting the height to be different between the front side and the rear side in the walking direction. For example, the handrails 130a can be given an inclination angle that gradually increases along the walking direction.

[0024] The handrail 130a is also provided with a handrail sensor 218 that detects the load received from the trainee 900. For example, the handrail sensor 218 can be a resistance change detection type load detection sheet in which electrodes are arranged in a matrix. The handrail sensor 218 can also be a six-axis sensor that combines a three-axis acceleration sensor (x, y, z) and a three-axis gyro sensor (roll, pitch, yaw). However, the type and installation position of the handrail sensor 218 are not important.

[0025] The camera 140 functions as an imaging unit for observing the entire body (at least the position of the hip joints) of the trainee 900. The camera 140 is installed near the training monitor 138 so as to face the trainee. The camera 140 takes still images and videos of the trainee 900 during training. The camera 140 includes a lens and imaging element set that provides an angle of view sufficient to capture the entire body of the trainee 900. The imaging element is, for example, a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor, and converts an optical image formed on an imaging surface into an image signal.

[0026] The coordinated operation of the front pulling section 135 and the rear pulling section 137 offsets the load of the walking assistance device 120 so that it does not become a burden on the affected leg, and further assists the swinging motion of the affected leg according to the set degree.

[0027] One end of the front wire 134 is connected to a winding mechanism of the front pulling unit 135, and the other end is connected to the walking assist device 120. The winding mechanism of the front pulling unit 135 turns on and off a motor (not shown), thereby winding or unwinding the front wire 134 in response to the movement of the affected leg. Similarly, one end of the rear wire 136 is connected to a winding mechanism of the rear pulling unit 137, and the other end is connected to the walking assist device 120. The winding mechanism of the rear pulling unit 137 turns on and off a motor (not shown), thereby winding or unwinding the rear wire 136 in response to the movement of the affected leg. Such coordinated operation of the front pulling unit 135 and the rear pulling unit 137 offsets the load of the walking assist device 120 so that the load does not become a burden on the affected leg, and further assists the swinging motion of the affected leg according to the set degree.

[0028] For example, the training staff 901, as an operator, sets a high assist level for a trainee with severe paralysis. When the assist level is set high, the front pulling unit 135 winds up the front wire 134 with a relatively large force in accordance with the timing of the swing of the affected leg. As the training progresses and assistance is no longer necessary, the training staff 901 sets the assist level to the minimum. When the assist level is set to the minimum, the front pulling unit 135 winds up the front wire 134 with a force sufficient to cancel the weight of the walking assist device 120 in accordance with the timing of the swing of the affected leg.

[0029] The walking training device 100 further includes a fall prevention harness device constituted by an attachment 110 , a harness wire 111 , and a harness tensioning portion 112 .

[0030] The harness 110 is a belt that is wrapped around the abdomen of the trainee 900 and is fixed to the waist by, for example, a hook and loop fastener. The harness 110 includes a connecting hook 110a that connects one end of a harness wire 111 that is a hanging device, and can also be called a hanger belt. The trainee 900 wears the harness 110 so that the connecting hook 110a is located at the rear of the trainee.

[0031] One end of the harness wire 111 is connected to the connecting hook 110a of the harness 110, and the other end is connected to a winding mechanism of the harness tensioning unit 112. The winding mechanism of the harness tensioning unit 112 winds and unwinds the harness wire 111 by turning on and off a motor (not shown). With this configuration, when the trainee 900 is about to fall, the fall prevention harness device winds up the harness wire 111 in accordance with an instruction from the overall control unit 210 that detects the movement, and the harness 110 supports the upper body of the trainee 900, preventing the trainee 900 from falling.

[0032] The orthosis 110 includes a posture sensor 217 for detecting the posture of the trainee 900. The posture sensor 217 is, for example, a combination of a gyro sensor and an acceleration sensor, and outputs the inclination angle of the abdomen on which the orthosis 110 is worn with respect to the direction of gravity.

[0033] The management monitor 139 is a display input device mainly used for monitoring and operation by the training staff 901, and is attached to the frame 130. The management monitor 139 is, for example, a liquid crystal panel, and a touch panel is provided on its surface. The management monitor 139 displays various menu items related to training settings, various parameter values ​​during training, training results, etc. In addition, an emergency stop button 232 is provided near the management monitor 139. When the training staff 901 presses the emergency stop button 232, the walking training device 100 is brought to an emergency stop.

[0034] The walking assist device 120 is attached to the affected leg of the trainee 900, and assists the trainee 900 in walking by reducing the load of extension and flexion on the knee joint of the affected leg. The walking assist device 120 transmits data on the leg movement obtained by walking training to the overall control unit 210, and drives the joint parts according to instructions from the overall control unit 210. The walking assist device 120 can also be connected via a wire or the like to a hip joint (a connection member having a rotating part) attached to the brace 110, which is part of the forward-transfer prevention harness device.

[0035] (Details of the walking aid device 120) 3 is a schematic perspective view showing a configuration example of the walking assist device 120. The walking assist device 120 mainly includes a control unit 121 and a plurality of frames that support each part of the affected leg. The walking assist device 120 is also called a robotic leg.

[0036] The control unit 121 includes an assist control section 220 that controls the walking assist device 120, and also includes a motor (not shown) that generates a driving force to assist the extension and flexion of the knee joint. The frame that supports each part of the affected leg includes an upper leg frame 122 and a lower leg frame 123 rotatably connected to the upper leg frame 122. This frame also includes a foot frame 124 rotatably connected to the lower leg frame 123, a front connecting frame 127 for connecting the front wire 134, and a rear connecting frame 128 for connecting the rear wire 136.

[0037] The upper leg frame 122 and the lower leg frame 123 rotate relatively around the hinge axis Ha shown in the figure. The motor of the control unit 121 rotates according to the instruction of the auxiliary control unit 220, and biases the upper leg frame 122 and the lower leg frame 123 to open or close relatively around the hinge axis Ha.

[0038] The angle sensor 223 includes, for example, a posture angle sensor 223a and a knee angle sensor 223b. The posture angle sensor 223a is attached to the thigh of the trainee 900 and detects the posture angle (roll, pitch, yaw angle, etc.) of the thigh. The knee angle sensor 223b is, for example, a rotary encoder and detects the angle (θ) between the upper leg frame 122 and the lower leg frame 123 around the hinge axis Ha. The lower leg frame 123 and the foot frame 124 rotate relatively around the hinge axis Hb shown in the figure. The angle range of the relative rotation is adjusted in advance by the adjustment mechanism 126. Note that the angle sensor 223 may further include, in addition to the posture angle sensor 223a and the knee angle sensor 223b, a sensor that detects the angle of the ankle joint, for example.

[0039] The front connecting frame 127 extends in the left-right direction on the front side of the upper leg, and is provided so as to connect to the upper leg frame 122 at both ends. The front connecting frame 127 is provided with a connecting hook 127a for connecting the front wire 134 near the center in the left-right direction. The rear connecting frame 128 extends in the left-right direction on the rear side of the lower leg, and is provided with a connecting hook 128a for connecting the rear wire 136 near the center in the left-right direction.

[0040] The upper leg frame 122 includes an upper leg belt 129. The upper leg belt 129 is a belt that is integrally provided on the upper leg frame, and is wrapped around the upper leg of the affected leg to fix the upper leg frame 122 to the upper leg. This prevents the entire walking assist device 120 from slipping off relative to the leg of the trainee 900.

[0041] (System configuration example of walking training device 100) Next, an example of the system configuration of the walking training device 100 will be described with reference to FIG. FIG. 4 is a block diagram showing an example of the system configuration of the walking training device 100.

[0042] As shown in FIG. 4, the system configuration of the walking training device 100 includes an overall control unit 210, a treadmill driving unit 211, an operation receiving unit 212, a display control unit 213, a tension driving unit 214, a harness driving unit 215, an image processing unit 216, a posture sensor 217, a handrail sensor 218, a load distribution sensor 222, a communication connection IF (interface) 219, and a walking assistance device 120.

[0043] The overall control unit 210 is, for example, an MPU (Micro Processing Unit), and controls the entire device by executing a control program read from the system memory.

[0044] The treadmill driving unit 211 includes a motor that rotates the belt 1311 of the treadmill 131 and its driving circuit. The overall control unit 210 executes rotation control of the belt 1311 by sending a driving signal to the treadmill driving unit 211. The overall control unit 210 adjusts the rotation speed of the belt 1311 according to, for example, a walking speed set by the training staff 901. Alternatively, the overall control unit 210 adjusts the rotation speed of the belt 1311 according to the walking state of the trainee 900 determined from the detection result of the load distribution sensor 222.

[0045] The operation reception unit 212 receives input operations by the training staff 901 via operation buttons provided on the device, a touch panel superimposed on the management monitor 139, or an attached remote control. The operation signal received by the operation reception unit 212 is transmitted to the overall control unit 210. Based on the operation signal received by the operation reception unit 212, the overall control unit 210 can give instructions to switch the power on and off or to start training. In addition, numerical values ​​related to settings can be input and menu items can be selected. Note that the operation reception unit 212 is not limited to receiving input operations by the training staff 901, and can naturally also receive input operations by the trainee 900.

[0046] The display control unit 213 receives a display signal from the overall control unit 210, generates a display image, and displays it on the training monitor 138 or the management monitor 139. The display control unit 213 generates an image showing the progress of training or a real-time video captured by the camera 140 according to the display signal.

[0047] The tension drive unit 214 includes a motor and its drive circuit provided in the front tension unit 135 for pulling the front wire 134, and a motor and its drive circuit provided in the rear tension unit 137 for pulling the rear wire 136. The overall control unit 210 controls the winding of the front wire 134 and the winding of the rear wire 136 by sending a drive signal to the tension drive unit 214. The overall control unit 210 also controls the tension of each wire by controlling the drive torque of the motor, not limited to the winding operation. Furthermore, the overall control unit 210 identifies the timing at which the affected leg switches from a stance state to a swing state from the detection result of the load distribution sensor 222, for example, and assists the swinging motion of the affected leg by increasing or decreasing the tension of each wire in synchronization with that timing.

[0048] The harness drive unit 215 includes a motor and its drive circuit for pulling the harness wire 111, which are provided in the harness tension unit 112. The overall control unit 210 controls the winding of the harness wire 111 and the pulling force of the harness wire 111 by sending a drive signal to the harness drive unit 215. For example, when predicting a fall of the trainee 900, the overall control unit 210 winds up a certain amount of the harness wire 111 to prevent the trainee from falling.

[0049] The image processing unit 216 is connected to the camera 140 and can receive an image signal from the camera 140. The image processing unit 216 receives an image signal from the camera 140 according to instructions from the overall control unit 210, and generates image data by image processing the received image signal. The image processing unit 216 can also perform specific image analysis by performing image processing on the image signal received from the camera 140 according to instructions from the overall control unit 210. For example, the image processing unit 216 detects the position of the foot of the affected leg in contact with the treadmill 131 (the stance position) by image analysis. Specifically, for example, the image area near the tip of the foot frame 124 is extracted, and an identification marker drawn on the belt 1311 that overlaps with the tip is analyzed to calculate the stance position.

[0050] As described above, the posture sensor 217 detects the inclination angle of the abdomen of the trainee 900 with respect to the direction of gravity, and transmits a detection signal to the overall control unit 210. The overall control unit 210 calculates the posture of the trainee 900, specifically the inclination angle of the trunk, using the detection signal from the posture sensor 217. Note that the overall control unit 210 and the posture sensor 217 may be connected by wire or by short-range wireless communication.

[0051] The handrail sensor 218 detects the load applied to the handrail 130a. In other words, the load that the trainee 900 cannot support with both legs is applied to the handrail 130a. The handrail sensor 218 detects this load and transmits a detection signal to the overall control unit 210.

[0052] As described above, the load distribution sensor 222 detects the magnitude and distribution of the surface pressure (load) received from the soles of the trainee 900, and transmits a detection signal to the overall control unit 210. The overall control unit 210 receives and analyzes the detection signal to determine the walking state, estimate switching, and the like.

[0053] The overall control unit 210 also serves as a function execution unit that executes various calculations and controls related to control. The overall control unit 210 includes, for example, a walking evaluation unit 210a, an exercise determination unit 210b, an estimation unit 210c, a walking state determination unit 210d, and a bending / extension control unit 210e. The estimation unit 210c, the walking state determination unit 210d, and the bending / extension control unit 210e will be described later.

[0054] The walking evaluation unit 210a uses data acquired from various sensors to evaluate whether or not the walking movement of the trainee 900 is abnormal. The training determination unit 210b determines the training result for a series of walking training based on, for example, the accumulated number of abnormal walks evaluated by the walking evaluation unit 210a.

[0055] The method and criteria for judging the training results may be set arbitrarily. For example, the training result may be determined by comparing the amount of movement of the paralyzed body part with a standard for each walking phase. The walking phase is a classification of one walking period (one walking cycle) for the affected leg (or healthy leg) into a stance phase in a stance state, a transition period from the stance phase to a swing phase in a swing state, a swing phase, and a transition period from the swing phase to the stance phase. The walking phase can be classified (determined) based on, for example, the detection result by the load distribution sensor 222. As described above, the walking cycle can be treated as one cycle consisting of a stance phase, a transition phase, a swing phase, and a transition phase, but it does not matter which period is defined as the start phase. In addition, the walking cycle can also be treated as one cycle consisting of, for example, a both-leg support state, a single-leg (affected leg) support state, a both-leg support state, and a single-leg (healthy leg) support state, and in this case, it does not matter which state is defined as the start state.

[0056] Furthermore, the gait cycle focusing on the right or left leg (healthy or affected leg) can be further subdivided. For example, the stance phase can be expressed by dividing it into an initial contact and four phases, and the swing phase into three phases. The initial contact refers to the moment when the observed foot touches the floor, and the four phases of the stance phase refer to the load response phase, mid-stance phase, end-stance phase, and pre-swing phase. The load response phase is the period from the initial contact to the moment when the opposite foot leaves the floor (opposite side take-off). The mid-stance phase is the period from the opposite side take-off to the moment when the heel of the observed foot leaves the floor (heel-off). The end-stance phase is the period from heel-off to the initial contact on the opposite side. The pre-swing phase is the period from the initial contact on the opposite side to the moment when the observed foot leaves the floor (take-off). The three phases of the swing phase refer to the early swing phase, mid-swing phase, and late swing phase. The early swing phase is the period from the end of the pre-swing phase (ground release) to when both feet cross (foot crossing). The mid-swing phase is the period from when the feet cross until the tibia becomes vertical (tibia vertical). The end-swing phase is the period from when the tibia becomes vertical until the next initial contact.

[0057] The communication connection IF 219 is an interface connected to the overall control unit 210, and is an interface for giving commands to the walking assist device 120 attached to the affected leg of the trainee 900 and receiving sensor information.

[0058] The walking assist device 120 may include a communication connection IF 229 that is connected to the communication connection IF 219 by wire or wirelessly. The communication connection IF 229 is connected to an assist control unit 220 of the walking assist device 120. The communication connection IFs 219 and 229 are communication interfaces such as a wired LAN or a wireless LAN that conforms to a communication standard.

[0059] The walking assist device 120 may also include an assist control unit 220, a joint driving unit 221, and an angle sensor 223. The assist control unit 220 is, for example, an MPU, and controls the walking assist device 120 by executing a control program provided by the overall control unit 210. The assist control unit 220 also notifies the overall control unit 210 of the state of the walking assist device 120 via communication connection IFs 219 and 229. The assist control unit 220 also receives commands from the overall control unit 210 and controls the walking assist device 120, such as starting and stopping.

[0060] The joint driving section 221 includes a motor of the control unit 121 and its driving circuit. The auxiliary control section 220 sends a driving signal to the joint driving section 221 to assist the upper leg frame 122 and the lower leg frame 123 to open or close relatively around the hinge axis Ha. This action assists the extension and bending of the knee and prevents the knee from bending.

[0061] As described above, the angle sensor 223 has the posture angle sensor 223a and the knee angle sensor 223b. The posture angle sensor 223a is attached to the thigh of the trainee 900, detects the posture angle of the thigh (roll, pitch, yaw angle, etc.), and transmits a detection signal to the auxiliary control unit 220. The knee angle sensor 223b detects the angle (θ) formed between the upper leg frame 122 and the lower leg frame 123 around the hinge axis Ha, and transmits a detection signal to the auxiliary control unit 220. The auxiliary control unit 220 receives these detection signals and calculates the opening angle of the knee joint.

[0062] Here, if an attempt is made to determine the walking state of the trainee 900 based only on the detection result of the load distribution sensor 222 attached to the treadmill 131 as in the related art, it is not possible to accurately determine which leg of the trainee 900 is receiving the load detected by the load distribution sensor 222, and therefore it is not possible to accurately detect the timing at which the leg wearing the walking assist device (robot leg) 120 switches from a standing state to a swing state. In other words, it is not possible to accurately determine the walking state of the trainee 900. As a result, the trainee 900 is unable to perform effective walking training.

[0063] In this embodiment, the estimation unit 210c estimates the contact position of the sole of the leg (affected leg) wearing the walking assist device 120 on the belt 1311 based on the analysis result of the image captured by the camera 140 and the detection result of the angle sensor 223. In this embodiment, the walking state determination unit 210d determines whether the leg wearing the walking assist device 120 has switched from the stance state to the swing state based on the change in the load received from the leg wearing the walking assist device 120 (or the opposite leg) specified based on the estimation result by the estimation unit 210c among the loads detected by the load distribution sensor 222. In this embodiment, when the walking state determination unit 210d determines that the leg wearing the walking assist device 120 has switched from the stance state to the swing state, the bending and stretching control unit 210e starts bending control for the swing state by the walking assist device 120.

[0064] As a result, the walking training device 100 according to this embodiment can accurately determine the load received from the leg wearing the walking assist device 120 among the loads detected by the load distribution sensor 222, and can accurately detect the timing when the leg wearing the walking assist device 120 switches from the stance state to the swing state. In other words, the walking training device 100 according to this embodiment can accurately determine the walking state of the trainee 900. As a result, the walking training device 100 according to this embodiment can flex and extend the walking assist device 120 at appropriate timing, and can provide the trainee 900 with effective walking training.

[0065] (An example of a method for estimating the position of the belt on the affected leg and a method for determining the load applied by the affected leg) Fig. 5 is a schematic perspective view for explaining an example of a method for estimating the ground contact position of the leg (affected leg) to which the walking assist device 120 is attached on the belt 1311. Fig. 6 is a schematic plan view for explaining an example of a method for determining the load received from the leg (affected leg) to which the walking assist device 120 is attached. Note that in the examples of Figs. 5 and 6, a case will be described in which the right leg is the affected leg to which the walking assist device 120 is attached and the left leg is the healthy leg.

[0066] 5, the estimation unit 210c extracts skeletal information of the right leg (affected leg) from the image captured by the camera 140, and identifies the position of the hip joint part P1 of the right leg from the extracted skeletal information. The estimation unit 210c may identify not only the position of the hip joint part P1 of the right leg but also the positions of other joint parts such as a knee joint from the skeletal information of the right leg (affected leg) extracted from the image captured by the camera 140. The estimation unit 210c estimates the ground contact position (expected ground contact position) P2 of the sole of the right leg (for example, the heel part) on the belt 1311 based on the position of the hip joint part P1 identified from the image captured by the camera 140, the posture angle of the thigh detected by the posture angle sensor 223a, and the flexion angle (θ) of the knee joint detected by the knee angle sensor 223b. The estimation unit 210c may further refer to the flexion angle of the ankle joint and the like when estimating the ground contact position P2 of the sole of the right leg on the belt 1311 in addition to the above-mentioned information. Here, by registering in advance the shape of the sole of the trainee 900 or by registering in advance a specified shape or a specified area, it is possible to estimate the contact surface (anticipated contact surface) E1 of the sole of the right leg.

[0067] The estimation unit 210c is not limited to identifying the position of the hip joint part P1 of the right leg from the skeletal information of the right leg (affected leg) extracted from the video captured by the camera 140, but may extract the marker from the video captured by the camera 140 and identify the position of the hip joint part P1 of the right leg from the position of the extracted marker, if a marker is attached to the hip joint part P1 of the right leg, for example. If markers are attached to other joint parts in addition to the hip joint part P1 of the right leg, the estimation unit 210c may identify the positions of multiple joint parts including the hip joint part P1 of the right leg from the positions of multiple markers extracted from the video captured by the camera 140.

[0068] As a result, as shown in FIG. 6, the walking condition discrimination unit 210d can identify that, among the loads FL, FR detected by the load distribution sensor 222, the load FR that overlaps with the contact surface E1 of the sole of the right leg (affected leg) estimated by the estimation unit 210c is the load received from the right leg.

[0069] (An example of a method for determining the walking state of the trainee 900) Fig. 7 is a timing chart showing an example of a method for determining the walking state of a trainee 900 by the walking training device 100. In the example of Fig. 7, a case will be described in which the right leg is the affected leg wearing the walking assist device 120 and the left leg is the healthy leg. Also, in the example of Fig. 7, detection of the timing of switching from the stance state to the swing state of the affected right leg will be mainly described.

[0070] 7, the walking state determination unit 210d determines that the right leg has switched from a stance state to a swing state when the load value of the right leg (affected leg) detected by the load distribution sensor 222 changes from a threshold value D1 or more to a value less than the threshold value D1 (times t11, t12, and t13). When the walking state determination unit 210d determines that the right leg has switched from a stance state to a swing state, the flexion / extension control unit 210e starts flexion control for the swing state by the walking assist device 120 attached to the right leg.

[0071] The threshold D1 can be set to an arbitrary load value for each trainee 900. For example, the threshold D1 is set to a predetermined load value by an operation of the trainee 900 or the training staff 901. Specifically, the threshold D1 is set to a load value of, for example, about 1 kg. Alternatively, the threshold D1 may be set to a load value that is a predetermined percentage of the maximum load received from the affected leg (the load value received from the affected leg when standing on only the affected leg). Specifically, the threshold D1 may be set to a load value that is, for example, about 10% of the maximum load received from the affected leg.

[0072] Alternatively, the threshold D1 may be set to a load value that is a predetermined percentage of the total value of the loads received from both legs. In this case, the walking state determination unit 210d determines that the affected right leg has switched from a stance state to a swing state, for example, at the timing when the load received from the affected right leg changes from a predetermined percentage or more of the total value of the loads received from both legs to less than the predetermined percentage.

[0073] (Another example of a method for determining the walking state of the trainee 900) Fig. 8 is a timing chart showing another example of the method for determining the walking state of the trainee 900 by the walking training device 100. In the example of Fig. 8, a case will be described in which the right leg is the affected leg wearing the walking assist device 120 and the left leg is the healthy leg. Also, in the example of Fig. 8, detection of the timing of switching from the stance state to the swing state of the affected right leg will be mainly described.

[0074] 8, the walking state determination unit 210d determines that the right leg (affected leg) has switched from a stance state to a swing state at the timing when the load value of the left leg (healthy leg) detected by the load distribution sensor 222 changes from less than the threshold D2 to equal to or greater than the threshold D2 (times t21, t22, and t23). When the walking state determination unit 210d determines that the right leg (affected leg) has switched from a stance state to a swing state, the flexion / extension control unit 210e starts flexion control for the swing state by the walking assist device 120 attached to the right leg.

[0075] The threshold D2 can be set to an arbitrary load value for each trainee 900. For example, the threshold D2 is set to a predetermined load value by an operation of the trainee 900 or the training staff 901. Specifically, the threshold D2 is set to a load value of, for example, about 5 kg. Alternatively, the threshold D2 may be set to a load value that is a predetermined percentage of the maximum load received from the affected leg (the load value received from the affected leg when standing on only the affected leg). Specifically, the threshold D2 may be set to a load value that is, for example, about 60% of the maximum load received from the affected leg.

[0076] Alternatively, the threshold D2 may be set to a load value that is a predetermined percentage of the total load value from both legs. In this case, the walking state determination unit 210d determines that the affected right leg has switched from a stance state to a swing state when the load from the healthy left leg changes from less than a predetermined percentage of the total load value from both legs to a predetermined percentage or more.

[0077] As described above, the walking training device 100 according to the present embodiment estimates the contact position of the sole of the leg (affected leg) wearing the walking assist device 120 on the belt 1311 based on the analysis result of the image captured by the camera 140 and the detection result of the angle sensor 223. As a result, the walking training device 100 according to the present embodiment can accurately determine the load received from the leg wearing the walking assist device 120 (or the opposite leg) among the loads detected by the load distribution sensor 222, and can accurately detect the timing of switching from the stance state to the swing state of the leg wearing the walking assist device 120. In other words, the walking training device 100 according to the present embodiment can accurately determine the walking state of the trainee 900. As a result, the walking training device 100 according to the present embodiment can flex and extend the walking assist device 120 at an appropriate timing, and can provide the trainee 900 with effective walking training.

[0078] In the present embodiment, the walking assist device 120 is attached to the right leg, but the present invention is not limited to this. For example, the walking assist device 120 may be attached to the left leg. In this case, the walking training device 100 determines that the left leg has switched from a stance state to a swing state at the timing when the load value of the left leg detected by the load distribution sensor 222 changes from a predetermined threshold value D3 or more to less than the threshold value D3 (or when the load value of the right leg changes from less than a predetermined threshold value D4 to a threshold value D4 or more), and starts flexion control for the swing state by the walking assist device 120 attached to the left leg. Alternatively, the walking assist device 120 may be attached to each of the right leg and the left leg individually.

[0079] In addition, in the present embodiment, a case has been described in which the change from the stance state to the swing state of one leg on which the walking assist device 120 is attached is detected, but it is also possible to detect the change from the stance state to the swing state of the other leg on which the walking assist device 120 is not attached. This makes it possible to determine the walking state of the trainee 900 more accurately.

[0080] Furthermore, in the present disclosure, a part or all of the processing in the walking training device 100 can be realized by causing a CPU (Central Processing Unit) to execute a computer program.

[0081] The above-mentioned program includes a set of instructions (or software code) for making the computer perform one or more functions described in the embodiment when the program is loaded into the computer. The program may be stored in a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, the computer-readable medium or the tangible storage medium includes random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technology, CD-ROM, digital versatile disc (DVD), Blu-ray® disk or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device. The program may be transmitted on a transitory computer-readable medium or a communication medium. By way of example and not limitation, the transitory computer-readable medium or the communication medium includes electrical, optical, acoustic, or other forms of propagating signals. [Explanation of symbols]

[0082] 100 Walking training device 110 Orthotics 110a Connecting hook 111 Harness wire 112 Harness tension section 120 Walking aids 121 Control Unit 122 Upper leg frame 123 Lower Leg Frame 124 Foot Frame 126 Adjustment mechanism 127 Front connecting frame 127a Connecting hook 128 Rear connecting frame 128a Connecting hook 129 Thigh Belt 130 frames 130a Handrail 131 Treadmill 133 Control Panel 134 Front Wire 135 Front tension section 136 Rear Wire 137 Rear tension section 138 Training Monitor 139 Management Monitor 140 Camera 210 Overall Control Unit 210a Gait Assessment Section 210b Training Judgment Section 210c Estimation part 210d Walking state discrimination unit 210e Bending and stretching control section 211 Treadmill Drive Unit 212 Operation reception section 213 Display control unit 214 Tension drive unit 215 Harness drive unit 216 Image Processing Unit 217 Attitude Sensor 218 Handrail Sensor 219 Communication connection interface 220 Auxiliary Control Unit 221 Joint Drive Unit 222 Load distribution sensor 223 Angle sensor (sensor part) 223a Attitude Angle Sensor 223b Knee angle sensor 229 Communication connection interface 232 Emergency stop button 900 Trainer 901 Training Staff 1311 Belt 1312 Pulley

Claims

1. A robotic leg attached to one leg of a trainee; A treadmill and a load distribution sensor attached to the treadmill for detecting a distribution of a load applied to the soles of the feet of the trainee standing on the belt of the treadmill; A camera installed so as to be able to photograph at least the hip joint portion of the one leg; a sensor unit attached to the robot leg and configured to detect at least a posture angle of a thigh and a flexion angle of a knee joint of the one leg; an estimation unit that estimates a ground contact position of a sole of the one leg to which the robot leg is attached on the belt based on a position of a hip joint of the one leg identified from the image captured by the camera and a detection result by the sensor unit; a walking state discrimination unit that determines whether the one leg has switched from a stance state to a swing state based on a change in the load received from the one leg or the other leg of the trainee during walking training, the change being identified based on an estimation result by the estimation unit, among the loads detected by the load distribution sensor; and a control unit that starts a bending control of the robot leg toward the swing leg state when the walking state determination unit determines that the one leg has switched from a stance state to a swing leg state; A walking training system equipped with

2. the estimation unit specifies a position of a hip joint part of the one leg from skeletal information of the one leg extracted from the image captured by the camera; The gait training system according to claim 1 .

3. A marker is attached to the hip joint of the one leg, the estimation unit specifies a position of a hip joint of the one leg from a position of the marker extracted from the image captured by the camera; The gait training system according to claim 1 .

4. the walking state determination unit determines that the one leg has switched from a stance state to a swing state when a load received from the one leg has changed from a first predetermined load or more to less than the first predetermined load. The gait training system according to claim 1 .

5. the walking state determination unit determines that the one leg has switched from a stance state to a swing state when a load received from the other leg changes from less than a second predetermined load to equal to or greater than the second predetermined load. The gait training system according to claim 1 .

6. A step of detecting a distribution of load applied to the soles of the feet of a trainee riding on a belt of the treadmill using a load distribution sensor attached to the treadmill; Taking an image of at least a hip joint portion of one leg to which the robot leg is attached using a camera; detecting at least a posture angle of a thigh and a flexion angle of a knee joint of the one leg using a sensor unit attached to the robot leg; estimating a contact position of the sole of the one leg to which the robot leg is attached on the belt based on a position of a hip joint of the one leg identified from the image captured by the camera and a detection result by the sensor unit; a step of determining whether the one leg has switched from a stance state to a swing state based on a change in a load received from the one leg or the other leg of the trainee during walking training, the change being determined based on an estimation result in the estimating step, among the loads detected by the load distribution sensor; when it is determined that the one leg has switched from a stance state to a swing state, starting a flexion control of the one leg by the robot leg toward the swing state; A method for controlling a walking training system comprising the steps of:

7. A process of detecting a distribution of load applied to the soles of the feet of a trainee riding on a belt of the treadmill using a load distribution sensor attached to the treadmill; A process of photographing at least a hip joint portion of one leg to which the robot leg is attached using a camera; detecting at least a posture angle of a thigh and a flexion angle of a knee joint of the one leg using a sensor unit attached to the robot leg; a process of estimating a contact position of the sole of the one leg to which the robot leg is attached on the belt based on a position of a hip joint of the one leg identified from the image captured by the camera and a detection result by the sensor unit; a process of determining whether the one leg has switched from a stance state to a swing state based on a change in a load received from the one leg or the other leg of the trainee during walking training, the change being identified based on an estimation result in the estimation process, among the loads detected by the load distribution sensor; when it is determined that the one leg has switched from a stance state to a swing state, starting a flexion control of the one leg by the robot leg toward the swing state; A control program that causes a computer to execute the above.

Images