Man-power drive vehicle control device, man-power drive vehicle control method, and computer program

Abstract

To provide a man-power drive vehicle control device, a man-power drive vehicle control method, and a computer program which optimize automatic control adapted to each rider.SOLUTION: A man-power drive vehicle control device includes a processor for reading out information from a storage part and executing processing, wherein the processor acquires input information on travel of a man-power drive vehicle, determines control data of a device mounted on the man-power drive vehicle by a predetermined control algorism, on the basis of the acquired input information, automatically controls the device by the determined control data, and changes a parameter of the predetermined control algorism, when probability output from an operation probability output model of outputting such probability that automatic control of the device is subjected to an intervening operation by a rider is equal to or more than a predetermined value using the operation probability output model, on the basis of the input information is deterministic, and it is defined that the intervening operation is performed.SELECTED DRAWING: Figure 6

Description

Technical Field

[0001] The present invention relates to a human-powered vehicle control device, a human-powered vehicle control method, and a computer program.

Background Art

[0002] The electrification of human-powered vehicles has advanced, and automatic control of mounted devices including a transmission, a braking device, and an assist device has been realized. Technologies have also been proposed to update and optimize the criteria used for automatic control of mounted devices based on the rider's intervention operation (Patent Document 1, etc.).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] It is desirable to more appropriately optimize the criteria for automatic control based on the rider's intervention operation while reducing the influence of the rider's misoperation.

[0005] An object of the present invention is to provide a human-powered vehicle control device, a human-powered vehicle control method, and a computer program that more optimally perform automatic control tailored to each rider.

Means for Solving the Problems

[0006] (1) The human-powered vehicle control device according to the first aspect of the present invention includes a processor that reads information from a storage unit and executes processing. The processor acquires input information related to the running of a human-powered vehicle, determines control data for a device mounted on the human-powered vehicle by a predetermined control algorithm based on the acquired input information, automatically controls the device with the determined control data, and uses an operation probability output model that outputs the probability of a rider intervening in the automatic control of the device based on the input information. When it is certain that the probability output from the operation probability output model is equal to or greater than a predetermined value and it is certain that the intervening operation has been performed, the parameters of the predetermined control algorithm are changed.

[0007] According to the human-powered vehicle control device of the first aspect, the automatic control is more appropriately optimized to match the rider's operation intention for the human-powered vehicle according to the situation.

[0008] (2) The human-powered vehicle control device according to the second aspect of the present invention is the human-powered vehicle control device of the first aspect, wherein the processor determines that it is certain that the probability output from the operation probability output model is equal to or greater than a predetermined value when the probability is a peak in time series and equal to or greater than a predetermined value.

[0009] According to the human-powered vehicle control device of the second aspect, the automatic control is more appropriately optimized to match the rider's operation intention for the human-powered vehicle according to the situation.

[0010] (3) The human-powered vehicle control device according to the third aspect of the present invention is the human-powered vehicle control device of the first aspect, wherein the processor determines that the intervening operation has been performed when an intervening operation is performed on the device by the rider and no other intervening operation is performed on the device within a predetermined time from the intervening operation.

[0011] According to the human-powered vehicle control device of the third aspect described above, the automatic control is more appropriately optimized so as to conform to the rider's operation intention for the human-powered vehicle according to the situation.

[0012] (4) The human-powered vehicle control device according to the fourth aspect of the present invention is the human-powered vehicle control device of the first aspect, and includes a learning unit that uses the input information as an input and learns the operation probability output model with the presence or absence of the rider's intervention operation on the device after a predetermined time when the input information is acquired as an output label.

[0013] According to the human-powered vehicle control device of the fourth aspect described above, the operation probability output model can be learned by reflecting the rider's habits, preferences, etc. based on the actual operations of the rider, and the automatic control can be more appropriately optimized.

[0014] (5) The human-powered vehicle control device according to the fifth aspect of the present invention is the human-powered vehicle control device of the first aspect, and includes a learning unit that uses the input information as an input and learns the operation probability output model with a value corresponding to the rider's discomfort after a predetermined time when the input information is acquired as an output label.

[0015] According to the human-powered vehicle control device of the fifth aspect described above, learning can be performed considering the case where the rider feels discomfort with respect to the automatic control even without an actual operation by the rider, and the automatic control can be more appropriately optimized.

[0016] (6) The human-powered vehicle control device according to the sixth aspect of the present invention is the human-powered vehicle control device of the first aspect, wherein the device is a transmission of the human-powered vehicle, the input information includes the crank cadence of the drive mechanism of the human-powered vehicle, and the processor changes the reference cadence for comparison with the cadence for determining the gear ratio in the transmission as the parameter by raising or lowering it.

[0017] According to the human-powered vehicle control device of the sixth aspect described above, the automatic control of the transmission is more appropriately optimized so as to conform to the reference cadence that the rider feels like maintaining individually.

[0018] (7) The human-powered vehicle control device according to the seventh aspect of the present invention is the human-powered vehicle control device of the sixth aspect, wherein the input information includes the traveling speed of the human-powered vehicle, the reference cadence is set for each section of the traveling speed, and the processor changes the reference cadence in the section including the traveling speed of the input information while maintaining the difference from the reference cadence in the adjacent section within a predetermined range.

[0019] According to the human-powered vehicle control device of the seventh aspect, the automatic control of the transmission is appropriately optimized smoothly so as to be the reference cadence that the rider feels like maintaining for each speed.

[0020] (8) The human-powered vehicle control device according to the eighth aspect of the present invention is the human-powered vehicle control device of any one of the first to fifth aspects, wherein the device is a transmission of the human-powered vehicle, the input information includes the torque of the crank of the drive mechanism of the human-powered vehicle, and the processor changes the reference torque for comparison with the torque for determining the gear ratio in the transmission as the parameter by increasing or decreasing it.

[0021] According to the human-powered vehicle control device of the eighth aspect, the automatic control of the transmission is more appropriately optimized so as to match the reference torque that the rider feels like maintaining individually.

[0022] (9) The human-powered vehicle control device according to the ninth aspect of the present invention is the human-powered vehicle control device of any one of the first to fifth aspects, wherein the device is an assist device of the human-powered vehicle, the input information includes the cadence of the crank of the drive mechanism of the human-powered vehicle, and the processor changes the reference cadence for comparison with the cadence for determining the output in the assist device as the parameter by increasing or decreasing it.

[0023] According to the human - powered vehicle control device of the ninth aspect, the automatic control of the assist device is more appropriately optimized so as to match the reference cadence that the rider feels like maintaining individually.

[0024] (10) The human - powered vehicle control device according to the tenth aspect of the present invention is the human - powered vehicle control device of the ninth aspect, wherein the input information includes the traveling speed of the human - powered vehicle, the reference cadence is set for each section of the traveling speed, and the processor changes the reference cadence in the section including the traveling speed of the input information while maintaining the difference from the reference cadence in the adjacent section within a predetermined range.

[0025] According to the human - powered vehicle control device of the tenth aspect, the automatic control of the assist device is appropriately optimized smoothly so as to be the reference cadence that the rider feels like maintaining for each speed.

[0026] (11) The human - powered vehicle control device according to the eleventh aspect of the present invention is the human - powered vehicle control device of any one of the first to fifth aspects, wherein the device is an assist device of the human - powered vehicle, the input information includes the torque of the crank of the drive mechanism of the human - powered vehicle, and the processor changes the reference torque for comparing with the torque for determining the output in the assist device as the parameter by increasing or decreasing it.

[0027] According to the human - powered vehicle control device of the eleventh aspect, the automatic control of the assist device is more appropriately optimized so as to match the reference torque that the rider feels like maintaining individually.

[0028] (12) The human-powered vehicle control method according to the 12th aspect of the present invention is such that a computer mounted on a human-powered vehicle, which reads information from a storage unit and executes processing, acquires input information regarding the running of the human-powered vehicle, determines control data for a device mounted on the human-powered vehicle by a predetermined control algorithm based on the acquired input information, automatically controls the device with the determined control data, and uses an operation probability output model that outputs the probability of a rider intervening in the automatic control of the device based on the input information. When it is certain that the probability output from the operation probability output model is equal to or greater than a predetermined value and it is certain that the intervening operation has been performed, the parameters of the predetermined control algorithm are changed.

[0029] According to the human-powered vehicle control method of the 12th aspect described above, the automatic control is more appropriately optimized so as to conform to the rider's operation intention for the human-powered vehicle according to the situation.

[0030] (13) The computer program according to the 13th aspect of the present invention causes a computer mounted on a human-powered vehicle, which reads information from a storage unit and executes processing, to acquire input information regarding the running of the human-powered vehicle, determine control data for a device mounted on the human-powered vehicle by a predetermined control algorithm based on the acquired input information, automatically control the device with the determined control data, and use an operation probability output model that outputs the probability of a rider intervening in the automatic control of the device based on the input information. When it is certain that the probability output from the operation probability output model is equal to or greater than a predetermined value and it is certain that the intervening operation has been performed, the computer program causes the computer to execute processing for changing the parameters of the predetermined control algorithm.

[0031] According to the computer program of the 13th aspect described above, the automatic control is more appropriately optimized so as to conform to the rider's operation intention for the human-powered vehicle according to the situation.

Advantages of the Invention

[0032] According to the present disclosure, it becomes possible to more appropriately optimize the automatic control in a human-powered vehicle.

Brief Description of the Drawings

[0033]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Mode for Carrying Out the Invention

[0034] The following descriptions of the embodiments are examples of forms that a human-powered vehicle control device, a computer program, a human-powered vehicle control method, a human-powered vehicle control data setting method, and a human-powered vehicle control system according to the present invention can take, and are not intended to limit the forms. The human-powered vehicle control device, computer program, human-powered vehicle control method, human-powered vehicle control data setting method, and human-powered vehicle control system according to the present invention can take forms different from the embodiments, such as modified examples of each embodiment and forms in which at least two non-contradictory modified examples are combined.

[0035] In the following descriptions of the embodiments, words representing directions such as front, rear, forward, backward, left, right, side, up, and down are used based on the directions in the state where the rider is seated on the saddle of the human-powered vehicle.

[0036] In the following embodiments, the control device for a human-powered vehicle according to the present invention will be described by referring to it as the control device.

[0037] (First Embodiment) FIG. 1 is a side view of a human-powered vehicle 1 to which a control device 100 in the first embodiment is applied. The human-powered vehicle 1 is a vehicle that uses at least partially human power for the driving power. Vehicles that use only an internal combustion engine or an electric motor as the driving power are excluded from the human-powered vehicle 1 of the present embodiment. The human-powered vehicle 1 is, for example, a bicycle including a mountain bike, a road bike, a cross bike, a city cycle, an electric assist bike (e-bike), etc.

[0038] The human - powered vehicle 1 includes a vehicle body 10, a handlebar 12, a front wheel 14, a rear wheel 16, and a saddle 18. The human - powered vehicle 1 further includes a drive mechanism 20, a device 30, an operating device 40, a battery 50, and a sensor 60.

[0039] The vehicle body 10 includes a frame 10A and a front fork 10B. The front wheel 14 is rotatably supported by the front fork 10B. The rear wheel 16 is rotatably supported by the frame 10A. The handlebar 12 is supported by the frame 10A so as to be able to change the traveling direction of the front wheel 14.

[0040] The drive mechanism 20 includes a crank 21, a first sprocket assembly 23, a second sprocket assembly 25, a chain 27, and a pair of pedals 29.

[0041] The crank 21 includes a crankshaft 21A, a right crank 21B, and a left crank 21C. The crankshaft 21A is rotatably supported by the frame 10A. The right crank 21B and the left crank 21C are respectively connected to the crankshaft 21A. One of the pair of pedals 29 is rotatably supported by the right crank 21B. The other of the pair of pedals 29 is rotatably supported by the left crank 21C.

[0042] The first sprocket assembly 23 is integrally and rotatably connected to the crankshaft 21A. The first sprocket assembly 23 includes one or more sprockets 23A. In one example, the first sprocket assembly 23 includes a plurality of sprockets 23A with different outer diameters.

[0043] The second sprocket assembly 25 is rotatably supported by the rear hub of the rear wheel 16. The second sprocket assembly 25 includes one or more sprockets 25A. In one example, the second sprocket assembly 25 includes a plurality of sprockets 25A with different outer diameters.

[0044] The chain 27 is wound around any one of the sprockets 23A of the first sprocket assembly 23 and any one of the sprockets 25A of the second sprocket assembly 25. When the crank 21 rotates forward by the manual driving force applied to the pedal 29, the sprocket 23A rotates forward together with the crank 21, and the rotation of the sprocket 23A is transmitted to the sprocket 25A of the second sprocket assembly 25 via the chain 27. The rotation of the sprocket 25A rotates the rear wheel 16. Instead of the chain 27, a belt or a shaft may be used.

[0045] In one example, the control device 100 is mounted on the battery 50, the cycle computer, the drive unit, etc. of the human-powered vehicle 1. The control device 100 is connected to the device 30, the operating device 40, and the battery 50. The connection form and details of the control device 100 will be described later.

[0046] The human-powered vehicle 1 includes a device 30 that operates by the electric power supplied from the battery 50 and whose operation is controlled by the control device 100. The device 30 includes a transmission 31 and an assist device 33. The device 30 may include a suspension, a seat post, and a braking device. Basically, the device 30 operates under the control of the control device 100 according to the operation in the operating device 40. The control target of the control device 100 for the device 30 is at least one of the transmission 31 and the assist device 33.

[0047] The speed change device 31 changes the ratio of the rotational speed of the rear wheel 16 to the rotational speed of the crank 21, that is, the speed ratio of the human - powered vehicle 1. The speed ratio is represented by the ratio of the output rotational speed output by the speed change device 31 to the input rotational speed input to the speed change device 31. When expressing the speed ratio by an equation, "speed ratio = output rotational speed / input rotational speed". In the first example, the speed change device 31 is an external speed change mechanism (rear derailleur) that changes the connection state between the second sprocket assembly 25 and the chain 27. In the second example, the speed change device 31 is an external speed change mechanism (front derailleur) that changes the connection state between the first sprocket assembly 23 and the chain 27. In the third example, it is an internal speed change mechanism provided on the hub of the rear wheel 16. The speed change device 31 may be a continuously variable transmission.

[0048] The assist device 33 is a device that assists the human - driving force of the human - powered vehicle 1. In one example, the assist device 33 is arranged within the drive unit. In one example, the assist device 33 is arranged in the battery 50. The assist device 33 includes a motor. In one example, the assist device 33 is interposed between the crankshaft 21A and the frame 10A and transmits torque to the first sprocket assembly 23 to assist the human - driving force to the human - powered vehicle 1. In one example, the assist device 33 drives the chain 27 that transmits the driving force to the rear wheel 16 of the human - powered vehicle 1 to assist the human - driving force to the human - powered vehicle 1.

[0049] The operation device 40 is provided on the handlebar 12. The operation device 40 includes an operation part 40A that is operated by the rider. The operation part 40A includes one or more buttons. The one or more buttons are provided separately on the left and right handlebars. The operation part 40A includes a brake lever. The operation part 40A can be operated by tilting the brake levers provided on the left and right handlebars forward and backward. As the operation part 40A, the client device 7 possessed by the rider may be used.

[0050] The operating device 40 includes a shift instruction device 40B. In one example, the shift instruction device 40B is a plurality of buttons included in the operation unit 40A. In another example, the shift instruction device 40B is a device attached to the brake lever. Each time the rider performs an operation such as tilting the shift instruction device 40B with respect to the brake lever or pressing any one of the plurality of buttons, it is possible to switch the ON / OFF of the automatic control for the transmission device 31 and at least one of the manual operations. The manual operation includes at least one of an upshift and a downshift of the gear ratio. The shift instruction device 40B, for example, receives an operation to increase and an operation to decrease the gear ratio in the first sprocket assembly 23 on the right handlebar among the left and right handlebars. The shift instruction device 40B receives an operation to increase and an operation to decrease the gear ratio in the second sprocket assembly 25 on the left handlebar. The shift instruction device 40B includes a button for switching the ON / OFF of the synchro setting that interlocks the gear ratio in the first sprocket assembly 23 and the gear ratio in the second sprocket assembly 25.

[0051] The operating device 40 includes an assist instruction device 40C. The assist instruction device 40C is, for example, a button included in the operation unit 40A. By pressing the button corresponding to the assist instruction device 40C, it is possible to set any one of a plurality of levels (high / mid / low) of the assist mode.

[0052] The operating device 40 is communicatively connected to the control device 100 so that it can transmit a signal corresponding to an operation to the control device 100. The operating device 40 may be communicatively connected so that it can directly output a signal corresponding to an operation to the transmission device 31 and the assist device 33. In the first example, the operating device 40 communicates with the control device 100 via a communication line or a wire capable of PLC (Power Line Communication). The operating device 40 may communicate with the transmission device 31, the assist device 33, and the control device 100 via a communication line or a wire capable of PLC. In the second example, the operating device 40 communicates with the control device 100 by wireless communication. The operating device 40 may communicate with the transmission device 31, the assist device 33, and the control device 100 by wireless communication.

[0053] The operating device 40 may include a notification unit that notifies an operating state. The operating device 40 may notify the rider of the control states for the transmission device 31 and the assist device 33 by means of a lamp, a display, a speaker, or the like.

[0054] The battery 50 includes a battery main body 51 and a battery holder 53. The battery main body 51 is a storage battery including one or more battery cells. The battery holder 53 is fixed to the frame 10A of the human-powered vehicle 1. The battery main body 51 is detachable from the battery holder 53. The battery 50 is electrically connected to the device 30, the operating device 40, and the control device 100, and supplies power as needed. The battery 50 preferably includes a control unit for communicating with the control device 100. The control unit preferably includes a processor using a CPU.

[0055] The human-powered vehicle 1 is provided with sensors 60 at various locations for acquiring information related to riding including the state of the rider and the driving environment. The sensors 60 include a speed sensor 61, an acceleration sensor 62, a torque sensor 63, a cadence sensor 64, a gyro sensor 65, a seating sensor 66, and a camera 67.

[0056] The speed sensor 61 is provided on the front wheel 14, for example, and transmits a signal corresponding to the number of rotations of the front wheel 14 per unit time to the control device 100. Based on the output of the speed sensor 61, the control device 100 can calculate the traveling speed and the moving distance of the human-powered vehicle 1.

[0057] The acceleration sensor 62 is fixed to the frame 10A, for example. The acceleration sensor 62 is a sensor that outputs the vibration of the human-powered vehicle 1 in three axes (front-rear direction, left-right direction, up-down direction) with reference to the frame 10A, and is provided for detecting the movement and vibration of the human-powered vehicle 1. The acceleration sensor 62 transmits a signal corresponding to the magnitude of the movement and vibration to the control device 100.

[0058] The torque sensor 63 is provided to measure the torque applied to the right crank 21B and the left crank 21C, for example. The torque sensor 63 transmits a signal corresponding to the torque measured in at least one of the right crank 21B and the left crank 21C to the control device 100.

[0059] The cadence sensor 64 is provided to measure the cadence of either the right crank 21B or the left crank 21C, for example. The cadence sensor 64 transmits a signal corresponding to the measured cadence to the control device 100.

[0060] The gyro sensor 65 is fixed to the frame 10A, for example. The gyro sensor 65 is provided for detecting the yaw, roll, and pitch rotations of the human-powered vehicle 1. The gyro sensor 65 transmits a signal corresponding to the amount of rotation of each of the three axes to the control device 100. Yaw is the rotation around the vertical axis. Roll is the rotation around the front-rear axis. Pitch is the rotation around the left-right axis.

[0061] The seating sensor 66 is provided on the inner surface of the saddle 18 to measure whether a rider is seated on the saddle 18. The seating sensor 66 uses a piezoelectric sensor, for example, and transmits a signal corresponding to the weight applied to the saddle 18 to the control device 100.

[0062] The camera 67 is provided facing forward on the front fork 10B. In the first example, it is provided facing forward on the front fork 10B together with a light. In the second example, it is provided on the handlebar 12. The camera 67 outputs an image corresponding to the rider's field of view using a camera module. The camera 67 outputs a video signal of an object existing in the traveling direction.

[0063] The sensor 60 does not necessarily include all of the speed sensor 61, the acceleration sensor 62, the torque sensor 63, the cadence sensor 64, the gyro sensor 65, the seating sensor 66, and the camera 67.

[0064] FIG. 2 is a block diagram for explaining the configuration of the control device 100. The control device 100 includes a processing unit 110 and a storage unit 112.

[0065] The processing unit 110 is a processor using a CPU. The processing unit 110 uses memories such as a built-in ROM (Read Only Memory) and RAM (Random Access Memory). The processing unit 110 is a processor that reads information from the memory and the storage unit 112 and executes processing. The processing unit 110 separates functions into a device control unit 114 and a parameter change unit 116 and executes processing.

[0066] The device control unit 114 executes automatic control processing. The device control unit 114 acquires input information regarding the running of the human-powered vehicle 1 from the sensor 60. The device control unit 114 determines control data for the device 30 mounted on the human-powered vehicle 1 by a predetermined control algorithm based on the acquired input information according to the device control program P14. The device control unit 114 controls the operation of the control target mounted on the human-powered vehicle 1 based on the determined control data according to the device control program P14.

[0067] Based on the input information, the parameter change unit 116 executes a process of changing parameters for determining control data in the device control unit 114 using the operation probability output model M1 that outputs the probability of the rider intervening in the automatic control of the device 30. The parameter change unit 116 executes a process of changing the parameters when it is certain that the probability output from the operation probability output model M1 is equal to or greater than a predetermined value and it is certain that an intervention operation has been performed.

[0068] The storage unit 112 includes a non-volatile memory such as a flash memory, for example. The storage unit 112 stores the device control program P14 and the setting update program P16. The device control program P14 and the setting update program P16 may each be a copy that the processing unit 110 reads from the device control program P94 and the setting update program P96 stored in the non-temporary storage medium 900 and stores in the storage unit 112.

[0069] The storage unit 112 stores the operation probability output model M1. Details of the operation probability output model M1 will be described later. The operation probability output model M1 may also be a copy that the processing unit 110 reads from the operation probability output model M9 stored in the non-temporary storage medium 900 and stores in the storage unit 112.

[0070] The storage unit 112 stores, in a rewritable manner, the parameters used for automatic control based on the device control program P14. The content of the parameters will be described later.

[0071] The processing unit 110 communicates with the control target. The processing unit 110 itself may have a communication unit (not shown) for the control target, or the processing unit 110 may be connected to a communication unit for the control target provided inside the control device 100. The processing unit 110 preferably has a connection unit for connecting to the control target or the communication unit.

[0072] The processing unit 110 preferably communicates with the control target by at least one of PLC and CAN communication. The communication that the processing unit 110 performs with the control target is not limited to wired communication, and may also be wireless communication such as ANT (registered trademark), ANT+ (registered trademark), Bluetooth (registered trademark), WiFi (registered trademark), ZigBee (registered trademark), etc.

[0073] The processing unit 110 is connected to the sensor 60 via a signal line. The processing unit 110 acquires input information regarding the running of the human-powered vehicle 1 from the signal output by the sensor 60 via the signal line.

[0074] The processing unit 110 can communicate with the rider's client device 7 described later via a wireless communication device 118 having an antenna. The wireless communication device 118 may be built into the control device 100. The wireless communication device 118 is a device that realizes communication via the so-called Internet. The wireless communication device 118 may also be a device for wireless communication such as ANT (registered trademark), ANT+ (registered trademark), Bluetooth (registered trademark), WiFi (registered trademark), ZigBee (registered trademark), LTE (Long Term Evolution), etc. The wireless communication device 118 may conform to a communication network such as 3G, 4G, 5G, LTE (Long Term Evolution), WAN (Wide Area Network), LAN (Local Area Network), Internet line, dedicated line, satellite line, etc.

[0075] The control content by the control device 100 configured as described above will be described. In the human-powered vehicle 1, the rider can switch ON / OFF the automatic control for the device 30 provided in the operation device 40, and can also perform a manual operation on the device 30 (intervention operation when the automatic control is ON) in either case of ON / OFF of the automatic control.

[0076] When the automatic control is ON, the processing unit 110 of the control device 100 determines control data by the function of the device control unit 114, and supplies the control data to the device 30 to control the device 30. The processing unit 110 determines the control data based on a comparison between the input information input by the sensor 60 and the parameters stored in the storage unit 112 according to the device control program P14. Hereinafter, the device 30 to be controlled will be described as the transmission 31.

[0077] The processing unit 110 acquires the cadence of the crank 21 of the drive mechanism 20 of the human-powered vehicle 1 from the cadence sensor 64, and compares the acquired cadence with a reference cadence for determining the gear ratio in the transmission 31. The processing unit 110, as the device control unit 114, determines the gear ratio according to whether the acquired cadence is in a certain range with respect to the reference cadence, and controls the transmission 31. Specifically, in the first embodiment, the device control unit 114 determines the gear ratio so that the cadence during traveling changes in the vicinity of the reference cadence, and controls the transmission 31 (FIG. 3).

[0078] FIG. 3 is a schematic diagram of a control algorithm for the transmission 31 by the device control unit 114. In the schematic diagram shown in FIG. 3, a control algorithm will be described by taking as an example a control algorithm that controls the cadence in the crank 21 during traveling to transition near a reference cadence set between an upper limit value and a lower limit value. FIG. 3 shows a reference for changing the gear ratio with respect to the cadence obtained from the cadence sensor 64. The vertical direction indicates the magnitude of the cadence. The higher the upper side of FIG. 3, the larger the cadence. The device control unit 114 compares the cadence with the upper and lower limit values based on the reference cadence and determines the gear ratio. For example, when the cadence obtained from the cadence sensor 64 reaches an upper limit value greater than the reference cadence, the device control unit 114 determines to change the gear ratio to a larger gear ratio side OW (Outward). Conversely, when the cadence obtained from the cadence sensor 64 reaches a lower limit value lower than the reference cadence, the device control unit 114 determines to change the gear ratio to a smaller gear ratio side IW (Inward). The device control unit 114 controls so that the cadence transitions near the reference cadence even after the change of the gear ratio.

[0079] The storage unit 112 of the control device 100 stores the above-described reference cadence, upper limit value, and lower limit value as parameters so that they can be changed. The parameter change unit 116 changes these parameters as necessary. The parameter change unit 116 learns an operation probability output model M1 that outputs a probability indicating the possibility of an operation as to whether the rider feels like manual driving rather than automatic control during the running of the human-powered vehicle 1. When the learning of the operation probability output model M1 is completed, the parameter change unit 116 inputs input information regarding the running to the operation probability output model M1 during running. When the probability output from the operation probability output model M1 is equal to or greater than a predetermined value, the parameter change unit 116 determines that it is necessary to change the parameters used by the device control unit 114. The parameter change unit 116 changes the reference cadence.

[0080] FIG. 4 is a schematic diagram of the operation probability output model M1. The operation probability output model M1 is a learning model learned by supervised deep learning using a neural network (hereinafter referred to as NN: Neural Network). The operation probability output model M1 may be a model learned by a Recurrent Neural Network. The operation probability output model M1 is learned by the function as the learning unit of the processing unit 110 so as to output "the probability that the rider will intervene in a few seconds" when the input information regarding the running of the human-powered vehicle 1 acquired by the sensor 60 is input.

[0081] The operation probability output model M1 includes an input layer M11 for inputting input information, an output layer M12 for outputting the probability that the rider will intervene, and an intermediate layer M13 including a node group composed of one or more layers. The intermediate layer M13 connected to the output layer M12 is a connection layer that aggregates a large number of nodes to the number of nodes in the output layer M12. The number of nodes in the output layer M12 is one. Each node in the intermediate layer M13 has a parameter including at least one of a weight and a bias in relation to the nodes in the previous layer. The operation probability output model M1 is learned by teacher data including input information that can be acquired from the sensor 60 such as cadence, torque, running speed, acceleration, inclination, etc. during the running of the human-powered vehicle 1, and the presence or absence of the rider's intervention operation on the transmission 31 at a predetermined time after the input information is acquired as an output label (0: none, 1: yes). The operation probability output model M1 backpropagates the error between the numerical value output from the output layer M12 when the input information in the teacher data is input to the input layer M11 and the label associated with the input information in the teacher data to update the parameters in the nodes of the intermediate layer M13 for learning.

[0082] The operation probability output model M1 not only inputs the input information that can be obtained from the sensors 60 such as cadence, torque, traveling speed, acceleration, inclination, etc. directly into the input layer M11 at each time point, but also may input the amount of change in the recent several seconds (for example, 2 seconds). The operation probability output model M1 may be trained to output the operation probability while also being influenced by the input information input in the past by the RNN.

[0083] The operation probability output model M1 may be trained with a value corresponding to the discomfort level of the rider after a predetermined time when the input information is acquired as the label of the output. FIG. 5 is a schematic diagram showing another learning method of the operation probability output model M1. As shown in FIG. 5, similar to the operation probability output model M1 shown in FIG. 4, when the operation probability output model M1 inputs the input information regarding the traveling of the human-powered vehicle 1 acquired by the sensor 60, it is trained to output the "probability that the rider will intervene in the operation after several seconds". The operation probability output model M1 in another example shown in FIG. 5 is trained with the input information that can be obtained from the sensors 60 such as cadence, torque, traveling speed, acceleration, inclination, etc. and the teacher data including a value (0 to 1) corresponding to the discomfort level of the rider after a predetermined time when the input information is acquired as the label. The operation probability output model M1 shown in FIG. 5 calculates the error between the numerical value (0 to 1) output from the output layer M12 when the input information in the teacher data is input into the input layer M11 and the label (0 to 1) of the discomfort level corresponding to the input information in the teacher data, and backpropagates the error to the intermediate layer M13 to update the parameters at the nodes of the intermediate layer M13 for learning.

[0084] The discomfort level of the rider is derived based on at least one of the magnitude of the cadence of the human - powered vehicle 1, the magnitude of the torque, the seating state of the rider, and the biometric information of the rider. The processing unit 110 that functions as a learning unit derives a higher discomfort level as the cadence increases, derives a higher discomfort level as the torque increases, and derives a higher discomfort level when the rider is not seated. This is because when the rider is not seated, i.e., in a so - called standing - pedaling state, a considerable amount of force must be exerted to continue pedaling the human - powered vehicle 1. The processing unit 110 derives a higher discomfort level when the rider is not seated and at least one of the running speed, cadence, and torque is less than a predetermined threshold value. This is because when the rider is not seated and the running speed or the input to the pedal is lower than the predetermined threshold value, there is a high possibility that the rider has gotten off the human - powered vehicle 1. The processing unit 110 that functions as a learning unit may derive a higher discomfort level as the pulse is faster and the blood flow is greater. The processing unit 110 may derive the discomfort level by a function that calculates the discomfort level using at least one of cadence, torque, presence or absence of seating, and biometric information as variables. The processing unit 110 may derive a higher discomfort level as the stability of the human - powered vehicle 1 is lower. The processing unit 110 may derive that the stability of the human - powered vehicle 1 becomes lower as the inclination of the human - powered vehicle 1 calculated by at least one of the acceleration sensor 62 and the gyro sensor 65 is greater.

[0085] By the learning method shown in FIG. 5, even when the rider feels uncomfortable with the automatic control by the device control unit 114 or does not actually perform the operation, the height of the discomfort level can be set as a label corresponding to the high possibility of performing the intervention operation, and the operation probability output model M1 can be learned.

[0086] Since the operation probability output model M1 shown in either FIG. 4 or FIG. 5 needs to be learned for each rider, it is stored in the storage unit 112 in a state where it has been learned to a certain extent before the control device 100 is shipped. The parameter change unit 116, as a learning unit of the control device 100, proceeds with the learning of the operation probability output model M1 for each rider after the human - powered vehicle 1 is shipped and purchased.

[0087] By using the learned operation probability output model M1, the parameter change unit 116 can predict whether an intervention operation will be performed by the rider several seconds later based on the input information corresponding to the driving state of the human-powered vehicle 1. The parameter change unit 116 predicts, using the operation probability output model M1, whether the control by the device control unit 114 is likely to be changed by the rider, and in addition to this prediction content, based on the presence or absence of the rider's intervention operation, the reference cadence for determining the gear ratio in the transmission 31 is increased or decreased and changed.

[0088] FIG. 6 is a flowchart showing an example of the parameter change processing procedure by the parameter change unit 116. After determining that the learning of the operation probability output model M1 is completed, the parameter change unit 116 executes the following processing.

[0089] The parameter change unit 116 acquires input information from the sensor 60 (step S101), and inputs the acquired input information into the learned operation probability output model M1 (step S103). The parameter change unit 116 acquires the operation probability obtained from the operation probability output model M1 and stores it in time series (step S105).

[0090] The parameter change unit 116 determines whether the operation probability obtained from the operation probability output model M1 stored in step S105 is definitely equal to or greater than a predetermined value, and whether an intervention operation has been determined by the shift instruction device 40B (step S107).

[0091] In step S101, the parameter change unit 116 continues to buffer in the RAM the data corresponding to a predetermined period (for example, 1 second, etc.) from the latest for the input information such as cadence, torque, traveling speed, acceleration, inclination, etc. that can be acquired from the sensor 60. During this period, the parameter change unit 116 may determine whether it is certain that an intervention operation has been performed in step S107.

[0092] When it is certain that the operation probability obtained from the operation probability output model M1 is equal to or greater than a predetermined value and it is determined that an intervention operation has been confirmed by the shift instruction device 40B (S107: YES), the parameter change unit 116 determines whether the cadence acquired from the cadence sensor 64 is equal to or greater than the reference cadence (step S109).

[0093] In step S109, when it is determined that the cadence is equal to or greater than the reference cadence (S109: YES), since the rider intends to change the gear ratio while the cadence is increasing, in order to facilitate the control of increasing the gear ratio (heavy control) at that cadence, the parameter change unit 116 lowers the reference cadence (step S111). The parameter change unit 116 ends the parameter change process.

[0094] In step S109, when it is determined that the cadence is less than the reference cadence (S109: NO), since the rider intends to change the gear ratio while the cadence is decreasing, in order to facilitate the control of decreasing the gear ratio (light control) at that cadence, the parameter change unit 116 raises the reference cadence (step S113). The parameter change unit 116 ends the parameter change process.

[0095] In step S107, when it is not certain that the operation probability is equal to or greater than a predetermined value or when the intervention operation by the shift instruction device 40B is not confirmed (S107: NO), the parameter change unit 116 ends the process without doing anything.

[0096] The determination process of whether it is certain that the operation probability obtained from the operation probability output model M1 in step S107 is equal to or greater than a predetermined value is executed, for example, by the parameter change unit 116 determining whether the probability output from the operation probability output model M1 is a peak in time series and is equal to or greater than the predetermined value. For example, when the parameter change unit 116 determines that the operation probability stored in time series in step S1005 is the highest within a predetermined period such as 3 to 5 seconds and is, for example, 40% or more, it determines that it is certain that the operation probability is equal to or greater than the predetermined value.

[0097] The determination process of whether an intervention operation has been determined by the shift instruction device 40B in step S107 is executed by the parameter change unit 116 determining whether an intervention operation has been performed on the transmission 31 by the rider via the shift instruction device 40B and whether a different intervention operation (reverse intervention operation) has been performed on the shift instruction device 40B within a predetermined time from the intervention operation. For example, when an intervention operation is performed on the shift instruction device 40B after the input information is acquired in step S101 and it is determined that no reverse intervention operation has been performed within 1 second, the parameter change unit 116 can determine that the intervention operation has been determined.

[0098] FIG. 7 is a flowchart showing an example of the determination process of operation determination. The processing procedure shown in FIG. 7 corresponds to the details of the processing procedure of step S107 among the processing procedures shown in FIG. 6.

[0099] The parameter change unit 116 determines whether there is an intervention operation on the shift instruction device 40B within a predetermined time (for example, 1 to 3 seconds) after acquiring the input information in step S101 (step S701).

[0100] When it is determined that there is an intervention operation (S701: YES), the parameter change unit 116 determines whether the operation probability obtained from the operation probability output model M1 within the predetermined time after acquiring the input information is the highest among the operation probabilities stored in time series and whether it is a peak (step S703).

[0101] If it is determined that the operation probability is the highest among the operation probabilities stored in time series (S703: YES), the parameter change unit 116 determines whether the operation probability is equal to or greater than a predetermined value (for example, 40%) (step S705).

[0102] If it is determined in step S705 that the operation probability is equal to or greater than the predetermined value (S705: YES), the parameter change unit 116 determines whether there is a reverse intervention operation within, for example, 1 to 3 seconds after the intervention operation determined in step S701 (step S707).

[0103] If it is determined that there is no reverse intervention operation (S707: NO), the parameter change unit 116 increments the number of determinations by 1 (step S709). The parameter change unit 116 determines whether the number of determinations is equal to or greater than a predetermined number (for example, 2) (step S711).

[0104] If it is determined in step S711 that the number of determinations is equal to or greater than the predetermined number (S711: YES), the parameter change unit 116 determines that the operation probability obtained from the operation probability output model M1 is definitely equal to or greater than the predetermined value, and that an intervention operation has been determined by the shift instruction device 40B (step S713), and ends the determination process.

[0105] If it is determined in step S711 that the number of determinations is less than the predetermined number (S711: NO), the parameter change unit 116 ends the determination process without doing anything.

[0106] If it is determined in step S707 that there is a reverse intervention operation (S707: YES), the parameter change unit 116 resets the number of determinations to zero (step S715), and determines that the operation probability obtained from the operation probability output model M1 is not definitely equal to or greater than the predetermined value, or that an intervention operation has not been determined by the shift instruction device 40B (step S717), and ends the determination process.

[0107] If it is determined in step S705 that the operation probability is less than a predetermined value (S705: NO), the parameter change unit 116 ends the determination process without doing anything. In this case, the parameter change unit 116 may proceed with the process to step S715.

[0108] If it is determined in step S703 that the operation probability is not the highest among the operation probabilities stored in time series (S703: NO), the parameter change unit 116 ends the determination process without doing anything. In this case, the parameter change unit 116 may proceed with the process to step S715.

[0109] If it is determined in step S701 that there is no intervention operation (S701: NO), the parameter change unit 116 ends the determination process without doing anything. In this case, the parameter change unit 116 may proceed with the process to step S715.

[0110] By the processes shown in FIGS. 6 and 7, for example, when the parameter change unit 116 sets the reference cadence to 60 rpm (Revolutions Per Minute), the upper limit value to 70 rpm (= reference cadence + 10), and the lower limit value to 50 rpm (= reference cadence - 10), in step S111, the reference cadence is decreased by 1 rpm, and in step S113, the reference cadence is increased by 1 rpm. Instead of decreasing the reference cadence in step S111, the parameter change unit 116 may decrease at least one of the upper limit value and the lower limit value. Instead of increasing the reference cadence in step S113, the parameter change unit 116 may increase at least one of the upper limit value and the lower limit value.

[0111] In this way, the reference cadence is adjusted so as to surely match the rider's operation intention for the human - powered vehicle 1 according to the situation, and the automatic control by the device control unit 114 is more appropriately optimized.

[0112] (Second Embodiment) In the second embodiment, the reference cadence is set and stored for each section of the traveling speed, and when increasing and decreasing the reference cadence for determining the gear ratio, control is performed so as to balance with the reference cadence in other sections of the traveling speed.

[0113] The configuration of the human - powered vehicle 1 and the configuration of the control device 100 in the second embodiment are the same as the configuration of the human - powered vehicle 1 and the control device 100 in the first embodiment, except for the following processing procedures. Therefore, among the human - powered vehicle 1 and the control device 100 in the second embodiment, the same components as those in the first embodiment are denoted by the same reference numerals, and detailed descriptions thereof are omitted.

[0114] FIG. 8 is a diagram showing the setting of the reference cadence in the second embodiment. In FIG. 8, the horizontal axis represents the traveling speed, and the vertical axis represents the magnitude of the reference cadence. In FIG. 8, the reference cadence is indicated by a thick line. For each section of the traveling speed, the reference cadence, the upper limit value and the lower limit value sandwiching the reference cadence are stored in the storage unit 112. In the example of FIG. 8, the reference cadence is stored in the storage unit 112 so as to increase step - by - step for each section of the traveling speed range from 0 [km / h] to 20 [km / h], the traveling speed range from 20 [km / h] to 25 [km / h], the traveling speed range from 25 [km / h] to 30 [km / h], and the traveling speed range of 30 [km / h] or more.

[0115] In the second embodiment, the parameter changing unit 116 of the control device 100 changes the reference cadence set for each section of the traveling speed shown in FIG. 8 while maintaining the difference from the reference cadence in adjacent sections within a predetermined range.

[0116] The parameter changing unit 116 of the control device 100 in the second embodiment executes the same processing as the processing procedure shown in FIG. 6 of the first embodiment. Among the processing procedures shown in FIG. 6, the parameter changing unit 116 of the control device 100 in the second embodiment performs a decrease corresponding to the traveling speed in the processing of step S111 and step S113 among the input information acquired in step S101.

[0117] FIG. 9 is a flowchart showing an example of a reference cadence change processing procedure in the second embodiment. The processing procedure shown in FIG. 9 shows the processing procedure when the reference cadence is lowered. The processing procedure shown in FIG. 9 corresponds to the details of the processing procedure of step S111 among the processing procedures shown in FIG. 6.

[0118] The parameter change unit 116 determines whether or not the value after lowering the reference cadence falls within a range equal to or higher than a second threshold value that is the lower limit in the running speed range included in the input information (step S201). When it is determined that the value after lowering falls within the range equal to or higher than the second threshold value (S201: YES), the parameter change unit 116 determines whether or not the difference between the value after lowering and the reference cadence in the adjacent running speed range is within a predetermined difference range (step S203).

[0119] In step S203, when the parameter change unit 116 determines that the difference between the value after lowering and the reference cadence in the adjacent running speed range is within the predetermined difference range (S203: YES), the reference cadence of the running speed included in the input information is lowered by a predetermined value (for example, 1 [rpm]) (step S205).

[0120] In step S203, when the parameter change unit 116 determines that the difference between the value after lowering and the reference cadence in the adjacent running speed range exceeds the predetermined difference range (S203: NO), the reference cadence of all running speed ranges is lowered as a whole by a predetermined value (for example, 1 [rpm]) (step S207).

[0121] In step S201, when it is determined that the value after lowering does not fall within the range equal to or higher than the second threshold value (S201: NO), the parameter change unit 116 ends the process without changing the reference cadence.

[0122] FIG. 10 is a flowchart showing an example of a reference cadence change processing procedure in the second embodiment. The processing procedure shown in FIG. 10 shows the processing procedure when raising the reference cadence, and the processing procedure shown in FIG. 10 corresponds to the details of the processing procedure of step S113 among the processing procedures shown in FIG. 6.

[0123] The parameter change unit 116 determines whether the value after raising the reference cadence falls within a range equal to or less than a first threshold value that is the upper limit in the travel speed range included in the input information (step S301). When it is determined that the value after the raise falls within the range equal to or less than the first threshold value (S301: YES), the parameter change unit 116 determines whether the difference between the value after the raise and the reference cadence in the adjacent travel speed range is within a predetermined difference range (step S303).

[0124] In step S303, when the parameter change unit 116 determines that the difference between the value after the raise and the reference cadence in the adjacent travel speed range is within the predetermined difference range (S303: YES), the reference cadence of the travel speed included in the input information is raised by a predetermined value (for example, 1 [rpm]) (step S305).

[0125] In step S303, when the parameter change unit 116 determines that the difference between the value after the raise and the reference cadence in the adjacent travel speed range exceeds the predetermined difference range (S303: NO), the reference cadence of all travel speed ranges is raised as a whole by a predetermined value (for example, 1 [rpm]) (step S307).

[0126] In step S301, when it is determined that the value after the raise does not fall within the range equal to or less than the first threshold value (S301: NO), the parameter change unit 116 ends the process without changing the reference cadence.

[0127] FIG. 11 is a diagram showing the setting of the reference cadence after the change. Similar to FIG. 8, in FIG. 11, the horizontal axis represents the traveling speed, and the vertical axis represents the magnitude of the reference cadence. In FIG. 11, the reference cadence before the change is indicated by a thick dashed line, and the reference cadence after the change is indicated by a thick solid line. The reference cadence after the change shown in FIG. 11 has a lower reference cadence in the speed range from 0 [km / h] to 20 [km / h] compared to the reference cadence shown in FIG. 8, but it is changed so that the difference from the reference cadence in the adjacent speed range from 20 [km / h] to 25 [km / h] is maintained.

[0128] By setting and changing the reference cadence for each traveling section as shown in the second embodiment, the control can be made to reliably match the reference cadence that the rider feels like maintaining individually. Also, since it is possible to suppress the difference between the reference cadence after the change and the reference cadence in the adjacent traveling speed sections from becoming too large, the automatic control of the transmission 31 is appropriately optimized smoothly for each speed.

[0129] (Third Embodiment) In the first and second embodiments, the processing unit 110 has been described as being configured to automatically control the transmission 31 according to the cadence in the crank 21 by the device control unit 114. However, the automatic control by the device control unit 114 is not limited to the transmission 31, and the reference for automatically controlling the transmission 31 is not limited to the cadence.

[0130] The configuration of the control device 100 in the third embodiment is the same as that of at least one of the control devices 100 in the first and second embodiments, except for the control method by the device control unit 114 and the change target by the parameter change unit 116. Among the configurations of the control device 100 in the third embodiment, the configurations common to the first and second embodiments are denoted by the same reference numerals, and detailed descriptions thereof are omitted.

[0131] In the third embodiment, the processing unit 110 acquires the torque applied to the crank 21 of the drive mechanism 20 of the human-powered vehicle 1 from the torque sensor 63, and compares the reference torque for determining the gear ratio in the transmission 31 with the acquired torque. The processing unit 110, as the device control unit 114, determines the gear ratio according to the range in which the acquired torque is with respect to the reference torque, and controls the transmission 31. Specifically, in the third embodiment, the device control unit 114 determines the gear ratio so that the torque of the crank 21 during traveling fluctuates near the reference torque, and controls the transmission 31.

[0132] FIG. 12 is a schematic diagram of the control algorithm of the transmission 31 in the third embodiment. FIG. 12 shows the criteria for changing the gear ratio with respect to the torque obtained from the torque sensor 63. FIG. 12 shows the magnitude of the torque in the vertical direction, and the larger the torque is shown on the upper side. The device control unit 114 controls so that the torque applied to the crank 21 fluctuates near the reference torque. The device control unit 114 compares the torque obtained from the torque sensor 63 with the upper and lower limit values based on the reference torque to determine the gear ratio. For example, when the torque obtained from the torque sensor 63 reaches an upper limit value greater than the reference torque, the device control unit 114 determines to change the gear ratio to the smaller gear ratio side IW (Inward). Conversely, when the torque obtained from the torque sensor 63 reaches a lower limit value lower than the reference torque, the device control unit 114 determines to change the gear ratio to the larger gear ratio side OW (Outward). After changing the gear ratio, the device control unit 114 controls so that the torque fluctuates near the reference torque.

[0133] In the third embodiment, the storage unit 112 of the control device 100 stores the above-described reference torque, upper limit value, and lower limit value so that they can be changed as parameters. The processing unit 110 of the control device 100 executes a process of changing the reference torque by increasing or decreasing the reference torque as a parameter change unit 116. In the third embodiment, when it is certain that the probability output from the operation probability output model M1 is equal to or greater than a predetermined value and it can be determined that an intervention operation has been performed on the transmission 31, the parameter change unit 116 determines that it is necessary to change the reference torque used by the device control unit 114, and changes the reference torque.

[0134] FIG. 13 is a flowchart showing an example of a parameter change process by the parameter change unit 116 of the third embodiment. Among the processing procedures shown in the flowchart of FIG. 13, the procedures common to the processing procedures shown in the flowchart of FIG. 6 of the first embodiment are given the same step numbers and detailed descriptions thereof are omitted.

[0135] In the third embodiment, when it is determined that the operation probability obtained from the operation probability output model M1 is equal to or greater than a predetermined value and an intervention operation has been determined by the shift instruction device 40B (S107: YES), the parameter change unit 116 determines whether the torque acquired from the torque sensor 63 is equal to or greater than the reference torque (step S131).

[0136] In step S131, when it is determined that the acquired torque is equal to or greater than the reference torque (S131: YES), since the lidar intends to change the gear ratio while the torque is increasing, in order to facilitate control to reduce the gear ratio (lighten the control) with that torque, the parameter change unit 116 decreases the reference torque (step S133). The parameter change unit 116 ends the parameter change process.

[0137] In step S131, if it is determined that the acquired torque is less than the reference torque (S131: NO), since the torque is in a decreasing state and the rider has the intention to change the gear ratio, in order to facilitate the control of increasing the gear ratio (heavy control) for that torque, the parameter changing unit 116 raises the reference torque (step S135). The parameter changing unit 116 ends the parameter changing process.

[0138] In step S107, if it is not certain that the operation probability is equal to or greater than the predetermined value, or if the intervention operation by the shift instruction device 40B is not determined (S107: NO), the parameter changing unit 116 ends the process without doing anything.

[0139] In this way, the reference torque is adjusted so as to surely match the operation intention of the rider with respect to the human - powered vehicle 1 according to the situation, and the automatic control by the device control unit 114 is more appropriately optimized.

[0140] Regarding the reference torque as well, as shown in the second embodiment, different references are stored for each section of the traveling speed, and the parameter changing unit 116 may perform raising and lowering so that the difference from the reference torque in the adjacent traveling speed sections becomes within a predetermined range according to the intervention operation from the rider.

[0141] (Fourth Embodiment) In the fourth embodiment, the processing unit 110 automatically controls the assist device 33 according to the cadence by the device control unit 114. The automatic control of the assist device 33 based on the cadence by the device control unit 114 in the fourth embodiment described below can be combined with and substituted for the control of the transmission 31 by the cadence in the first and second embodiments.

[0142] The configuration of the human-powered vehicle 1 according to the fourth embodiment and the configuration of the control device 100 are the same as those in the first embodiment, except for the processing procedures shown below. Therefore, for the common configurations of the human-powered vehicle 1 and the control device 100 according to the fourth embodiment, the same reference numerals as those in the first embodiment are used, and detailed descriptions thereof are omitted.

[0143] In the fourth embodiment, the processing unit 110 of the control device 100 compares the cadence of the crank 21 of the drive mechanism 20 of the human-powered vehicle 1 with the reference cadence stored in the storage unit 112 by the device control unit 114, and controls the assist device 33 of the human-powered vehicle 1 based on the comparison result.

[0144] FIG. 14 is a schematic diagram of the control algorithm of the assist device 33 according to the fourth embodiment. FIG. 14 shows the criteria for changing the output of the assist device 33 with respect to the cadence obtained from the cadence sensor 64. In FIG. 14, the magnitude of the cadence is shown in the vertical direction, and the larger the cadence is, the closer it is to the upper side. The device control unit 114 controls the cadence applied to the crank 21 to transition near the reference cadence. The device control unit 114 compares the cadence obtained from the cadence sensor 64 with the upper and lower limit values based on the reference cadence, and determines the output from the assist device 33. When the cadence obtained from the cadence sensor 64 reaches a value equal to or greater than the upper limit value greater than the reference cadence, the device control unit 114 determines to reduce the output from the assist device 33 and decrease the output. Conversely, when the cadence reaches a value equal to or less than the lower limit value based on the reference cadence, the device control unit 114 determines to increase the output from the assist device 33 and increase the output.

[0145] In the fourth embodiment, the storage unit 112 of the control device 100 stores the reference cadence, upper limit value, and lower limit value for the output of the assist device 33 described above as parameters so that they can be changed. The processing unit 110 of the control device 100, as a parameter change unit 116, executes a process of raising or lowering and changing the reference cadence for comparison with the cadence for determining the output in the assist device 33 described above. In the fourth embodiment, when it is certain that the probability output from the operation probability output model M1 is equal to or greater than a predetermined value and it can be determined that an intervention operation has been performed on the assist device 33, the parameter change unit 116 determines that it is necessary to change the reference cadence used by the device control unit 114, and changes the reference cadence.

[0146] FIG. 15 is a flowchart showing an example of a parameter change process by the parameter change unit 116 in the fourth embodiment. Among the processing procedures shown in the flowchart of FIG. 15, the procedures common to the processing procedures shown in the flowchart of FIG. 6 in the first embodiment are assigned the same step numbers and detailed descriptions thereof are omitted.

[0147] In the fourth embodiment, when it is determined that the operation probability obtained from the operation probability output model M1 is definitely equal to or greater than a predetermined value and an intervention operation has been determined by the assist instruction device 40C (S107: YES), the parameter change unit 116 determines whether the cadence acquired from the cadence sensor 64 is equal to or greater than the reference cadence (step S141).

[0148] In step S141, when it is determined that the acquired cadence is equal to or greater than the reference cadence (S141: YES), since the cadence is in an increasing state and the rider intends to change the output from the assist device 33, in order to facilitate control to reduce the output (make it heavier) at that cadence, the parameter change unit 116 lowers the reference cadence for the assist device 33 (step S143). The parameter change unit 116 ends the parameter change process.

[0149] In step S141, if it is determined that the acquired cadence is less than the reference cadence (S141: NO), since the cadence is in a decreasing state and the rider intends to change the output from the assist device 33, in order to facilitate the control of increasing the output (lightening the control) at that cadence, the parameter changing unit 116 raises the reference cadence for the assist device 33 (step S145). The parameter changing unit 116 ends the parameter change process.

[0150] In step S107, if it is not certain that the operation probability is equal to or greater than a predetermined value, or if the intervention operation by the assist instruction device 40C is not determined (S107: NO), the parameter changing unit 116 ends the process without doing anything.

[0151] In this way, the reference cadence is adjusted so as to surely match the rider's operation intention for the human - powered vehicle 1 according to the situation, and the automatic control by the device control unit 114 is more appropriately optimized.

[0152] (Fifth Embodiment) In the fifth embodiment, the reference cadence is set and stored for each section of the traveling speed. When raising and lowering the reference cadence for determining the output from the assist device 33, control is performed to balance it with the reference cadence in other sections of the traveling speed.

[0153] The configuration of the human - powered vehicle 1 and the configuration of the control device 100 in the fifth embodiment are the same as the configurations of the human - powered vehicle 1 and the control device 100 in the first embodiment and the fourth embodiment, except for the following processing procedures. Therefore, for the common configurations among the human - powered vehicle 1 and the control device 100 in the fifth embodiment, the same reference numerals as those in the first embodiment and the fourth embodiment are used, and detailed descriptions are omitted.

[0154] FIG. 16 is a diagram showing the setting of the reference cadence in the fifth embodiment. In FIG. 16, the horizontal axis represents the traveling speed, and the vertical axis represents the magnitude of the reference cadence. In FIG. 16, the reference cadence is indicated by a thick line. For each section of the traveling speed, the reference cadence, and the upper and lower limit values sandwiching the reference cadence are stored in the storage unit 112. In the example of FIG. 16, the reference cadence for determining the output from the assist device 33 is stored in the storage unit 112 so as to increase stepwise for each section of the traveling speed range from 0 [km / h] to 20 [km / h], the traveling speed range from 20 [km / h] to 25 [km / h], the traveling speed range from 25 [km / h] to 30 [km / h], and the traveling speed range of 30 [km / h] or more.

[0155] In the fifth embodiment, the parameter changing unit 116 of the control device 100 changes the reference cadence for the assist device 33 set for each section of the traveling speed shown in FIG. 16 while maintaining the difference from the reference cadence in adjacent sections within a predetermined range. The parameter changing unit 116 of the control device 100 in the fifth embodiment executes the same processing as the processing procedure shown in FIG. 15 of the fourth embodiment. Among the processing procedures shown in FIG. 15, the parameter changing unit 116 of the control device 100 in the fifth embodiment performs a reduction corresponding to the traveling speed among the input information acquired in step S101 in the processing of steps S143 and S145.

[0156] Also in the fifth embodiment, the parameter changing unit 116 executes the processing procedure shown in FIG. 9 of the second embodiment in step S143, and executes the processing procedure shown in FIG. 10 of the second embodiment in step S145. In the fifth embodiment, the target of the increase and decrease by the parameter changing unit 116 is the reference cadence for determining the output of the assist device 33.

[0157] With the configuration of the fifth embodiment, the reference cadence for determining the output of the assist device 33 is also changed so as to change smoothly for each speed, and the automatic control of the assist device 33 is appropriately optimized.

[0158] (Sixth Embodiment) In the sixth embodiment, the processing unit 110 automatically controls the assist device 33 by the torque in the crank 21 by the device control unit 114. The configuration of the control device 100 in the sixth embodiment is the same as that of the control device 100 in the first embodiment, except for the control method by the device control unit 114 and the change target by the parameter change unit 116. Among the configurations of the control device 100 in the sixth embodiment, the configurations common to the first and second embodiments are denoted by the same reference numerals and detailed descriptions thereof are omitted.

[0159] In the sixth embodiment, the processing unit 110 acquires the torque of the crank 21 of the drive mechanism 20 of the human-powered vehicle 1 from the torque sensor 63, and compares the reference torque for determining the output in the assist device 33 with the acquired torque. The processing unit 110, as the device control unit 114, determines the output from the assist device 33 according to which range the acquired torque is in with respect to the reference torque, and controls the assist device 33. Specifically, in the sixth embodiment, the device control unit 114 determines the output from the assist device 33 so that the torque of the crank 21 during traveling changes in the vicinity of the reference torque.

[0160] FIG. 17 is a schematic diagram of the control algorithm of the assist device 33 in the sixth embodiment. FIG. 17 shows the criteria for changing the output from the assist device 33 with respect to the torque obtained from the torque sensor 63. FIG. 16 shows the magnitude of the torque in the vertical direction, with the upper side indicating a larger torque. The device control unit 114 controls so that the torque applied to the crank 21 fluctuates near the reference torque. The device control unit 114 compares the torque obtained from the torque sensor 63 with the upper and lower limit values based on the reference torque, and determines the output from the assist device 33. For example, when the torque obtained from the torque sensor 63 reaches an upper limit value greater than the reference torque, the device control unit 114 determines to increase the output from the assist device 33 and increase the output. It may be a switch to a mode with a large output from the assist device 33. It may also be a switch to a mode with a large ratio of the output from the assist device 33 to the manual torque. Conversely, when the torque obtained from the torque sensor 63 reaches a lower limit value lower than the reference torque, the device control unit 114 determines to decrease the output from the assist device 33 and decrease the output. It may be a switch to a mode with a small output from the assist device 33. It may also be a switch to a mode with a small ratio of the output from the assist device 33 to the manual torque. The device control unit 114 controls so that the torque fluctuates near the reference torque even after the output is changed.

[0161] In the sixth embodiment, the storage unit 112 of the control device 100 stores the reference cadence, upper limit value, and lower limit value for the output of the assist device 33 described above as parameters so that they can be changed. The processing unit 110 of the control device 100 executes a process of raising or lowering and changing the reference torque compared with the torque for determining the output in the assist device 33 described above as the parameter change unit 116. In the sixth embodiment, when it is certain that the probability output from the operation probability output model M1 is equal to or greater than a predetermined value and it can be determined that an intervention operation has been performed on the assist device 33, the parameter change unit 116 determines that it is necessary to change the reference torque used by the device control unit 114, and changes the reference torque.

[0162] FIG. 18 is a flowchart showing an example of a parameter change processing procedure by the parameter change unit 116 of the sixth embodiment. Among the processing procedures shown in the flowchart of FIG. 18, the procedures common to the processing procedures shown in the flowchart of FIG. 6 of the first embodiment are assigned the same step numbers and detailed descriptions thereof are omitted.

[0163] In the sixth embodiment, when it is determined that the operation probability obtained from the operation probability output model M1 is equal to or greater than a predetermined value and an intervention operation is determined by the assist instruction device 40C (S107: YES), the parameter change unit 116 determines whether the torque acquired from the torque sensor 63 is equal to or greater than the reference torque (step S151).

[0164] In step S151, when it is determined that the acquired torque is equal to or greater than the reference torque (S151: YES), since the lidar intends to change the output from the assist device 33 while the torque is increasing, in order to facilitate the control of increasing the output with that torque (lightening control), the parameter change unit 116 decreases the reference torque for the assist device 33 (step S153). The parameter change unit 116 ends the parameter change process.

[0165] In step S151, when it is determined that the acquired torque is less than the reference torque (S151: NO), since the lidar intends to change the output from the assist device 33 while the torque is decreasing, in order to facilitate the control of decreasing the output with that torque (weighting control), the parameter change unit 116 increases the reference torque for the assist device 33 (step S155). The parameter change unit 116 ends the parameter change process.

[0166] In step S107, when it is not determined that the operation probability is equal to or greater than the predetermined value or when the intervention operation by the assist instruction device 40C is not determined (S107: NO), the parameter change unit 116 ends the process without performing anything.

[0167] In this way, the reference torque is adjusted so as to surely match the operation intention of the rider with respect to the human-powered vehicle 1 according to the situation, and the automatic control by the device control unit 114 is more appropriately optimized.

[0168] The embodiments disclosed as above are illustrative in all respects and not restrictive. The scope of the present invention is indicated by the claims, and includes all modifications within the meaning and scope equivalent to the claims.

[0169] As used herein, the expression "at least one" means "one or more" of the desired options. As an example, as used herein, the expression "at least one" means "only one option" or "both of the two options" if the number of options is two. As another example, as used herein, the expression "at least one" means "only one option" or "any combination of two or more options" if the number of options is three or more.

Explanation of Reference Signs

[0170] 1…Human-powered vehicle, 10…Vehicle body, 10A…Frame, 10B…Front fork, 12…Handlebar, 14…Front wheel, 16…Rear wheel, 18…Saddle, 20…Drive mechanism, 21…Crank, 21A…Crankshaft, 21B…Right crank, 21C…Left crank, 23…First sprocket assembly, 23A…Sprocket, 25…Second sprocket assembly, 25A…Sprocket, 27…Chain, 29…Pedal, 30…Device, 31…Transmission, 33…Assist device, 40…Operating device, 40A…Operation unit, 40B…Shift indicator, 40C…Assist indicator, 50…Battery, 51…Battery body, 53…Battery holder, 60…Sensor, 61…Speed sensor, 62…Acceleration sensor, 63…Torque sensor, 64…Cadence sensor, 65…Gyro sensor, 66…Seat sensor, 67…Camera, 7…Client device, 100…Control device, 110…Processing unit, 112…Memory unit, 114…Device control unit, 116…Parameter change unit, 118…Wireless communication device, P14…Device control program, P16…Setting update program, 200…Non-transitory storage medium, P2…App program, 900…Non-transitory storage medium, P94…Device control program, P96…Setting update program

Claims

1. A processor that reads information from a memory unit and executes processing, wherein the processor acquires input information regarding the running of a human-powered vehicle, determines control data for a device mounted on the human-powered vehicle by a predetermined control algorithm based on the acquired input information, automatically controls the device with the determined control data, uses an operation probability output model that outputs the probability that a rider intervenes in the automatic control of the device based on the input information, and changes the parameters of the predetermined control algorithm when it is certain that the probability output from the operation probability output model is equal to or greater than a predetermined value and it is certain that the intervention operation has been performed. A human-powered vehicle control device.

2. The processor determines that it is certain that the probability is equal to or greater than a predetermined value when the probability output from the operation probability output model is a peak in time series and is equal to or greater than a predetermined value. The human-powered vehicle control device according to claim 1.

3. The processor determines that the intervention operation has been performed when an intervention operation is performed on the device by the rider and no other intervention operation is performed on the device within a predetermined time from the intervention operation. The human-powered vehicle control device according to claim 1.

4. It includes a learning unit that uses the input information as an input and learns the operation probability output model with the presence or absence of the rider's intervention operation on the device after a predetermined time when the input information is acquired as an output label. The human-powered vehicle control device according to claim 1.

5. It includes a learning unit that uses the input information as an input and learns the operation probability output model with a value corresponding to the rider's discomfort after a predetermined time when the input information is acquired as an output label. The human-powered vehicle control device according to claim 1.

6. The device is a transmission of the human-powered vehicle, the input information includes the cadence of the crank of the drive mechanism of the human-powered vehicle, and the processor changes, by raising or lowering, a reference cadence to be compared with the cadence for determining a gear ratio in the transmission as the parameter. The human-powered vehicle control device according to claim 1.

7. The input information includes the running speed of the human-powered vehicle, and the reference cadence is set for each section of the running speed. The processor changes the reference cadence in the section including the running speed of the input information while maintaining the difference from the reference cadence in the adjacent section within a predetermined range. The human-powered vehicle control device according to claim 6.

8. The device is a transmission of the human-powered vehicle, and the input information includes the torque of the crank of the drive mechanism of the human-powered vehicle. The processor changes the reference torque for comparison with the torque for determining the gear ratio in the transmission as the parameter by increasing or decreasing it. The human-powered vehicle control device according to any one of claims 1 to 3.

9. The device is an assist device of the human-powered vehicle, and the input information includes the cadence of the crank of the drive mechanism of the human-powered vehicle. The processor changes the reference cadence for comparison with the cadence for determining the output in the assist device as the parameter by increasing or decreasing it. The human-powered vehicle control device according to any one of claims 1 to 3.

10. The input information includes the running speed of the human-powered vehicle. The reference cadence is set for each section of the running speed. The processor changes the reference cadence in the section including the running speed of the input information while maintaining the difference from the reference cadence in the adjacent section within a predetermined range. The human-powered vehicle control device according to claim 9.

11. The device is an assist device of the human-powered vehicle, and the input information includes the torque of the crank of the drive mechanism of the human-powered vehicle. The processor changes the reference torque for comparison with the torque for determining the output in the assist device as the parameter by increasing or decreasing it. The human-powered vehicle control device according to any one of claims 1 to 3.

12. A computer mounted on a human-powered vehicle that reads information from a storage unit and executes processing acquires input information regarding the running of the human-powered vehicle, determines control data of a device mounted on the human-powered vehicle by a predetermined control algorithm based on the acquired input information, automatically controls the device with the determined control data, and uses an operation probability output model that outputs the probability of a rider's intervention operation with respect to the automatic control of the device based on the input information. When it is certain that the probability output from the operation probability output model is equal to or greater than a predetermined value and it is certain that the intervention operation has been performed, change the parameters of the predetermined control algorithm. Human-powered vehicle control method.

13. A computer mounted on a human-powered vehicle that reads information from a storage unit and executes processing, acquires input information related to the running of the human-powered vehicle, determines control data for a device mounted on the human-powered vehicle by a predetermined control algorithm based on the acquired input information, automatically controls the device with the determined control data, uses an operation probability output model that outputs the probability that a rider will perform an intervention operation on the automatic control of the device based on the input information, When it is certain that the probability output from the operation probability output model is equal to or greater than a predetermined value and it is certain that the intervention operation has been performed, change the parameters of the predetermined control algorithm. A computer program that causes processing to be executed.

Images