Control device for human-powered vehicles

Abstract

To provide a control device for a human-powered vehicle which can control an electric device preferably.SOLUTION: A control device is a control device for a human-powered vehicle and includes a control unit configured to control an electric device of the human-powered vehicle. The control unit is configured to control the electric device in a first mode for off-road traveling. Further, the control unit is configured to estimate at least one of land information and an obstacle according to a front image of a travel path obtained by the imaging device in the first mode and control the electric device according to the at least one of the land information and the obstacle estimated. The land information gives information about a land on a first flat surface intersecting with a travel direction of the human-powered vehicle. The obstacle is an obstacle placed on the first flat surface.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present disclosure relates to a control device for a human-powered vehicle. [Background technology]

[0002] For example, the control device for a human-powered vehicle disclosed in Patent Document 1 controls an electric device in accordance with the output of a sensor that detects the traveling state. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6005110 Summary of the Invention [Problem to be solved by the invention]

[0004] The control device for a human-powered vehicle in Patent Document 1 can control an electric device according to the traveling state of the human-powered vehicle, but does not take into consideration the surrounding environment, etc. An object of the present disclosure is to provide a control device for a human-powered vehicle that can suitably control an electric device. [Means for solving the problem]

[0005] A control device according to a first aspect of the present disclosure is a control device for a human-powered vehicle, comprising a control unit configured to control an electric device of the human-powered vehicle, the control unit being configured to be able to control the electric device in a first mode for traveling off-road, and being configured to estimate at least one of land information and obstacles in accordance with a forward image of the traveling path acquired by an imaging device in the first mode, and to control the electric device in accordance with the estimated land information and at least one of the obstacles, the forward land information being on a first plane that intersects with the traveling direction of the human-powered vehicle, and the obstacles being on the first plane. According to the control device of the first aspect, it is possible to suitably control the electric device in accordance with at least one of the estimated land information on the first plane and the obstacles on the first plane.

[0006] In the control device of a second aspect according to the first aspect of the present disclosure, the control unit includes a first plane estimation unit configured to estimate at least one of the land information and the obstacle from the forward image. According to the control device of the second aspect, the first plane estimation section can suitably estimate at least one of land information and obstacles from the forward image.

[0007] In the control device of a third aspect according to the second aspect of the present disclosure, the first plane estimation unit includes an artificial intelligence processing unit. According to the control device of the third aspect, at least one of land information and obstacles can be suitably estimated from the forward image by the artificial intelligence processing unit.

[0008] In the control device of the fourth aspect according to the third aspect of the present disclosure, the artificial intelligence processing unit is configured to identify an object on the driving path based on the forward image, and to estimate at least one of the land information and the obstacle based on the identified object. According to the control device of the fourth aspect, at least one of the land information and the obstacle can be suitably estimated by identifying at least one of the features of the land information and the obstacle as an object from the forward image.

[0009] First to fourth aspects of the present disclosure One of In the control device of the fifth aspect according to the present invention, the first plane is perpendicular to the traveling direction. According to the control device of the fifth aspect, the electric device can be suitably controlled in accordance with at least one of land information and obstacles in a first plane perpendicular to the traveling direction.

[0010] Aspects 1 to 5 of the present disclosure One ofIn the control device of the sixth aspect according to the present invention, the at least one of the land information and the obstacle includes the land information, and the land information includes at least one of topography information in the first plane and ground surface information in the first plane. According to the control device of the sixth aspect, the electric device can be controlled in response to at least one of topographical information and ground surface information ahead of the travel path.

[0011] In the control device of the seventh aspect according to the sixth aspect of the present disclosure, the at least one of the topographical information and the ground surface information includes the topographical information, and further includes a first memory unit that stores two-dimensional image information relating to the topographical information, and the control unit is configured to estimate the topographical information by comparing the forward image with the image information. According to the control device of the seventh aspect, the topographical information can be suitably estimated by comparing the forward image with the image information.

[0012] Aspects 1 to 7 of the present disclosure One of In the control device according to an eighth aspect, the control unit is configured to control the electric device in response to the estimated land information and a distance to the at least one of the obstacles. According to the control device of the eighth aspect, the motorized device can be suitably controlled according to the land information and the distance to at least one of the obstacles.

[0013] Aspects 1 to 8 of the present disclosure One of In the control device of a ninth aspect according to the present invention, a second memory unit that stores judgment information is further provided, and the control unit is configured to, when a suspected obstacle is detected based on the forward image, estimate whether the detected suspected obstacle corresponds to the obstacle based on the judgment information. According to the control device of the ninth aspect, since it is possible to determine whether a detected suspected obstacle corresponds to an obstacle, the accuracy of obstacle detection can be improved.

[0014] Aspects 1 to 9 of the present disclosure One ofIn the control device according to a tenth aspect according to the present invention, the control unit includes a passage difficulty estimation unit configured to estimate a passage difficulty for the human-powered vehicle based on the land information and the at least one of the obstacles. According to the control device of the tenth aspect, the degree of difficulty of passage for a human-powered vehicle can be suitably estimated based on at least one of land information and obstacles.

[0015] In the control device of an eleventh aspect according to a tenth aspect of the present disclosure, the passing difficulty level estimation unit is configured to estimate the passing difficulty level in response to information relating to a rider. According to the control device of the eleventh aspect, it is possible to suitably estimate the passage difficulty level corresponding to the rider.

[0016] In the control device of a twelfth aspect according to an eleventh aspect of the present disclosure, the control unit is configured to control the electrically-powered device in accordance with the estimated passing difficulty level. According to the control device of the twelfth aspect, the electric device can be suitably controlled according to the rider and the corresponding degree of difficulty of passage.

[0017] In the control device of the thirteenth aspect according to the twelfth aspect of the present disclosure, the electric device includes an alarm unit, and the control unit is configured to control the alarm unit to alarm information regarding the estimated difficulty of passing. According to the control device of the thirteenth aspect, the rider can grasp the degree of difficulty of passing.

[0018] Aspects 1 to 12 of the present disclosure One of In the control device of a fourteenth aspect according to the present invention, the electrically-powered device includes an alarm unit, and the control unit is configured to control the alarm unit to alarm the land information and information relating to the at least one of the obstacles. The control device of the fourteenth aspect enables the lidar to grasp at least one of land information and obstacles.

[0019] Aspects 1 to 14 of the present disclosure One ofIn the control device according to a fifteenth aspect, the control unit includes a slipperiness estimation unit configured to estimate slipperiness of the human-powered vehicle in response to the at least one of the land information and the obstacle. According to the control device of the fifteenth aspect, the slipperiness estimation section can suitably estimate slipperiness according to at least one of land information and obstacles.

[0020] In the control device of a sixteenth aspect according to a fifteenth aspect of the present disclosure, the control unit is configured to control the electric device depending on the slipperiness. According to the control device of the sixteenth aspect, the electric device can be suitably controlled according to the slipperiness.

[0021] In the control device of the seventeenth aspect according to the sixteenth aspect of the present disclosure, the electric device includes a motor configured to provide propulsive force to the human-powered vehicle, and the control unit is configured to control the motor in response to the slipperiness. According to the control device of the seventeenth aspect, the motor can be suitably controlled according to the slipperiness.

[0022] In the control device of the 18th aspect according to the 16th or 17th aspect of the present disclosure, the electric device includes an electric brake that brakes the human-powered vehicle, and the control unit is configured to control the electric brake according to the slipperiness. According to the control device of the eighteenth aspect, the electric brake can be suitably controlled according to the degree of slipperiness.

[0023] Aspects 1 to 18 of the present disclosure One of In the control device of a nineteenth aspect according to the present invention, the control unit is configured to be able to select one of a plurality of modes including the first mode. The control device of the nineteenth aspect allows selection of one of a plurality of modes including the first mode.

[0024] In the control device of a twentieth aspect according to a nineteenth aspect of the present disclosure, the control unit is configured to be able to select the one mode in response to an operation input to an operation unit. According to the control device of the twentieth aspect, the rider can select the first mode by operating the operating unit. Effect of the Invention

[0025] According to the control device of the present disclosure, it is possible to suitably control an electrically-driven device. [Brief description of the drawings]

[0026] [Figure 1] 1 is a side view of a human-powered vehicle including a control device for a human-powered vehicle according to an embodiment; [Diagram 2] 2 is a block diagram showing an electrical configuration of the human-powered vehicle including the control device for the human-powered vehicle of FIG. 1; [Diagram 3] Schematic diagram of the estimation section in Figure 2. [Figure 4] Schematic diagram of a learning model included in the artificial intelligence processing unit in Figure 3. [Diagram 5] 2 is a schematic diagram showing a relationship between the human-powered vehicle of FIG. 1 and a first plane. [Figure 6] FIG. 4 is a schematic diagram of an example of a forward image processed by the artificial intelligence processing unit of FIG. 3 . [Figure 7] 4 is a schematic diagram of a forward image onto which a cross-sectional view of a road in a first plane estimated by a first plane estimation unit in FIG. 3 is superimposed. [Figure 8] 3 is a schematic diagram of an example of image information stored in a second storage unit in FIG. 2; [Figure 9] 3 is a flowchart of a process executed by the control unit of FIG. 2 to estimate at least one of land information and obstacles. [Figure 10] 3 is a flowchart of a process executed by the control unit in FIG. 2 to estimate a passing difficulty level. [Figure 11] 3 is a flowchart of a process for estimating slipperiness, which is executed by the control unit in FIG. 2 . [Figure 12] 3 is a flowchart of a process executed by the control unit in FIG. 2 to control the notification unit in response to information about a suspected obstacle. [Figure 13] 3 is a flowchart of a process executed by the control unit in FIG. 2 to control the notification unit in accordance with land information. [Figure 14] 3 is a flowchart of a process executed by the control unit in FIG. 2 to control a motor. [Figure 15] 3 is a flowchart of a process executed by the control unit in FIG. 2 to control an electric brake. [Figure 16] 3 is a flowchart of a process executed by the control unit in FIG. 2 to control the electric brake in accordance with the road surface gradient. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0027] <Embodiment> A control device 60 for a human-powered vehicle according to an embodiment will be described with reference to Figs. 1 to 16. A human-powered vehicle is a vehicle that has at least one wheel and can be driven at least by human-powered driving force. Human-powered vehicles include various types of bicycles, such as mountain bikes, road bikes, city bikes, cargo bikes, hand bikes, and recumbents. The number of wheels that a human-powered vehicle has is not limited. Human-powered vehicles also include, for example, one-wheeled vehicles and vehicles with three or more wheels. Human-powered vehicles are not limited to vehicles that can be driven only by human-powered driving force. Human-powered vehicles include E-bikes that use not only human-powered driving force but also the driving force of an electric motor for propulsion. E-bikes include electrically assisted bicycles whose propulsion is assisted by an electric motor. In the following embodiment, a human-powered vehicle will be described as a mountain bike.

[0028] In this specification, the following directional terms, such as “front,” “rear,” “forward,” “backward,” “left,” “right,” “sideways,” “upward,” and “downward,” and any other similar directional terms, refer to those directions determined with reference to a rider facing the handlebars 34 in a reference position on the human-powered vehicle 10 (e.g., on the saddle 36A or seat).

[0029] The human-powered vehicle 10 includes at least one wheel 14 and a vehicle body 16. The at least one wheel 14 includes a rear wheel 14A and a front wheel 14B. The vehicle body 16 includes a frame 18. The vehicle body 16 is provided with an input rotation shaft 12A that is rotatable relative to the frame 18. In this embodiment, the input rotation shaft 12A is a crank shaft included in the crank 12. The crank 12 includes the input rotation shaft 12A, a first crank arm 12B provided at one end in the axial direction of the input rotation shaft 12A, and a second crank arm 12C provided at the other end in the axial direction of the input rotation shaft 12A. A pedal 20 is connected to the crank 12. The pedal 20 includes a first pedal 20A and a second pedal 20B. The first pedal 20A is connected to the first crank arm 12B. The second pedal 20B is connected to the second crank arm 12C. The rear wheel 14A is driven by the rotation of the crank 12. The rear wheel 14A is supported by a frame 18. The crank 12 is connected to the rear wheel 14A by a drive mechanism 22.

[0030] The drive mechanism 22 includes a first rotor 24 connected to the input rotary shaft 12A. The input rotary shaft 12A may be connected to the first rotor 24 so as to rotate integrally with the input rotary shaft 12A, or may be connected via a first one-way clutch. The first one-way clutch is configured to rotate the first rotor 24 forward when the crank 12 rotates forward, and to allow relative rotation between the crank 12 and the first rotor 24 when the crank 12 rotates backward. The first rotor 24 includes a front sprocket. The first rotor 24 may include a pulley or a bevel gear. The drive mechanism 22 further includes a second rotor 26 and a connecting member 28. The connecting member 28 transmits the rotational force of the first rotor 24 to the second rotor 26. The connecting member 28 includes, for example, a chain, a belt, or a shaft.

[0031] The second rotating body 26 is connected to the rear wheel 14A. The second rotating body 26 includes a rear sprocket. The second rotating body 26 may include a pulley or a bevel gear. A second one-way clutch is preferably provided between the second rotating body 26 and the rear wheel 14A. The second one-way clutch is configured to rotate the rear wheel 14A forward when the second rotating body 26 rotates forward, and to allow relative rotation between the second rotating body 26 and the rear wheel 14A when the second rotating body 26 rotates backward.

[0032] A front wheel 14B is attached to the frame 18 via a front fork 30. A handlebar 34 is connected to the front fork 30 via a stem 32. The handlebar 34 and the stem 32 form a handlebar. In this embodiment, the rear wheel 14A is connected to the crank 12 by the drive mechanism 22, but at least one of the rear wheel 14A and the front wheel 14B may be connected to the crank 12 by the drive mechanism 22. A seat post 36 on which a saddle 36A is provided is attached to the frame 18.

[0033] For example, the human-powered vehicle 10 further includes a battery 38. The battery 38 includes one or more battery elements. The battery elements include a rechargeable battery. The battery 38 is configured to supply power to the control device 60. The battery 38 is preferably communicatively connected to a control unit 62 of the control device 60 via an electric cable or a wireless communication device. The battery 38 can communicate with the control unit 62 by, for example, power line communication (PLC), a controller area network (CAN), or a universal asynchronous receiver / transmitter (UART).

[0034] The human-powered vehicle 10 further includes an electric device 40. For example, the electric device 40 is provided on the human-powered vehicle 10. For example, the electric device 40 includes an electric actuator. For example, the electric device 40 is supplied with power from a battery 38. The electric device 40 may include a built-in battery.

[0035] For example, the motorized device 40 includes an alarm unit 42. The alarm unit 42 outputs alarm information using at least one of light, sound, and vibration. For example, the alarm unit 42 includes at least one of a display unit, a sound generation unit, and a vibration unit. For example, the display unit included in the alarm unit 42 includes a liquid crystal display panel or an organic EL (Electro-Luminescence) panel. For example, the display unit outputs various alarm information by displaying characters, numbers, symbols, patterns, images, icons, and the like. For example, the display unit may output various alarm information by a lighting pattern of a light-emitting element. An example of a light-emitting element is an LED (Light Emitting Diode) lamp. For example, the sound generation unit included in the alarm unit 42 includes a speaker or a buzzer. For example, the sound generation unit outputs various alarm information by voice, melody, beep, and the like. For example, the vibration unit included in the alarm unit 42 outputs various alarm information by, for example, a vibration pattern. The notification unit 42 may be, for example, at least one of a cycle computer and a smartphone. The notification unit 42 is provided on the handlebar 34 of the human-powered vehicle 10, the stem 32 of the human-powered vehicle 10, or the top tube of the frame 18 of the human-powered vehicle 10. The notification unit 42 may also be provided on a helmet, a wristwatch, or a protector worn by the rider. The notification unit 42 is connected to the control unit 62 via a wireless communication device or an electric cable.

[0036] For example, the electric device 40 includes a motor 44 configured to provide a propulsive force to the human-powered vehicle 10. For example, the motor 44 assists in the propulsion of the human-powered vehicle 10. The motor 44 includes an electric motor. The motor 44 is accommodated in a housing 44A. A drive circuit for the motor 44 is provided in the housing 44A. The drive circuit controls the power supplied from the battery 38 to the motor 44. In this embodiment, the motor 44 transmits an assist torque to a power transmission path of the human-powered driving force from the crank 12 to the first rotor 24. It is preferable that a one-way clutch is provided in the power transmission path between the motor 44 and the crank 12 so that the motor 44 is not rotated by the rotational force of the crank 12 when the crank 12 is rotated in the forward direction of the human-powered vehicle 10. The control unit of the motor 44 drives the motor 44 in response to at least one of the human-powered driving force and the rotational speed of the crank 12. When the control unit of the motor 44 receives an operation command, the control unit of the motor 44 switches the operation state. The control unit of the motor 44 operates the motor 44 in a plurality of operation modes with different assist characteristics. For example, the assist characteristics include an assist force. The assist force means the strength of the assist by the motor 44. The assist force may be an assist ratio. The plurality of operation modes may include a plurality of operation modes with different assist ratios. The plurality of operation modes may include a plurality of operation modes with different upper limits of the assist torque. The motor 44 switches the operation mode in response to an operation command. The motor 44 may be configured to switch the operation mode in sequence each time it receives an operation command. The motor 44 may be configured to switch the operation mode in response to an operation command corresponding to the plurality of operation modes. The operation mode of the motor 44 may include a mode in which the motor 44 does not assist the propulsion of the human-powered vehicle 10.

[0037] For example, the electric device 40 includes an electric brake 46 that brakes the human-powered vehicle 10. For example, the electric brake 46 includes at least one of a front brake 46F and a rear brake 46R. For example, the electric brake 46 generates a braking force that brakes the rotation of the wheels 14 in response to the operation of a brake lever 46A. The brake lever 46A is provided on the handlebar 34. At least one of the front brake 46F and the rear brake 46R operates in response to the amount of operation of the brake lever 46A. In this case, the brake lever 46A and at least one of the front brake 46F and the rear brake 46R may be connected by a wire. For example, the front brake 46F and the rear brake 46R may be a rim brake, a disc brake, or a roller brake.

[0038] The front brake 46F is provided on the front fork 30 and generates a braking force for braking the rotation of the front wheel 14B. The front brake 46F includes an electric actuator or an electric motor. When the control unit of the front brake 46F receives an operation command, the control unit operates the electric actuator or the electric motor to move the brake shoes, the brake pads, or the rollers to generate a braking force. When the control unit of the front brake 46F receives an operation command, the control unit switches the operation state. The control unit of the front brake 46F operates the front brake 46F in a plurality of operation modes having different braking characteristics. The plurality of operation modes includes a plurality of operation modes having different upper limit values ​​of the braking force. The plurality of operation modes may include a plurality of operation modes having different ratios of the braking force to the operation amount of the brake lever 46A. The front brake 46F switches the operation mode in response to the operation command. The front brake 46F may be configured to switch the operation mode in sequence each time it receives one operation command. The front brake 46F may be configured to switch the operation mode in response to an operation command corresponding to the plurality of operation modes.

[0039] The rear brake 46R is provided on the frame 18 and generates a braking force for braking the rotation of the rear wheel 14A. The rear brake 46R includes an electric actuator or an electric motor. When the control unit of the rear brake 46R receives an operation command, the control unit operates the electric actuator or the electric motor to move the brake shoes, brake pads, or rollers to generate a braking force. When the control unit of the rear brake 46R receives an operation command, the control unit switches the operation state. The control unit of the rear brake 46R operates the rear brake 46R in a plurality of operation modes having different braking characteristics. The plurality of operation modes includes a plurality of operation modes having different upper limit values ​​of the braking force. The plurality of operation modes may include a plurality of operation modes having different ratios of the braking force to the operation amount of the brake lever 46A. The rear brake 46R switches the operation mode in response to the operation command. The rear brake 46R may be configured to switch the operation mode in sequence each time it receives one operation command. The rear brake 46R may be configured to switch the operation mode in response to an operation command corresponding to the plurality of operation modes.

[0040] For example, the human-powered vehicle 10 is provided with an imaging device 48 capable of capturing a forward image F of the human-powered vehicle 10. When the imaging device 48 is provided in the human-powered vehicle 10, for example, the imaging device 48 is provided in the frame 18 or the handlebar 34. The imaging device 48 may be provided in the rider. When the imaging device 48 is provided in the rider, the imaging device 48 may be provided in a helmet worn by the rider. The imaging device 48 includes, for example, a camera. The imaging device 48 may be capable of capturing only the forward image F, or may be capable of capturing the forward image F and a peripheral image other than the forward image F. The imaging device 48 may be capable of capturing an image of the entire circumference around the imaging device 48. For example, the imaging device 48 is configured to be able to communicate with the control device 60 by at least one of wireless communication and wired communication. The imaging device 48 transmits the captured forward image F to the control device 60.

[0041] For example, the control device 60 includes a control unit 62. The control unit 62 includes a processor that executes a predetermined control program. The processor included in the control unit 62 includes, for example, a CPU (Central Processing Unit) or an MPU (Micro Processing Unit). The processors included in the control unit 62 may be provided in multiple locations separated from each other. The control unit 62 may include one or multiple microcomputers.

[0042] For example, the control device 60 further includes a storage unit 64. The storage unit 64 stores a predetermined control program and information used in the control process. The storage unit 64 includes, for example, a non-volatile memory and a volatile memory. The non-volatile memory includes, for example, at least one of a Read-Only Memory (ROM), an Erasable Programmable Read Only Memory (EPROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), and a flash memory. The volatile memory includes, for example, a Random Access Memory (RAM).

[0043] For example, the control device 60 further includes a first storage unit 64A that stores two-dimensional image information related to topographical information. The first storage unit 64A includes, for example, a non-volatile memory and a volatile memory. The non-volatile memory includes, for example, at least one of a ROM, an EPROM, an EEPROM, and a flash memory. The volatile memory includes, for example, a RAM.

[0044] For example, the control device 60 further includes a second storage unit 64B that stores the determination information. The second storage unit 64B includes, for example, a non-volatile memory and a volatile memory. The non-volatile memory includes, for example, at least one of a ROM, an EPROM, an EEPROM, and a flash memory. The volatile memory includes, for example, a RAM.

[0045] For example, the first storage unit 64A is configured integrally with the storage unit 64. For example, the second storage unit 64B is configured integrally with the storage unit 64. For example, the first storage unit 64A is configured integrally with the second storage unit 64B.

[0046] The control unit 62 is configured to control the electric device 40 of the human-powered vehicle 10. The control unit 62 is configured to be able to control the electric device 40 in the first mode. The control unit 60 may be provided in the electric device 40, or may be provided in a component of the human-powered vehicle 10 other than the electric device 40. For example, the control unit 60 is configured to control the electric device 40 by transmitting an operation command. When the electric device 40 includes a notification unit 42, the electric device 40 can be read as the notification unit 42 in the description of the control of the electric device 40 by the control unit 62. When the electric device 40 includes a motor 44, the electric device 40 can be read as the motor 44 in the description of the control of the electric device 40 by the control unit 62. When the electric device 40 includes an electric brake 46, the electric device 40 can be read as the electric brake 46 in the description of the control of the electric device 40 by the control unit 62.

[0047] For example, the control unit 62 is configured to be able to select one of a plurality of modes including a first mode. For example, the plurality of modes include a first mode and a second mode. The first mode is a mode for traveling off-road. An off-road is, for example, a road on which the human-powered vehicle 10 can travel, and is an unpaved road. The second mode is a mode for traveling on a road that is not off-road. For example, the control unit 62 is configured to be able to select the first mode according to an operation input to the operation unit 50. For example, the operation unit 50 is provided on the handlebar 34. The operation unit 50 may be provided on at least one of a cycle computer and a smartphone. For example, the operation unit 50 includes at least one of a button and a lever. When the operation unit 50 includes a button, the operation unit 50 may be provided with a button corresponding to the first mode and a button corresponding to the second mode. When the operation unit 50 includes a button, the operation unit 50 may be configured to switch between the first mode and the second mode by pressing one button. When the operation unit 50 includes a lever, a lever corresponding to the first mode and a lever corresponding to the second mode may be provided on the operation unit 50. When the operation unit 50 includes a lever, the operation unit 50 may be configured to switch between the first mode and the second mode by operating one lever.

[0048] For example, the control unit 62 includes an electric device control unit 68. The electric device control unit 68 controls the electric device 40. The electric device control unit 68 controls the electric device 40 in response to at least one of a signal from an operating device of the electric device 40, the driving environment of the human-powered vehicle 10, and the driving state of the human-powered vehicle 10. For example, the operating device of the electric device 40 is provided on the handlebar 34. In the case where the electric device 40 includes an electric brake 46, the operating device of the electric device 40 includes a brake lever 46A. For example, the electric device control unit 68 is configured to transmit an operation command to the electric device 40 to be controlled.

[0049] For example, the control unit 62 is configured to control the electric device 40 in response to at least one of the human-powered driving force, the rotation speed of the input rotating shaft 12A, the vehicle speed, and the tilt angle of the human-powered vehicle 10. The human-powered vehicle 10 further includes at least one of a human-powered driving force detection unit 52, a crank rotation sensor 54, a vehicle speed sensor 56, and a tilt sensor 58.

[0050] The human-powered driving force detection unit 52 is configured to detect information related to the human-powered driving force. The human-powered driving force detection unit 52 is provided, for example, on the frame 18, the motor 44, the crank 12, or the pedals 20A, 20B of the human-powered vehicle 10. The human-powered driving force detection unit 52 may be provided on the housing 44A of the motor 44. The human-powered driving force detection unit 52 includes, for example, a torque sensor. The torque sensor is configured to output a signal corresponding to the torque applied to the crank 12 by the human-powered driving force. For example, when a first one-way clutch is provided in the power transmission path, the torque sensor is preferably provided upstream of the first one-way clutch in the power transmission path. The torque sensor includes a strain sensor, a magnetostrictive sensor, a pressure sensor, or the like. The strain sensor includes a strain gauge.

[0051] The crank rotation sensor 54 is configured to detect information related to the rotation speed of the input rotating shaft 12A. The crank rotation sensor 54 is provided, for example, on the frame 18 or the motor 44 of the human-powered vehicle 10. The crank rotation sensor 54 may be provided on the housing 44A of the motor 44. The crank rotation sensor 54 includes a magnetic sensor that outputs a signal according to the strength of a magnetic field. An annular magnet with an S pole and an N pole adjacent to each other in the circumferential direction is provided on the input rotating shaft 12A, a member that rotates in conjunction with the input rotating shaft 12A, or a power transmission path from the input rotating shaft 12A to the first rotor 24. The member that rotates in conjunction with the input rotating shaft 12A may include the output shaft of the motor 44.

[0052] The vehicle speed sensor 56 is configured to output a predetermined number of detection signals during one rotation of one of the at least one wheels 14. The predetermined number is, for example, 1. The vehicle speed sensor 56 outputs a signal corresponding to the rotation speed of the wheel 14. The control unit 62 can calculate the vehicle speed of the human-powered vehicle 10 based on the signal corresponding to the rotation speed of the wheel 14 and information related to the circumference of the wheel 14.

[0053] For example, the vehicle speed sensor 56 is configured to detect information related to the vehicle speed of the human-powered vehicle 10. The vehicle speed sensor 56 is configured to detect information related to the rotational speed of at least one wheel 14 of the human-powered vehicle 10. The vehicle speed sensor 56 is configured to detect, for example, a magnet provided on at least one wheel 14 of the human-powered vehicle 10. The vehicle speed sensor 56 includes, for example, a magnetic reed constituting a reed switch, or a magnetic sensor such as a Hall element. The vehicle speed sensor 56 may be configured to be attached to a chain stay of the frame 18 of the human-powered vehicle 10 and detect a magnet attached to the rear wheel 14A, or may be configured to be attached to the front fork 30 and detect a magnet attached to the front wheel 14B.

[0054] The vehicle speed sensor 56 may have any configuration as long as it can obtain information related to the vehicle speed of the human-powered vehicle 10. The vehicle speed sensor 56 may be configured to detect slits provided in a disc brake, for example. The vehicle speed sensor 56 may be configured to include an optical sensor, for example. The vehicle speed sensor 56 may be configured to include a GPS (Global Positioning System) receiver, for example. When the vehicle speed sensor 56 includes a GPS receiver, the control unit 62 can calculate the vehicle speed according to the time and the traveled distance. The vehicle speed sensor 56 is connected to the control unit 62 via a wireless communication device or an electric cable.

[0055] The tilt sensor 58 is configured to detect information related to the tilt of the human-powered vehicle 10. The tilt sensor 58 includes, for example, a gyro sensor or an acceleration sensor. The tilt sensor 58 includes a GPS receiver. The control unit 62 may calculate the tilt angle of the road surface on which the human-powered vehicle 10 is traveling, based on the GPS information acquired by the GPS receiver and the road surface gradient included in the map information pre-recorded in the memory unit 64.

[0056] For example, in the first mode, the control unit 62 estimates at least one of land information and obstacles according to a forward image F of the road captured by the imaging device 48. The land information is on a first plane P that intersects with the traveling direction of the human-powered vehicle 10. The obstacles are on the first plane P.

[0057] As shown in FIG. 5, for example, the first plane P is set in front of the traveling direction of the human-powered vehicle 10. For example, the first plane P is perpendicular to the traveling direction. The lateral direction of the human-powered vehicle 10 is the X-axis direction, the height direction of the human-powered vehicle 10 is the Y-axis direction, and the traveling direction of the human-powered vehicle 10 is the Z-axis direction. For example, the lateral direction of the human-powered vehicle 10 is the left-right direction of the human-powered vehicle 10. For example, the height direction of the human-powered vehicle 10 is above or below the human-powered vehicle 10. For example, the traveling direction of the human-powered vehicle 10 is forward of the human-powered vehicle 10. The first plane P is defined by a front plane that is a distance D from the human-powered vehicle 10 in the Z-axis direction. For example, the first plane P is perpendicular to the Z-axis direction. For example, the first plane P is perpendicular to the X-axis direction and perpendicular to the Y-axis direction. The first plane P may be set so as not to be perpendicular to at least one of the X-axis direction and the Y-axis direction. For example, the control unit 62 may set a second plane different from the first plane P in addition to the first plane P, and estimate at least one of land information on the second plane and obstacles on the second plane. The second plane may include a plurality of different planes. For example, each of the plurality of different planes has a different positional relationship with the human-powered vehicle 10. The second plane may be a forward plane that is parallel to the first plane P and is at a distance different from the distance D from the human-powered vehicle 10 in the Z-axis direction.

[0058] For example, the control unit 62 includes a first plane estimation unit 72A. For example, the control unit 62 includes an estimation unit 70. For example, the estimation unit 70 includes at least one of a first plane estimation unit 72A, a passing difficulty estimation unit 72B, and a slipperiness estimation unit 72C. For example, the first plane estimation unit 72A is configured to estimate at least one of land information and obstacles from the forward image F.

[0059] For example, the first plane estimation unit 72A includes an artificial intelligence processing unit 74A. The artificial intelligence processing unit 74A includes, for example, a storage device 76A that stores software, and an arithmetic processing unit 78A that executes the software stored in the storage device 76A. The arithmetic processing unit 78A includes, for example, a CPU or MPU. The arithmetic processing unit 78A preferably includes a GPU (Graphics Processing Unit) in addition to the CPU or MPU. The arithmetic processing unit 78A may include a field-programmable gate array (FPGA). The artificial intelligence processing unit 74A may include one or more arithmetic processing units 78A. The artificial intelligence processing unit 74A may include a plurality of arithmetic processing units 78A that are disposed at a plurality of locations. The storage device 76A includes, for example, a non-volatile memory and a volatile memory. The storage device 76A stores a control program 80A, a learning program 82A, and a learning model 84A. The learning model 84A may be a learned model that has been learned by a predetermined learning algorithm, or may be configured to be updated by a learning algorithm. The learning algorithm includes machine learning, deep learning, or deep reinforcement learning. The learning algorithm includes, for example, at least one of supervised learning, unsupervised learning, and reinforcement learning. As the learning algorithm, a method other than the method described in this specification may be used as long as it is configured to update the learning model 84A using a method belonging to the field of artificial intelligence. The learning process for updating the learning model 84A is preferably performed by a GPU. The learning algorithm may use a neural network (NN). The learning algorithm may use a recurrent neural network (RNN).

[0060] For example, the land information includes at least one of the land information and the obstacle information. For example, the land information includes at least one of the topography information on the first plane P and the ground surface information on the first plane P.

[0061] For example, the terrain information relates to the shape of the terrain. For example, the shape of the terrain includes at least one of a ridge, a valley, a slope traverse, a gentle drop, a steep drop, a flat, a hill, a single bank, a gentle slope, a steep slope, and a wall. For example, the artificial intelligence processing unit 74A estimates the terrain information on the first plane P based on the forward image F.

[0062] For example, the ground surface information relates to the state of the ground surface. The state of the ground surface includes at least one of a state in which objects such as tree roots and rocks are exposed on the road, a state in which the road is covered with loose sand, mud, puddles, fallen leaves, and moss, a state in which the road is sandy, a state related to the soil quality of the road, and a state related to the wetness of the road. For example, the artificial intelligence processing unit 74A estimates the ground surface information on the first plane P based on the forward image F.

[0063] For example, the obstacles include trees growing on the road, branches hanging down on the road, rocks on the road, etc. For example, the artificial intelligence processing unit 74A estimates the obstacles on the first plane P based on the forward image F.

[0064] 4 includes an input layer 86, an intermediate layer 88, and an output layer 90. Input information is input to the input layer 86. The learning model 84A is trained in advance to output output information from the output layer 90 when information is input to the input layer 86. The intermediate layer 88 learns the relationship between the information input to the input layer 86 and the output information output by the output layer 90 by using teacher data.

[0065] For example, the learning model 84A is configured to be updatable by an external device 92. The external device 92 is, for example, a smartphone or a personal computer. For example, when the learning model 84A is updatable by the external device 92, the number of convolutional layers 88A, pooling layers 88B, and fully connected layers 88C of the intermediate layer 88 can be updated. The relationship learned by the intermediate layer 88 between the input information input to the input layer 86 and the output information output by the output layer 90 can be updated.

[0066] In the artificial intelligence processing unit 74A, the input information is an image of a road. The image of the road is, for example, an image of an off-road road. In the artificial intelligence processing unit 74A, the output information is at least one of terrain information and obstacles on the first plane P. The teacher data used by the intermediate layer 88 includes information on the image of the road and information on at least one of the terrain information and obstacles.

[0067] For example, the artificial intelligence processing unit 74A estimates at least one of land information and obstacles based on the forward image F. For example, the artificial intelligence processing unit 74A estimates at least one of topographical information and obstacles by performing image processing on the forward image F. For example, when the forward image F transmitted from the imaging device 48 is input, the artificial intelligence processing unit 74A estimates a travel path based on the feature amount of the forward image F. For example, the artificial intelligence processing unit 74A is configured to estimate a first plane P from the estimated travel path and estimate at least one of topographical information and obstacles on the estimated first plane P. For example, the artificial intelligence processing unit 74A identifies an object X on the travel path based on the forward image F. The artificial intelligence processing unit 74A is configured to estimate at least one of land information and obstacles based on the identified object X. For example, the artificial intelligence processing unit 74A detects edges from the forward image F and identifies the detected edges as object X. For example, the object X is a characteristic part in the forward image F. For example, the object X includes at least one outline of a characteristic ground surface, a tree, a rock, and an artificial object that is different from the surrounding ground surface.

[0068] For example, the artificial intelligence processing unit 74A identifies a boundary B between an area in the forward image F that is a driving path and an area that is not a driving path based on the identified object X. The artificial intelligence processing unit 74A is configured to estimate the driving path based on the identified boundary B. For example, the artificial intelligence processing unit 74A estimates the driving path by detecting edges from the forward image F. For example, the area in the forward image F that is a driving path includes an area in the forward image F that is the ground surface and is suitable for driving. For example, the area suitable for driving includes a flat earth road surface and a flat paved road. For example, the area in the forward image F that is not a driving path includes an area in the forward image F that is not the ground surface and an area in the forward image F that is the ground surface and is not suitable for driving. For example, the area that is not the ground surface includes a water surface, a sky, and a space. For example, the area that is not suitable for driving includes a green area, an untravelable slope, a cliff, an uneven earth road surface, and an uneven paved road. For example, the driving path estimated by the artificial intelligence processing unit 74A has a width in the left-right direction of the human-powered vehicle 10, which is perpendicular to the driving direction of the human-powered vehicle 10. For example, if there is an obstacle that the human-powered vehicle 10 cannot pass, the artificial intelligence processing unit 74A does not specify that part as the driving path.

[0069] For example, the artificial intelligence processing unit 74A estimates that there is a change in the road based on the boundary B going forward. For example, when the boundary B going forward is curved, the artificial intelligence processing unit 74A determines that there is a curve in the road. For example, when the boundary B going forward is interrupted in the traveling direction of the human-powered vehicle 10, and when the boundary B extends laterally in the front and the two boundaries B overlap, the artificial intelligence processing unit 74A determines that there is a step in the estimated road. For example, when the boundary B is distorted, the artificial intelligence processing unit 74A estimates that there is a road surface gradient in the road. For example, the artificial intelligence processing unit 74A estimates that there is a road surface gradient in the road based on the position on the front image F of the boundary B that contacts the part corresponding to the sky. For example, the artificial intelligence processing unit 74A estimates that there is a change in the road surface gradient in the road in response to the distortion of the boundary B. For example, the artificial intelligence processing unit 74A estimates that there is a change in the road surface gradient in the road based on the position on the front image F of the boundary B that contacts the part corresponding to the sky. For example, when the boundary B surrounds a certain area, the artificial intelligence processing unit 74A estimates that there is an obstacle on the travel path.

[0070] FIG. 6 shows an example of a forward image when the road has a road gradient. For example, FIG. 6 shows a scene where the road has a downhill road gradient. For example, the artificial intelligence processing unit 74A determines that the road has a road gradient because the range between the right boundary B and the left boundary B is distorted so as to narrow rapidly toward the front. For example, when the range between the right boundary B and the left boundary B is distorted so as to narrow rapidly toward the front, and the boundary B is curved after narrowing, the artificial intelligence processing unit 74A estimates that the road is downhill.

[0071] For example, the artificial intelligence processing unit 74A estimates a first plane P on the estimated travel path. For example, the distance from the human-powered vehicle 10 to an object captured in the forward image F can be detected by color aperture imaging technology. The artificial intelligence processing unit 74A can create a three-dimensional model of the forward image F from the object captured in the forward image F based on the distance from the human-powered vehicle 10 to the object captured in the forward image F. The artificial intelligence processing unit 74A estimates the first plane P from the three-dimensional model of the forward image F and the distance to the object captured in the forward image F detected by the color aperture imaging technology. The first plane estimation unit 72A estimates a cross-sectional view S of the travel path on the estimated first plane P. The artificial intelligence processing unit 74A may estimate the cross-sectional view S of the travel path on the first plane P without using a three-dimensional model. In this case, the artificial intelligence processing unit 74A estimates multiple planes from the forward image F and identifies a plane located at a distance D forward from the human-powered vehicle 10 in the Z-axis direction as the first plane P. The artificial intelligence processing unit 74A may estimate a cross-sectional view S of the road on the first plane P by connecting together only the contours of the object X located on the first plane P.

[0072] For example, the cross-sectional view S of the travel path on the first plane P is a boundary between an area where an object exists and an area where no object exists on the first plane P. The cross-sectional view S of the travel path may include a boundary between an area where an obstacle exists and an area where no obstacle exists on the first plane P. The first plane P is set so as to straddle an area below the ground surface of the travel path and an area above the ground surface of the travel path. The first plane estimation unit 72A estimates the shape of the ground surface of the travel path on the first plane P as the cross-sectional view S of the travel path on the first plane P. For example, the cross-sectional view S of the travel path on the first plane P includes the exposed ground surface of the travel path. For example, if an obstacle is included on the first plane P, the cross-sectional view S of the travel path on the first plane P includes the outline of the obstacle. For example, the cross-sectional view S of the travel path on the first plane P is represented by a single line.

[0073] Fig. 7 shows an estimated cross-sectional view S superimposed on a forward image F when the road includes a valley. In Fig. 7, the cross-sectional view S of the road on the first plane P has an upwardly opening shape. For example, the artificial intelligence processing unit 74A outputs the cross-sectional view S of the road on the first plane P as an estimation result of at least one of the topographical information and the obstacle.

[0074] For example, at least one of the topographical information and the ground surface information includes topographical information, and the control unit 62 is configured to estimate the topographical information by comparing a forward image F with the image information. For example, the control unit 62 is configured to estimate the topographical information by comparing a first plane P estimated from the forward image F with the image information. The control unit 62 is configured to estimate the topographical information by comparing a cross-sectional view S of the road on the first plane P with the image information. For example, the first plane estimation unit 72A estimates the topographical information by comparing the cross-sectional view S of the road on the first plane P with the image information.

[0075] FIG. 8 shows an example of image information stored in the first storage unit 64A. For example, the image information includes a plurality of figures. Each of the plurality of figures is a two-dimensional figure corresponding to the topographical information. For example, each of the plurality of figures is represented by a single line. The first plane estimation unit 72A selects, from the plurality of figures, a figure that is most similar in shape to the cross-sectional view S of the road on the first plane P. Table 1 shows the topographical information associated with the image information A to L shown in FIG. 8.

[0076] [Table 1]

[0077] The first plane estimation unit 72A may determine the degree of agreement between the cross-sectional view S of the road on the first plane P and the figure from the magnitude of deviation in a predetermined direction when the cross-sectional view S of the road on the first plane P and the figure are superimposed. For example, the first plane estimation unit 72A determines the degree of agreement between the cross-sectional view S of the road on the first plane P and the figure based on the magnitude of deviation between the lines included in the cross-sectional view S and the lines included in the figure. For example, the first plane estimation unit 72A determines the magnitude of deviation between the lines included in the cross-sectional view S and the lines included in the figure based on the area of ​​the area surrounded by the lines included in the cross-sectional view S and the lines included in the figure. In this case, for example, the first plane estimation unit 72A scales the sizes of the cross-sectional view S and the figure to adjust the cross-sectional view S and the figure to the same scale, and then determines the degree of agreement between the cross-sectional view S of the road on the first plane P and the figure.

[0078] The first plane estimation unit 72A may include an additional artificial intelligence processing unit that estimates a figure that is most similar in shape to the cross-sectional view S of the road on the first plane P, separately from the artificial intelligence processing unit 74A. When the first plane estimation unit 72A includes the additional artificial intelligence processing unit, the additional artificial intelligence processing unit includes a learning model that outputs information about the figure in response to input of information about the cross-sectional view S of the road. For example, the learning model includes an input layer, an intermediate layer, and an output layer, and is configured to be able to update the relationship between the information about the cross-sectional view S of the road input to the input layer and the information about the figure output by the output layer in response to the characteristics of the rider of the human-powered vehicle 10. The additional artificial intelligence processing unit may learn the information about the cross-sectional view S of the road and the information about the figure as teacher data. The additional artificial intelligence processing unit is configured to output image information that is most similar to the cross-sectional view S of the road among the figures included in the image information. The additional artificial intelligence processing unit may be configured to output the degree of similarity between each of the figures included in the image information and the cross-sectional view S of the road as information about the figure. The control unit 62 may control the electric device 40 according to the degree of match between each of the figures included in the image information output from the additional artificial intelligence processing unit and the cross-sectional diagram S of the travel path.

[0079] An example of a method for estimating topographical information by the first plane estimation unit 72A will be described with reference to FIG. 7 and FIG. 8. For example, since the road in FIG. 7 is a valley, the estimated cross-sectional view S shown in FIG. 7 has an upwardly open shape. For example, the first plane estimation unit 72A is configured to select a figure that is close to the shape of the cross-sectional view S from among the two-dimensional image information related to the topographical information stored in the first storage unit 64A when the cross-sectional view S is estimated. For example, the image information A in FIG. 8 is associated with a valley in the topographical information. For example, when the artificial intelligence processing unit 74A estimates that the cross-sectional view S in FIG. 7 is closest to the shape of the image information A among the image information, the first plane estimation unit 72A estimates that the topographical information on the first plane P of the road is a valley.

[0080] The artificial intelligence processing unit 74A may be configured to estimate ground surface information on the first plane P of the estimated travel path instead of or in addition to the topographical information. For example, the artificial intelligence processing unit 74A estimates whether or not objects such as tree roots and rocks are exposed on the estimated travel path. For example, the artificial intelligence processing unit 74A estimates the state of the ground surface from the color of the travel path in the forward image F. For example, the artificial intelligence processing unit 74A estimates whether or not the travel path is covered with loose sand, mud, puddles, fallen leaves, moss, and the like from the color of the travel path. For example, the artificial intelligence processing unit 74A estimates whether or not the travel path is sandy from the color of the travel path. For example, the artificial intelligence processing unit 74A estimates the soil quality of the travel path from the color of the travel path. For example, the artificial intelligence processing unit 74A estimates whether or not the travel path is wet from the color of the travel path.

[0081] The artificial intelligence processing unit 74A may be configured to estimate a suspected obstacle on the first plane P of the estimated travel path instead of or in addition to the topographical information. For example, the artificial intelligence processing unit 74A estimates a suspected obstacle on the first plane P from the result of edge detection of the travel path. A suspected obstacle is, for example, an area surrounded by a boundary B in the forward image F, but which cannot be determined to be an obstacle. A suspected obstacle includes, for example, sunlight filtering through the trees, fog, and dust. If the imaging device 48 includes a lens, a suspected obstacle includes, for example, water droplets on the lens of the imaging device 48.

[0082] For example, when the control unit 62 detects a suspected obstacle based on the forward image F, the control unit 62 is configured to estimate whether or not the detected suspected obstacle corresponds to an obstacle based on the determination information. The control unit 62 causes the artificial intelligence processing unit 74A to estimate the suspected obstacle based on the forward image F. The determination information is, for example, information related to transparency. For example, when the transparency of the suspected obstacle is high, the first plane estimation unit 72A estimates that the suspected obstacle is a region that is not an obstacle. When the transparency of the suspected obstacle is high, the background of the suspected obstacle can be confirmed as being continuous with the surrounding background.

[0083] A process in which the control unit 62 estimates at least one of land information and obstacles on the first plane P will be described with reference to the flowchart of Fig. 9. For example, when power is supplied to the control unit 62, the control unit 62 starts the process and proceeds to step S11 of the flowchart shown in Fig. 9. When the flowchart of Fig. 9 ends, the control unit 62 repeats the process from step S11 after a predetermined period, for example, until the supply of power is stopped.

[0084] In step S11, the control unit 62 determines whether or not a front image F has been input. If a front image F has been input, the control unit 62 proceeds to step S12. If a front image F has not been input, the control unit 62 ends the process.

[0085] In step S12, the control unit 62 estimates the driving path, and the process proceeds to step S13. For example, the control unit 62 inputs the input front image F to the artificial intelligence processing unit 74A, and estimates the driving path. For example, the process of step S12 is executed by the artificial intelligence processing unit 74A.

[0086] In step S13, the control unit 62 estimates at least one of land information and obstacles on the first plane P, and ends the process. In step S13, the control unit 62 estimates at least one of land information and obstacles on the first plane P based on the travel path estimated by the process of step S12. For example, the process of step S13 is executed by the artificial intelligence processing unit 74A.

[0087] The control unit 62 does not estimate the driving route from the forward image F, but calculates land information and At least one of the obstacles may be estimated. In this case, step S12 is omitted. In the case of YES in step S11, the control unit 62 proceeds to step S13. In this case, for example, the artificial intelligence processing unit 74A estimates at least one of the land information and the obstacles in the first plane P including the area that is not a driving path.

[0088] For example, the control unit 62 estimates the passing difficulty level for the human-powered vehicle 10 based on at least one of the land information and the obstacles. For example, the control unit 62 includes a passing difficulty level estimation unit 72B. The passing difficulty level estimation unit 72B is configured to estimate the passing difficulty level for the human-powered vehicle 10 based on at least one of the land information and the obstacles. For example, the passing difficulty level estimation unit 72B is configured to estimate the passing difficulty level in response to information on the rider.

[0089] For example, the passing difficulty estimation unit 72B includes an artificial intelligence processing unit 74B. The artificial intelligence processing unit 74B includes, for example, a storage device 76B that stores software, and an arithmetic processing device 78B that executes the software stored in the storage device 76B. The arithmetic processing device 78B includes, for example, a CPU or MPU. The arithmetic processing device 78B preferably includes a GPU in addition to the CPU or MPU. The arithmetic processing device 78B may include an FPGA. The artificial intelligence processing unit 74B may include one or more arithmetic processing devices 78B. The artificial intelligence processing unit 74B may include a plurality of arithmetic processing devices 78B that are disposed at a plurality of locations. The storage device 76B includes, for example, a non-volatile memory and a volatile memory. The storage device 76B stores a control program 80B, a learning program 82B, and a learning model 84B. The learning model 84B may be a trained model trained by a predetermined learning algorithm, or may be configured to be updated by the learning algorithm. The learning algorithm includes machine learning, deep learning, or deep reinforcement learning. The learning algorithm includes, for example, at least one of supervised learning, unsupervised learning, and reinforcement learning. As the learning algorithm, a method other than the method described in this specification may be used as long as it is configured to update the learning model 84B using a method belonging to the field of artificial intelligence. The learning process for updating the learning model 84B is preferably performed by a GPU. The learning algorithm may use a neural network. The learning algorithm may use a recurrent neural network.

[0090] An example of the learning model 84B of the artificial intelligence processing unit 74B includes an input layer, an intermediate layer, and an output layer. Input information is input to the input layer. The learning model 84B is pre-trained to output output information from the output layer when information is input to the input layer. The intermediate layer learns the relationship between the input information input to the input layer and the output information output by the output layer by using teacher data. The learning model 84B of the artificial intelligence processing unit 74B may be configured in the same manner as the learning model 84A of the artificial intelligence processing unit 74A shown in FIG. 3, for example, except that the teacher data is different. The artificial intelligence processing unit 74B may be configured integrally with the artificial intelligence processing unit 74A. In this case, the artificial intelligence processing unit 74B includes a learning model for estimating the passing difficulty from the forward image F.

[0091] For example, the learning model 84B is configured to be updatable by the external device 92. For example, when the learning model 84B is updatable by the external device 92, the numbers of the convolutional layers, the pooling layers, and the fully connected layers in the intermediate layers can be updated. The relationship between the input information input to the input layer on which the intermediate layer learns and the output information output by the output layer can be updated.

[0092] The intermediate layer learns the relationship between the input information input to the input layer and the output information output by the output layer by using the teacher data. In the case of the artificial intelligence processing unit 74B, the input information is at least one of land information, obstacles, and information about the rider. In the case of the artificial intelligence processing unit 74B, the output information is the difficulty of passing. In layersTherefore, the teacher data used includes information on at least one of the land information, the obstacle, and the information on the rider, and information on the passing difficulty. For example, the passing difficulty, which is the output information, is information indicating whether the rider can pass through the travel path corresponding to the land information and the obstacle. For example, the information indicating whether the rider can pass through the travel path corresponding to the land information and the obstacle is expressed in stages according to the level of passing difficulty. The level of passing difficulty includes impassable and passable. Passable includes difficult to pass and easy to pass. The information indicating whether the rider can pass through the travel path corresponding to the land information and the obstacle may be the probability that the rider can pass through the travel path.

[0093] For example, the control unit 62 estimates the passage difficulty level based on information about land information and information about the rider. The information about the rider includes information about the width of the handlebars 34, information about the shape of the rider's head when the rider rides on the human-powered vehicle 10, and the like. Location The information includes at least one of information regarding the position of the crank 12, information regarding the length of the crank 12, and information regarding the width of the human-powered vehicle 10. For example, if the road on the first plane P is a valley, the control unit 62 compares the width of the valley with the width of the handlebar 34 to determine whether the road is passable.

[0094] If the road is passable, the control unit 62 The corresponding driving path The control unit 62 may compare a threshold value for determining that the area is easy to pass with the parameter related to the difficulty of passing estimated by the passing difficulty estimation unit 72B to determine whether the area is easy to pass. For example, if the parameter related to the difficulty of passing is lower than the threshold value for determining that the area is easy to pass, the control unit 62 determines that the area is easy to pass. The threshold value for determining that the area is easy to pass can be changed, for example, depending on the driving technique of the rider. The control unit 62 may compare the land information about the area to be passed with the parameter related to the difficulty of passing estimated by the passing difficulty estimation unit 72B to determine whether the area is easy to pass. The corresponding driving path Similar types of land information The corresponding driving path Depending on the number of times the lidar has been able to pass through in the past, the land information The corresponding driving path The threshold value for determining that the obstacle is easy to pass through may be changed.

[0095] The artificial intelligence processing unit 74B may be configured to output the passing difficulty level assuming that the terrain information is given when the terrain information of the land information is not given as the input information. In this case, the artificial intelligence processing unit 74B outputs the passing difficulty level assuming that the terrain information is given as flat.

[0096] The artificial intelligence processing unit 74B receives the land information as input information. Surface information If not given, Surface information In this case, the artificial intelligence processing unit 74B may be configured to output the passing difficulty level assuming that Surface information Given flat soil, output the difficulty of passing.

[0097] The artificial intelligence processing unit 74B may be configured to output the passing difficulty level as if an obstacle was given when no obstacle was given as input information. In this case, the artificial intelligence processing unit 74B outputs the passing difficulty level as if information that there is no obstacle was given.

[0098] The artificial intelligence processing unit 74B may be configured to output the passing difficulty level as if information about a rider is given when information about a rider is not given as input information. In this case, the artificial intelligence processing unit 74B outputs the passing difficulty level as if information about a predetermined rider is given.

[0099] The process of estimating the passage difficulty level by the control unit 62 will be described with reference to the flowchart of Fig. 10. For example, when power is supplied to the control unit 62, the control unit 62 starts the process and proceeds to step S21 of the flowchart shown in Fig. 10. When the flowchart of Fig. 10 ends, the control unit 62 repeats the process from step S21 after a predetermined period, for example, until the supply of power is stopped.

[0100] In step S21, the control unit 62 determines whether the first plane estimation unit 72A has estimated at least one of the land information and the obstacle. If the first plane estimation unit 72A has estimated at least one of the land information and the obstacle, the control unit 62 proceeds to step S22. If the first plane estimation unit 72A has not estimated at least one of the land information and the obstacle, the control unit 62 ends the process.

[0101] In step S22, the control unit 62 estimates the passage difficulty level and ends the process. For example, the process of step S22 is executed by the artificial intelligence processing unit 74B.

[0102] When the artificial intelligence processing unit 74A is configured integrally with the artificial intelligence processing unit 74B, the process of step S21 may be omitted. In this case, when the process of step S13 in FIG. 9 is completed, the process may proceed to step S22.

[0103] For example, the control unit 62 estimates the slipperiness of the human-powered vehicle 10 based on at least one of the land information and the obstacles. The slipperiness of the human-powered vehicle 10 may include the slipperiness in the traveling direction of the human-powered vehicle 10 and the slipperiness in the lateral direction of the human-powered vehicle 10. The slipperiness may be expressed by a level or a numerical value. For example, the control unit 62 determines that the human-powered vehicle 10 is more slippery when the shape of the terrain includes at least one of a ridge, a valley, a slope traverse, a gentle one-sided drop, a steep one-sided drop, a hill, a one-sided bank, a gentle one-sided slope, and a steep one-sided slope, than when the shape of the terrain is flat. For example, the control unit 62 determines that the human-powered vehicle 10 is more slippery when objects such as tree roots and rocks are exposed on the traveling road than when the traveling road is a dry paved road. For example, when the road is covered with loose sand, mud, puddles, fallen leaves, moss, etc., the control unit 62 determines that the human-powered vehicle 10 is more slippery than when the road is a dry paved road. For example, when the road is sandy, the control unit 62 determines that the human-powered vehicle 10 is more slippery than when the road is a dry paved road. For example, when the soil of the road is muddy, the control unit 62 determines that the human-powered vehicle 10 is more slippery than when the road is a dry paved road. For example, when the road is wet, the control unit 62 determines that the human-powered vehicle 10 is more slippery than when the road is a dry paved road. Place If this is the case, it is determined that the road is more slippery for the human-powered vehicle 10 than if the road were a dry paved road.

[0104] For example, the control unit 62 includes a slipperiness estimation unit 72C. The slipperiness estimation unit 72C is configured to estimate the slipperiness of the human-powered vehicle 10 according to at least one of land information and obstacles.

[0105] For example, the slipperiness estimation unit 72C includes an artificial intelligence processing unit 74C. The artificial intelligence processing unit 74C includes, for example, a storage device 76C that stores software, and an arithmetic processing unit 78C that executes the software stored in the storage device 76C. The arithmetic processing unit 78C includes, for example, a CPU or MPU. The arithmetic processing unit 78C preferably includes a GPU in addition to the CPU or MPU. The arithmetic processing unit 78C may include an FPGA. The artificial intelligence processing unit 74C may include one or more arithmetic processing units 78C. The artificial intelligence processing unit 74C may include a plurality of arithmetic processing units 78C that are disposed at a plurality of locations. The storage device 76C includes, for example, a non-volatile memory and a volatile memory. The storage device 76C stores a control program 80C, a learning program 82C, and a learning model 84C. The learning model 84C may be a trained model trained by a predetermined learning algorithm, or may be configured to be updated by the learning algorithm. The learning algorithm includes machine learning, deep learning, or deep reinforcement learning. The learning algorithm may include at least one of supervised learning, unsupervised learning, and reinforcement learning. As the learning algorithm, a method other than the method described in this specification may be used as long as it is configured to update the learning model 84C using a method belonging to the field of artificial intelligence. The learning process for updating the learning model 84C is preferably performed by a GPU. The learning algorithm may use a neural network. The learning algorithm may use a recurrent neural network.

[0106] An example of the learning model 84C of the artificial intelligence processing unit 74C includes an input layer, an intermediate layer, and an output layer. Input information is input to the input layer. The learning model 84C is pre-trained to output output information from the output layer when information is input to the input layer. The intermediate layer learns the relationship between the input information input to the input layer and the output information output by the output layer by using teacher data. The learning model 84C of the artificial intelligence processing unit 74C may be configured in the same manner as the learning model 84A of the artificial intelligence processing unit 74A shown in FIG. 3, for example, except that the teacher data is different. The artificial intelligence processing unit 74C may be configured integrally with the artificial intelligence processing unit 74A. In this case, the artificial intelligence processing unit 74A includes a learning model for estimating slipperiness from the forward image F.

[0107] For example, the learning model 84C is configured to be updatable by the external device 92. For example, when the learning model 84C is updatable by the external device 92, the numbers of the convolutional layers, the pooling layers, and the fully connected layers in the intermediate layers can be updated. The relationship between the input information input to the input layer on which the intermediate layer learns and the output information output by the output layer can be updated.

[0108] The intermediate layer learns the relationship between the input information input to the input layer and the output information output by the output layer by using the teacher data. In the case of the artificial intelligence processing unit 74C, the input information is at least one of land information, obstacles, and information about the rider. In the case of the artificial intelligence processing unit 74C, the output information is slipperiness. In layersTherefore, the teacher data used includes information on at least one of the land information, the obstacle, and the information on the rider, and information on slipperiness. For example, the information on slipperiness is information corresponding to the slipperiness of the human-powered vehicle 10 on a running path corresponding to the land information and the obstacle. For example, the information corresponding to the slipperiness of the human-powered vehicle 10 on a running path corresponding to the land information and the obstacle is information corresponding to the probability or slip ratio of the human-powered vehicle 10 slipping when the rider passes through the first plane P. For example, the information corresponding to the slipperiness of the human-powered vehicle 10 on a running path corresponding to the land information and the obstacle may include a level of slipperiness. For example, the level of slipperiness includes a level at which slipperiness is unlikely to occur, a level at which slipperiness is likely to occur and corresponds to a first slip ratio, and a level at which slipperiness is likely to occur and corresponds to a second slip ratio greater than the first slip ratio.

[0109] The artificial intelligence processing unit 74C may be configured to output the slipperiness as if the terrain information of the land information was given as input information when the terrain information is not given as input information. In this case, the artificial intelligence processing unit 74C outputs the slipperiness as if the terrain information was given as flat.

[0110] The artificial intelligence processing unit 74C receives the land information as input information. Surface information If not given, Surface information In this case, the artificial intelligence processing unit 74C may be configured to output the slipperiness as if the following had been given: Surface information The slipperiness is output as given flat soil.

[0111] The artificial intelligence processing unit 74C may be configured to output the slipperiness as if an obstacle were given when no obstacle was given as input information. In this case, the artificial intelligence processing unit 74C outputs the slipperiness as if information that there is no obstacle was given.

[0112] The artificial intelligence processing unit 74C may be configured to output the slipperiness as if information about a rider was given when information about a rider was not given as input information. In this case, the artificial intelligence processing unit 74C outputs the slipperiness as if information about a predetermined rider was given.

[0113] The process of estimating slipperiness by the control unit 62 will be described with reference to the flowchart of Fig. 11. For example, when power is supplied to the control unit 62, the control unit 62 starts the process and proceeds to step S31 of the flowchart shown in Fig. 11. When the flowchart of Fig. 11 ends, the control unit 62 repeats the process from step S31 after a predetermined period, for example, until the supply of power is stopped.

[0114] In step S31, the control unit 62 determines whether the first plane estimation unit 72A has estimated at least one of the land information and the obstacle. If the first plane estimation unit 72A has estimated at least one of the land information and the obstacle, the control unit 62 proceeds to step S32. If the first plane estimation unit 72A has not estimated at least one of the land information and the obstacle, the control unit 62 ends the process.

[0115] In step S32, the control unit 62 estimates the slipperiness and ends the process. For example, the process of step S32 is executed by the artificial intelligence processing unit 74C.

[0116] When the artificial intelligence processing unit 74A is configured integrally with the artificial intelligence processing unit 74C, the process of step S31 may be omitted. In this case, when the process of step S13 in FIG. 9 is completed, the process may proceed to step S32.

[0117] For example, the control unit 62 is configured to control the motorized device 40 in response to at least one of the estimated land information and the obstacle. For example, the control unit 62 is configured to control the motorized device 40 in response to at least one of the estimated land information and the distance to the obstacle.

[0118] When the motorized device 40 includes the notification unit 42, for example, the control unit 62 is configured to control the notification unit 42 to notify information regarding at least one of land information and obstacles. For example, the control unit 62 controls the notification unit 42 to notify information regarding land information. The control unit 62 may also control the notification unit 42 to notify the shape of the terrain according to the terrain information. The control unit 62 Surface information The control unit 62 may control the notification unit 42 to notify the state of the ground surface according to the obstacle type.

[0119] For example, the control unit 62 is configured to control the motorized device 40 in accordance with the estimated passing difficulty level. For example, the control unit 62 is configured to control the notification unit 42 to notify information related to the estimated passing difficulty level.

[0120] For example, when the notification unit 42 includes a display unit, the notification unit 42 causes the display unit to display notification information corresponding to the passing difficulty level. For example, when the notification unit 42 includes a sound output unit, the notification unit 42 causes the sound output unit to output notification information corresponding to the passing difficulty level. For example, when the notification unit 42 includes a vibration unit, the control unit 62 causes the vibration unit to output notification information corresponding to the passing difficulty level. For example, the control unit 62 may be configured to communicate notification information corresponding to the passing difficulty level to the notification unit 42. The notification unit 42 may be configured to store notification information corresponding to the passing difficulty level in advance.

[0121] When the motorized device 40 includes the notification unit 42, for example, the control unit 62 is configured to control the notification unit 42 to notify information related to the land information and the distance to at least one of the obstacles. For example, the control unit 62 may be configured to control the notification unit 42 in accordance with the distance D to the first plane P when it is estimated that the passage difficulty on the first plane P is high. For example, the control unit 62 may A human-powered vehicle 10 Estimated places with high passage difficulty To When the object approaches, the notification unit 42 may be controlled to issue a notification.

[0122] A process in which the control unit 62 controls the notification unit 42 will be described with reference to the flowchart of Fig. 12. For example, when power is supplied to the control unit 62, the control unit 62 starts the process and proceeds to step S41 of the flowchart shown in Fig. 12. When the flowchart of Fig. 12 ends, the control unit 62 repeats the process from step S41 after a predetermined period, for example, until the supply of power is stopped.

[0123] In step S41, the control unit 62 determines whether or not information on a suspected obstacle has been acquired. The control unit 62 acquires, for example, information on a suspected obstacle estimated by the first plane estimation unit 72A. If the control unit 62 acquires information on a suspected obstacle, the control unit 62 proceeds to step S42. If the control unit 62 does not acquire information on a suspected obstacle, the control unit 62 ends the process.

[0124] In step S42, the control unit 62 determines whether the suspected obstacle is an obstacle. For example, the first plane estimation unit 72A determines whether the suspected obstacle is an obstacle. If the suspected obstacle is an obstacle, the control unit 62 proceeds to step S43. If the suspected obstacle is not an obstacle, the control unit 62 ends the process. The control unit 62 may control the notification unit 42 to notify that the suspected obstacle is not an obstacle.

[0125] In step S43, the control unit 62 determines whether the obstacle is passable or not. For example, the passing difficulty estimation unit 72B estimates whether the obstacle is passable or not. The control unit 62 may determine whether the obstacle is passable or not based on information about the obstacle and information about the rider. The information about the rider includes at least one of information about the width of the handlebars 34, information about the position of the rider's head when the rider is on the human-powered vehicle 10, information about the length of the crank 12, and information about the width of the human-powered vehicle 10. For example, 10 human-powered vehiclesWhen passing between obstacles, the control unit 62 compares the width between the obstacles with the width of the handlebar 34 to determine whether the obstacle can be passed through. If the control unit 62 determines that the obstacle can be passed through, the process proceeds to step S44. If the control unit 62 determines that the obstacle cannot be passed through, the process proceeds to step S45. 47 The control unit 62 may store information about impassable obstacles in advance. In this case, if the obstacle is an impassable obstacle, the control unit 62 proceeds to step S47.

[0126] In step S44, the control unit 62 determines whether the obstacle is easy to pass through. For example, the passing difficulty estimation unit 72B estimates whether the obstacle is easy to pass through. In this case, the control unit 62 may compare a threshold value for determining that the obstacle is easy to pass through with a parameter related to the passing difficulty estimated by the passing difficulty estimation unit 72B to determine whether the obstacle is easy to pass through. For example, if the parameter related to the passing difficulty is lower than the threshold value for determining that the obstacle is easy to pass through, the control unit 62 determines that the obstacle is easy to pass through. The threshold value for determining that the obstacle is easy to pass through can be changed, for example, by the riding technique of the rider. The control unit 62 may change the threshold value for determining that the obstacle is easy to pass through depending on the number of times that the rider has been able to pass through obstacles of the same type as the obstacle to be passed through in the past. If the control unit 62 determines that the obstacle is easy to pass through, the control unit 62 proceeds to step S45.

[0127] In step S45, the control unit 62 controls the notification unit 42 to notify that the obstacle is passable, and ends the process. In step S44, if the obstacle is not easy to pass through, the control unit 62 proceeds to step S46. In step S46, the control unit 62 controls the notification unit 42 to notify that the obstacle is difficult to pass, and ends the process. In step S43, if the obstacle is not passable, the control unit 62 proceeds to step S47. In step S47, the control unit 62 controls the notification unit 42 to notify that the obstacle is impassable, and ends the process. In steps S45 to S47, the control unit 62 may further control the notification unit 42 to notify the type of obstacle.

[0128] When information about an obstacle is acquired in step S41, the control unit 62 may determine that information about a suspected obstacle is acquired, and proceed to step S42. The control unit 62 may determine whether or not information about an obstacle is acquired before at least one of the processes of steps S41, S42, and S43. In this case, the control unit 62 may proceed to step S43 when information about an obstacle is acquired. In this case, if the control unit 62 has not acquired information about an obstacle and the acquired suspected obstacle is not an obstacle, if the control unit 62 has not acquired information about an obstacle and has not acquired a suspected obstacle, the control unit 62 ends the process without proceeding to step S43.

[0129] A process in which the control unit 62 controls the notification unit 42 to notify information related to land information will be described with reference to the flowchart of Fig. 13. For example, when power is supplied to the control unit 62, the control unit 62 starts the process and proceeds to step S51 of the flowchart shown in Fig. 13. When the flowchart of Fig. 13 ends, the control unit 62 repeats the process from step S51 after a predetermined period, for example, until the supply of power is stopped.

[0130] In step S51, the control unit 62 determines whether or not the passing difficulty level has been acquired. For example, the control unit 62 acquires the passing difficulty level estimated by the passing difficulty level estimation unit 72B. If the control unit 62 acquires the passing difficulty level, the control unit 62 proceeds to step S52. If the control unit 62 does not acquire the passing difficulty level, the control unit 62 ends the process.

[0131] In step S52, the control unit 62 determines whether the passage difficulty level is passable or not. If the passage difficulty level is passable, the control unit 62 proceeds to step S53. If the passage difficulty level is not passable, the control unit 62 proceeds to step S56.

[0132] In step S53, the control unit 62 determines whether the passage difficulty level is "easy to pass through." If the passage difficulty level is "easy to pass through," the control unit 62 proceeds to step S54.

[0133] In step S54, the control unit 62 controls the notification unit 42 to notify that passage is possible, and ends the process. In step S53, if the passage difficulty level is not easy, the control unit 62 proceeds to step S55. In step S55, the control unit 62 controls the notification unit 42 to notify that passage is difficult, and ends the process. In step S52, if the passage difficulty level is not passable, the control unit 62 proceeds to step S56. In step S56, the control unit 62 controls the notification unit 42 to notify that passage is not possible, and ends the process.

[0134] For example, the control unit 62 is configured to control the motorized device 40 according to the slipperiness. If the motorized device 40 includes a motor 44, the control unit 62 is configured to control the motor 44 according to the slipperiness.

[0135] For example, the control unit 62 controls the motor 44 according to the slipperiness estimated by the slipperiness estimation unit 72C according to at least one of the land information and the obstacle. For example, the control unit 62 is configured to control the motor 44 so as to change the assist characteristics of the motor 44 according to the slipperiness of the human-powered vehicle 10. For example, the control unit 62 is configured to control the motor 44 so as to switch the operation mode of the motor 44 according to the slipperiness of the human-powered vehicle 10. For example, when the human-powered vehicle 10 is slippery, the control unit 62 controls the motor 44 according to the slipperiness. For example, when the human-powered vehicle 10 is slippery and therefore difficult to pass through the road with the current assist characteristics, the control unit 62 lowers at least one of the assist force and the assist ratio of the motor 44 according to the slipperiness. For example, when the human-powered vehicle 10 is slippery but passing through the road is not difficult with the current assist characteristics, the control unit 62 maintains the current assist characteristics of the motor 44 according to the slipperiness. For example, if the control unit 62 estimates that the area ahead is slippery and that the human-powered vehicle 10 is likely to slip in the driving direction in the area ahead with the current assist characteristics, it estimates that it will be difficult to pass through the road with the current assist characteristics. For example, when the human-powered vehicle 10 is likely to slip in the driving direction, this includes cases where it will be difficult to maintain traction if the human-powered vehicle 10 slips. For example, when the control unit 62 estimates that the area ahead is slippery and that the human-powered vehicle 10 is likely to slip laterally in the area ahead with the current assist characteristics, it estimates that it will be difficult to pass through the road with the current assist characteristics. For example, when the human-powered vehicle 10 is likely to slip laterally in the area ahead, this includes cases where there is a possibility that the human-powered vehicle 10 will skid sideways if it slips. For example, when the control unit 62 estimates that the human-powered vehicle 10 is slippery and that it will be difficult to pass through the road, it adjusts the motor 4 to a value that is appropriate for the degree of slipperiness. 4 For example, when the control unit 62 estimates that the human-powered vehicle 10 is slippery but that it is not difficult to pass through the road, the control unit 62 controls the motor 4 in accordance with the degree of slipperiness. 4The control unit 62 controls the motor 44 to maintain the current operation mode. When the operation mode of the motor 44 changes stepwise, the control unit 62 may change how many steps the operation mode of the motor 44 is changed by, depending on the parameter related to the slipperiness estimated by the slipperiness estimation unit 72C. When the operation mode of the motor 44 changes steplessly, the control unit 62 may change the amount of change in the operation mode of the motor 44, depending on the parameter related to the slipperiness estimated by the slipperiness estimation unit 72C.

[0136] For example, the control unit 62 is configured to estimate an acceleration request to the area ahead based on an assist characteristic corresponding to the slipperiness when the area ahead is slippery. For example, the control unit 62 estimates an acceleration request to the area ahead based on an assist characteristic corresponding to the slipperiness of the area ahead and the vehicle speed. The control unit 62 may estimate whether the acceleration request is high or low. The control unit 62 may estimate whether there is an acceleration request or not. A low acceleration request may include a case where there is no acceleration request. The control unit 62 may estimate the acceleration request as a numerical value. The control unit 62 but acceleration request of Estimation by numbers do In this case, for example, the acceleration request is represented by acceleration. For example, when the acceleration required to move to the forward area is equal to or greater than a predetermined acceleration, the control unit 62 may determine that the acceleration request is high or that an acceleration request is present.

[0137] For example, the control unit 62 is configured to estimate that the acceleration requirement up to the front area is high when it is estimated that the vehicle speed in the front area will be low and it will be difficult for the human-powered vehicle 10 to travel with the assist characteristics according to the slipperiness of the front area. For example, the control unit 62 is configured to estimate that the acceleration requirement up to the front area is low when it is estimated that the vehicle speed in the front area will be maintained and it will not ... It was estimated thatIn response to the acceleration request, the control unit 62 controls to change the assist characteristic of the motor 44 in the area up to the intrusion of the human-powered vehicle 10 into the area ahead. For example, in response to the acceleration request, the control unit 62 increases at least one of the assist force and the assist ratio of the motor 44 in the area up to the intrusion of the human-powered vehicle 10 into the area ahead. For example, when the acceleration request is high, the control unit 62 increases at least one of the assist force and the assist ratio of the motor 44 in the area up to the intrusion of the human-powered vehicle 10 into the area ahead. For example, the control unit 62 is configured to estimate the acceleration request up to the area ahead in response to at least one of the land information and the obstacles of the area ahead. For example, the control unit 62 is configured to estimate the level of the acceleration request up to the area ahead in response to the road surface gradient of the area ahead. For example, when the road surface gradient of the area ahead is uphill, the control unit 62 estimates that it is difficult for the human-powered vehicle 10 to travel in the area ahead and that the acceleration request up to the area ahead is high. For example, the control unit 62 estimates that the acceleration requirement to the area ahead is high when at least one of the assist force and the assist ratio corresponding to the road surface gradient of the area ahead is greater than at least one of the assist force and the assist ratio corresponding to the slipperiness of the area ahead.

[0138] For example, the control unit 62 may determine that the vehicle speed is low in the forward area in the assist characteristic according to the degree of slipperiness. 10 human-powered vehiclesWhen it is estimated that it will be difficult to travel, the control unit 62 increases at least one of the assist force and the assist ratio of the motor 44 in the region up to the intrusion of the human-powered vehicle 10 into the region ahead. For example, when the control unit 62 decreases at least one of the assist force and the assist ratio of the motor 44 in response to the slipperiness, and when it is estimated that the vehicle speed will be slow in the region ahead with the decreased assist force and at least one of the assist ratios, making it difficult for the human-powered vehicle 10 to travel, the control unit 62 maintains or increases at least one of the assist force and the assist ratio of the motor 44 in the region up to the intrusion of the human-powered vehicle 10 into the region ahead. For example, when the control unit 62 maintains the assist characteristics of the motor 44 in response to the slipperiness, and when it is estimated that the vehicle speed will be slow in the region ahead with the maintained assist characteristics, making it difficult for the human-powered vehicle 10 to travel, the control unit 62 increases at least one of the assist force and the assist ratio of the motor 44 in the region up to the intrusion of the human-powered vehicle 10 into the region ahead.

[0139] The process of the control unit 62 controlling the motor 44 will be described with reference to the flowchart of Fig. 14. For example, when power is supplied to the control unit 62, the control unit 62 starts the process and proceeds to step S61 of the flowchart shown in Fig. 14. When the flowchart of Fig. 14 ends, the control unit 62 repeats the process from step S61 after a predetermined period, for example, until the supply of power is stopped.

[0140] In step S61, the control unit 62 determines whether or not information on at least one of land information and obstacles has been acquired. The control unit 62 acquires, for example, the land information estimated by the first plane estimation unit 72A and information on at least one of obstacles. If the control unit 62 acquires the land information and information on at least one of obstacles, the control unit 62 proceeds to step S62. If the control unit 62 does not acquire the land information and information on at least one of obstacles, the control unit 62 ends the process.

[0141] In step S62, the control unit 62 determines whether the area ahead is slippery or not. The area ahead is an area to which at least one of the land information and the obstacles in the first plane P estimated by the first plane estimation unit 72A corresponds. For example, the slipperiness estimation unit 72C estimates the slipperiness of the area ahead. For example, the control unit 62 determines that the area ahead is slippery when the slipperiness estimation unit 72C estimates that the area ahead is slippery. For example, the control unit 62 may compare a threshold value for determining that the area ahead is slippery with a parameter related to the slipperiness estimated by the slipperiness estimation unit 72C to determine whether the area ahead is slippery or not. When the area ahead is slippery, the control unit 62 proceeds to step S63. When the area ahead is not slippery, the control unit 62 ends the process.

[0142] In step S63, the control unit 62 determines whether the area ahead is difficult to pass through. For example, the area ahead is difficult to pass through when it is difficult for the human-powered vehicle 10 to pass through the area ahead due to the slipperiness of the area ahead. For example, the control unit 62 may compare a threshold value for determining that the area is slippery with a parameter related to the slipperiness estimated by the slipperiness estimation unit 72C to determine whether the area ahead is difficult to pass through. If the control unit 62 determines that the area ahead is difficult to pass through, the process proceeds to step S64.

[0143] In step S64, the control unit 62 determines whether or not the acceleration requirement up to the front area is high. For example, if the acceleration requirement up to the front area is high, the control unit 62 proceeds to step S65. When estimating whether or not there is an acceleration requirement, the control unit 62 may determine in step S64 whether or not there is an acceleration requirement up to the front area. In this case, the control unit 62 determines that the acceleration requirement is high when there is an acceleration requirement. In the case where the acceleration requirement is expressed by acceleration, the control unit 62 may determine in step S64 whether or not the acceleration is equal to or greater than a predetermined acceleration. In this case, the control unit 62 determines that the acceleration requirement is high when the acceleration is equal to or greater than the predetermined acceleration.

[0144] In step S65, the control unit 62 controls the motor 44 to increase the assist force and to reduce the assist force in the forward area, and ends the process. For example, the control unit 62 increases the assist force in the area up to the time when the human-powered vehicle 10 enters the current forward area. For example, the control unit 62 increases the assist force by switching the operation mode of the motor 44 to an operation mode having a higher assist ratio than the current assist ratio. For example, when the human-powered vehicle 10 enters the forward area, the control unit 62 reduces the assist force so that it is lower than the current assist force. For example, when the human-powered vehicle 10 enters the forward area, the control unit 62 reduces the assist force by switching the operation mode of the motor 44 to an operation mode having a lower assist ratio than the current assist ratio.

[0145] In step S64, if the acceleration requirement up to the forward area is not high, the control unit 62 proceeds to step S66. For example, if the acceleration requirement up to the forward area is low, the control unit 62 determines that the acceleration requirement up to the forward area is not high. In step S66, the control unit 62 controls the motor 44 to reduce the assist force in the forward area, and ends the process. For example, when the human-powered vehicle 10 enters the forward area, the control unit 62 reduces the assist force by switching the operation mode of the motor 44 to an operation mode having a lower assist ratio than the current assist ratio. If the current operation mode of the motor 44 is the operation mode having the lowest assist ratio, the control unit 62 does not need to switch the operation mode.

[0146] In step S63, the front area is Difficult to passIf not, the control unit 62 proceeds to step S67. In step S67, the control unit 62 determines whether or not the acceleration request to the front area is high. For example, if the acceleration request to the front area is high, the control unit 62 proceeds to step S68. When estimating whether or not there is an acceleration request, the control unit 62 may determine in step S67 whether or not there is an acceleration request to the front area. In this case, the control unit 62 determines that the acceleration request is high when there is an acceleration request. When the acceleration request is expressed by acceleration, the control unit 62 may determine in step S67 whether or not the acceleration is equal to or greater than a predetermined acceleration. In this case, the control unit 62 determines that the acceleration request is high when the acceleration is equal to or greater than the predetermined acceleration.

[0147] In step S68, the control unit 62 increases the assist force and controls the motor 44 to reduce the assist force to the current assist force in the forward area, and ends the process. In this case, for example, the current assist force is the assist force at the time when the process of the flowchart in FIG. 14 is started. For example, the control unit 62 increases the assist force in the area up to the current area ahead. For example, the control unit 62 increases the assist force by switching the operation mode of the motor 44 to an operation mode having a higher assist ratio than the current assist ratio. For example, when the human-powered vehicle 10 enters the forward area, the control unit 62 reduces the assist force to the current assist force.

[0148] In step S67, if the acceleration requirement to the forward area is not high, the control unit 62 proceeds to step S69. In step S69, the control unit 62 controls the motor 44 to maintain the current assist force in the forward area, and ends the process. In this case, for example, the current assist force is the assist force at the time when the process of the flowchart in FIG. 14 is started.

[0149] When the electric device 40 includes the electric brake 46, the control unit 62 is configured to control the electric brake 46. For example, the control unit 62 is configured to control the electric brake 46 according to the slipperiness. For example, the control unit 62 controls the electric brake 46 according to the slipperiness estimated by the slipperiness estimation unit 72C according to at least one of the land information and the obstacles. For example, when the ratio of the braking force to the operation amount of the brake lever 46A is lowered, the braking force of the electric brake 46 is lowered when the operation amount of the brake lever 46A is the same. For example, when the ratio of the braking force to the operation amount of the brake lever 46A is increased, the braking force of the electric brake 46 is higher when the operation amount of the brake lever 46A is the same.

[0150] For example, the control unit 62 is configured to control at least one of the front brake 46F and the rear brake 46R according to the slipperiness. For example, the control unit 62 is configured to control at least one of the front brake 46F and the rear brake 46R so as to switch the operation mode of at least one of the front brake 46F and the rear brake 46R according to the slipperiness of the human-powered vehicle 10. For example, when the human-powered vehicle 10 is slippery, the control unit 62 controls the electric brake 46 according to the slipperiness. For example, when the human-powered vehicle 10 is slippery and therefore difficult to pass through the road with the current braking force, the control unit 62 reduces the braking force of the electric brake 46 according to the slipperiness. For example, when the human-powered vehicle 10 is slippery but it is not difficult to pass through the road with the current braking force, the control unit 62 maintains the current braking force of the electric brake 46 according to the slipperiness. For example, if the area ahead is slippery and the human-powered vehicle 10 is likely to slip in the travel direction in the area ahead with the current braking force, the control unit 62 estimates that it will be difficult to pass through the road with the current braking force. For example, cases where the human-powered vehicle 10 is likely to slip in the travel direction include cases where it will be difficult to sufficiently decelerate if the human-powered vehicle 10 slips. For example, if the area ahead is slippery and the human-powered vehicle 10 is likely to slip laterally in the area ahead with the current braking force, the control unit 62 estimates that it will be difficult to pass through the road with the current braking force. For example, cases where the human-powered vehicle 10 is likely to slip laterally include cases where there is a possibility that the human-powered vehicle 10 will skid sideways if it skids. For example, if the control unit 62 estimates that the human-powered vehicle 10 is slippery and that it will be difficult to pass through the road, the control unit 62 applies the electric brakes 4 according to the degree of slipperiness. 6The control unit 62 controls the operation mode in which the ratio of the braking force to the operation amount of the brake lever 46A is low. For example, when the control unit 62 estimates that the human-powered vehicle 10 is slippery but the travel path is not difficult, the control unit 62 controls the operation mode of the electric brake 46 to be maintained at the current operation mode according to the slipperiness. The control unit 62 may determine the operation mode to be changed according to the parameter related to the slipperiness estimated by the slipperiness estimation unit 72C. When the ratio of the braking force to the operation amount of the brake lever 46A can be changed continuously, the control unit 62 may change the ratio of the braking force to the operation amount of the brake lever 46A according to the parameter related to the slipperiness estimated by the slipperiness estimation unit 72C.

[0151] For example, the control unit 62 is configured to estimate a deceleration requirement to reach the area ahead based on a braking force corresponding to the slipperiness of the area ahead when the area ahead is slippery. For example, the control unit 62 estimates a deceleration requirement to reach the area ahead based on a braking force corresponding to the slipperiness of the area ahead and the vehicle speed. The control unit 62 may estimate whether the deceleration requirement is high or low. The control unit 62 may estimate whether there is a deceleration requirement or not. A case where the deceleration requirement is low may include a case where there is no deceleration requirement. The control unit 62 may estimate the deceleration requirement as a numerical value. The control unit 62 but deceleration request of Estimation by numbers do In this case, for example, the deceleration request is represented by a deceleration rate. For example, when the deceleration rate required until the vehicle moves to the forward area is equal to or greater than a predetermined deceleration rate, the control unit 62 may determine that the deceleration request is high or that a deceleration request is present.

[0152] For example, when it is estimated that the vehicle speed will be high in the area ahead with a braking force according to the slipperiness, making it difficult for the human-powered vehicle 10 to travel, the control unit 62 is configured to estimate that the deceleration requirement up to the area ahead is high. For example, when it is estimated that the vehicle speed will be maintained in the area ahead with a braking force according to the slipperiness, making it difficult for the human-powered vehicle 10 to travel, the control unit 62 is configured to estimate that the deceleration requirement up to the area ahead is low. For example, when the area ahead is slippery, the control unit 62 is configured to estimate that the deceleration requirement up to the area ahead is low based on the braking force according to the slipperiness. It was estimated that The control unit 62 controls the braking force of the electric brake 46 in the area up to the area ahead of the human-powered vehicle 10, so as to change it in accordance with the level of the deceleration request. For example, the control unit 62 increases the braking force of the electric brake 46 in the area up to the area ahead of the human-powered vehicle 10, in accordance with the deceleration request. For example, the control unit 62 is configured to estimate the deceleration request up to the area ahead of the human-powered vehicle 10 in accordance with at least one of the land information and the obstacles of the area ahead of the human-powered vehicle 10. For example, the control unit 62 is configured to estimate the deceleration request up to the area ahead of the human-powered vehicle 10 in accordance with the road surface gradient of the area ahead of the human-powered vehicle 10. For example, when the road surface gradient of the area ahead of the human-powered vehicle 10 is a downhill slope, the control unit 62 estimates that it is difficult for the human-powered vehicle 10 to travel in the area ahead of the human-powered vehicle 10, and that the deceleration request up to the area ahead of the human-powered vehicle 10 is high. For example, when the braking force corresponding to the road surface gradient of the area ahead of the human-powered vehicle 10 is higher than the braking force corresponding to the slipperiness of the area ahead of the human-powered vehicle 10, the control unit 62 estimates that the deceleration request up to the area ahead of the human-powered vehicle 10 is high. When the area ahead of the human-powered vehicle 10 is in front of at least one of a curve, an obstacle, and a wall, the control unit 62 may estimate that the deceleration request up to the area ahead of the human-powered vehicle 10 is high.

[0153] For example, when it is estimated that with a braking force according to the slipperiness, the vehicle speed will be high in the forward area and it will be difficult for the human-powered vehicle 10 to travel, the control unit 62 increases the braking force of the electric brake 46 in the area up to the intrusion into the forward area. For example, when the control unit 62 decreases the braking force of the electric brake 46 in accordance with the slipperiness, and when it is estimated that with the decreased braking force, the vehicle speed will be high in the forward area and it will be difficult for the human-powered vehicle 10 to travel, the control unit 62 maintains or increases the braking force of the electric brake 46 in the area up to the intrusion into the forward area. For example, when the control unit 62 maintains the braking force of the electric brake 46 in accordance with the slipperiness, and when it is estimated that with the maintained braking force, the vehicle speed will be high in the forward area and it will be difficult for the human-powered vehicle 10 to travel, the control unit 62 increases the braking force of the electric brake 46 in the area up to the intrusion into the forward area.

[0154] The process of the control unit 62 controlling the electric brake 46 will be described with reference to the flowchart of Fig. 15. For example, when power is supplied to the control unit 62, the control unit 62 starts the process and proceeds to step S71 of the flowchart shown in Fig. 15. When the flowchart of Fig. 15 ends, the control unit 62 repeats the process from step S71 after a predetermined period, for example, until the supply of power is stopped.

[0155] In step S71, the control unit 62 determines whether or not information on at least one of land information and obstacles has been acquired. The control unit 62 acquires, for example, the land information estimated by the first plane estimation unit 72A and information on at least one of obstacles. If the control unit 62 determines that the land information and information on at least one of obstacles have been acquired, the control unit 62 proceeds to step S72. If the control unit 62 determines that the land information and information on at least one of obstacles have not been acquired, the control unit 62 ends the process.

[0156] In step S72, the control unit 62 determines whether the area ahead is slippery or not. The control unit 62 determines whether the area ahead is slippery or not, for example, by a process similar to step S62 in Fig. 14. If the area ahead is slippery, the control unit 62 proceeds to step S73. If the area ahead is not slippery, the control unit 62 ends the process.

[0157] In step S73, the control unit 62 determines whether the area ahead is difficult to pass through. For example, the control unit 62 determines whether the area ahead is difficult to pass through by the same process as in step S63 of FIG. Difficulty passing If the control unit 62 determines that the area ahead is difficult to pass through, the process proceeds to step S74.

[0158] In step S74, the control unit 62 determines whether or not the deceleration requirement up to the front area is high. For example, if the deceleration requirement up to the front area is high, the control unit 62 proceeds to step S75. When estimating whether or not there is a deceleration requirement, the control unit 62 may determine in step S74 whether or not there is a deceleration requirement up to the front area. In this case, the control unit 62 determines that the deceleration requirement is high when there is a deceleration requirement. In the case where the deceleration requirement is expressed by deceleration, the control unit 62 may determine in step S74 whether or not the deceleration is equal to or greater than a predetermined deceleration. In this case, the control unit 62 determines that the deceleration requirement is high when the deceleration is equal to or greater than the predetermined deceleration.

[0159] In step S75, the control unit 62 controls the electric brake 46 to increase the braking force and reduce the braking force in the forward area, and then ends the process. For example, the control unit 62 increases the braking force in the area up to the current area ahead. For example, the control unit 62 increases the braking force by switching the operation mode of the electric brake 46 to an operation mode with a braking force higher than the current braking force. For example, when the human-powered vehicle 10 enters the forward area, the control unit 62 reduces the braking force so that it is lower than the current braking force. For example, when the human-powered vehicle 10 enters the forward area, the control unit 62 controls the electric brake 46 to increase the braking force in the area ahead. 6The operation mode is switched to one in which the braking force is lower than the current braking force, and the operation mode of the electric brake 46 is controlled in a mode in which the ratio of the braking force to the operation amount of the brake lever 46A is low.

[0160] In step S74, if the deceleration requirement up to the front area is not high, the control unit 62 proceeds to step S76. For example, if the deceleration requirement up to the front area is low, the control unit 62 determines that the deceleration requirement up to the front area is not high. In step S76, the control unit 62 controls the electric brake 46 to reduce the braking force in the front area, and ends the process. For example, the control unit 62 reduces the braking force by switching the operation mode of the electric brake 46 to an operation mode in which the ratio of the braking force to the operation amount of the brake lever 46A is lower than the current ratio of the braking force to the operation amount of the brake lever 46A. In the case where the current operation mode of the electric brake 46 is the operation mode in which the ratio of the braking force to the operation amount of the brake lever 46A is the lowest, the control unit 62 does not need to switch the operation mode.

[0161] In step S73, the front area is Difficult to pass If not, the control unit 62 proceeds to step S77. In step S77, the control unit 62 determines whether or not the deceleration requirement up to the front area is high. For example, if the control unit 62 determines that the deceleration requirement up to the front area is high, the control unit 62 proceeds to step S78. When estimating whether or not there is a deceleration requirement, the control unit 62 may determine in step S77 whether or not there is a deceleration requirement up to the front area. In this case, the control unit 62 determines that the deceleration requirement is high when there is a deceleration requirement. In the case where the deceleration requirement is expressed by deceleration, the control unit 62 may determine in step S77 whether or not the deceleration is equal to or greater than a predetermined deceleration. In this case, the control unit 62 determines that the deceleration requirement is high when the deceleration is equal to or greater than the predetermined deceleration.

[0162] In step S78, the control unit 62 increases the braking force and controls the electric brake 46 to reduce the braking force to the current braking force in the forward area, and ends the process. In this case, for example, the current braking force is the braking force at the time when the process of the flowchart in FIG. 15 is started. For example, the control unit 62 increases the braking force in the area up to when the human-powered vehicle 10 enters the current forward area. For example, the control unit 62 increases the braking force by switching the operation mode of the electric brake 46 to an operation mode with a braking force higher than the current braking force. For example, when the human-powered vehicle 10 enters the forward area, the control unit 62 reduces the braking force to the current braking force.

[0163] In step S77, if the deceleration requirement to the forward area is not high, the control unit 62 proceeds to step S79. In step S79, the control unit 62 controls the electric brake 46 to maintain the current braking force in the forward area, and ends the process. In this case, for example, the current braking force is the braking force at the time when the process of the flowchart in FIG. 15 is started.

[0164] For example, the control unit 62 is configured to control the motor 44 in response to at least one of the land information and the obstacle. For example, the control unit 62 is configured to control the motor 44 in response to the land information. For example, the control unit 62 is configured to control the motor 44 in response to the estimated road surface gradient. For example, the control unit 62 is configured to change the assist characteristic of the motor 44 in response to at least one of the land information and the obstacle. For example, the control unit 62 changes at least one of the assist force and the assist ratio of the motor 44 in response to at least one of the land information and the obstacle. For example, the control unit 62 changes at least one of the assist force and the assist ratio by switching the operation mode of the motor 44 in response to at least one of the land information and the obstacle. For example, the control unit 62 controls the motor 44 to increase at least one of the assist force and the assist ratio when the estimated road surface gradient is an uphill slope. The control unit 62 may control the motor 44 to increase at least one of the assist force and the assist ratio when the magnitude of the road surface gradient is equal to or greater than a predetermined value. The control unit 62 may control the motor 44 to change at least one of the increase amounts of the assist force and the assist ratio according to the magnitude of the road surface gradient. For example, the control unit 62 is configured to control the motor 44 according to an obstacle. For example, the control unit 62 is configured to control the motor 44 according to the type of the estimated obstacle. For example, the control unit 62 is configured to control the motor 44 so as not to assist when the estimated obstacle cannot be passed through.

[0165] A process in which the control unit 62 controls the motor 44 in response to at least one of the land information and the obstacles will be described with reference to the flowchart of Fig. 16. For example, when power is supplied to the control unit 62, the control unit 62 starts the process and proceeds to step S81 of the flowchart shown in Fig. 16. When the flowchart of Fig. 16 ends, the control unit 62 repeats the process from step S81 after a predetermined period, for example, until the supply of power is stopped.

[0166] In step S81, the control unit 62 determines whether or not information on at least one of land information and obstacles has been acquired. The control unit 62 acquires, for example, the land information estimated by the first plane estimation unit 72A and information on at least one of obstacles. If the control unit 62 acquires the land information and information on at least one of obstacles, the control unit 62 proceeds to step S82. If the control unit 62 does not acquire the land information and information on at least one of obstacles, the control unit 62 ends the process.

[0167] In step S82, the control unit 62 determines whether or not to change the assist characteristics. For example, the control unit 62 determines to change the assist characteristics when the road surface gradient in the area ahead is uphill. For example, the control unit 62 determines to change the assist characteristics to increase at least one of the assist force and the assist ratio when the road surface gradient in the area ahead is uphill. The control unit 62 may determine to change the assist characteristics to increase at least one of the assist force and the assist ratio when the uphill road surface gradient in the area ahead is equal to or greater than a predetermined value. The control unit 62 determines to change the assist characteristics to increase at least one of the assist force and the assist ratio when the uphill road surface gradient in the area ahead is equal to or greater than a predetermined value and An upward slope continues for a specified distance or more In this case, the control unit 62 may determine to change the assist characteristics so as to increase at least one of the assist force and the assist ratio. For example, when there is an obstacle in the forward area, the control unit 62 determines to change the assist characteristics. For example, when there is no obstacle in the forward area, the control unit 62 determines not to change the assist characteristics. When the control unit 62 does not change the assist characteristics, it ends the process.

[0168] When the control unit 62 changes the assist characteristics, the process proceeds to step S83. In step S83, the control unit 62 controls the motor 44 to change the assist characteristics according to the forward area, and ends the process. The control unit 62 changes at least one of the assist force and the assist ratio, for example, by switching the operation mode of the motor 44.

[0169] <Modification> The description of the embodiments is merely an example of a form that the control device according to the present disclosure may take, and is not intended to limit the form. The control device according to the present disclosure may take, for example, a modified version of the embodiment shown below, or a form that combines at least two mutually non-contradictory modified versions. In the following modified versions, parts that are common to the embodiment will be given the same reference numerals as the embodiment, and descriptions thereof will be omitted.

[0170] The control unit 62 may be configured to be able to select the first mode depending on at least one of the land information and obstacles. The control unit 62 is configured to select the first mode when it is determined that the driving path is off-road depending on at least one of the land information and obstacles. The control unit 62 determines that the driving path is off-road when the terrain information is not flat. The control unit 62 determines that the driving path is off-road when the ground surface information is in a state in which tree roots and rocks are exposed on the driving path.

[0171] The control unit 62 may be configured to select the first mode when the road is off-road. The control unit 62 determines whether the road is off-road or not, for example, according to the output of the road detection unit. For example, the road detection unit is configured to be able to detect at least one of the driving environment and driving state of the human-powered vehicle 10. For example, the road detection unit includes at least one of the imaging device 48, the human-powered driving force detection unit 52, the crank rotation sensor 54, the vehicle speed sensor 56, the tilt sensor 58, and a GPS receiver.

[0172] The control unit 62 may be configured not to operate the imaging device 48 when the first mode is not selected. The imaging device 48 may be configured to be switchable between on and off in response to an operation of the operation unit 50.

[0173] The control unit 62 does not necessarily have to have any mode other than the first mode. In this case, the control unit 62 controls the electric device 40 in the first mode regardless of whether the traveling road is off-road or not.

[0174] In the process of the flowchart of Fig. 12, the control unit 62 may be configured not to perform the process of step S43. In this case, if the suspected obstacle is an obstacle in step S42, the control unit 62 proceeds to step S44.

[0175] In the control of the flowchart of Fig. 13, the control unit 62 may be configured not to perform the control of step S52. In this case, when the control unit 62 acquires information on land information in step S51, the control unit 62 proceeds to step S53.

[0176] The control unit 62 may estimate the change in the travel path based on a plurality of planes. For example, the control unit 62 is configured to be able to estimate the cross section of each of the plurality of planes. The control unit 62 may be configured to control the electric device 40 according to the estimated change in the travel path. For example, the plurality of planes includes a first plane P and a second plane. The first plane P and the second plane have different distances from the human-powered vehicle 10 to each plane. For example, the distance from the human-powered vehicle 10 to the second plane is greater than the distance D from the human-powered vehicle 10 to the first plane P. If the first plane P is a valley and the second plane is a wall, the control unit 62 estimates that the travel path in the second plane is a curve. If the first plane P is a valley and the second plane is a single bank, the control unit 62 estimates that the travel path in the second plane is a curve. The plurality of planes may include a third plane in addition to the first plane P and the second plane. The first plane P, the second plane, and the third plane have different distances from the human-powered vehicle 10 to each plane. The distance from the human-powered vehicle 10 to the third plane is greater than the distance from the human-powered vehicle 10 to the second plane. When the first plane P is a valley, the second plane is a slope traverse, and the third plane is a wall, the control unit 62 estimates that the road on the third plane is a curve.

[0177] The electric device 40 may include at least one of a gear shifter, an electric suspension, an electric adjustable seat post, and a display device, instead of or in addition to at least one of the alarm unit 42, the motor 44, and the electric brake 46. When the electric device 40 includes a gear shifter, the control unit 62 may be configured to change a gear ratio in response to at least one of the land information and an obstacle. When the electric device 40 includes an electric suspension, the control unit 62 may be configured to change a rebound force of the suspension and a corresponding control state in response to at least one of the land information and an obstacle. When the electric device 40 includes an electric adjustable seat post, the control unit 62 may be configured to change a height of the seat post 36 and a corresponding control state in response to at least one of the land information and an obstacle. When the electric device 40 includes a display device, the control unit 62 may be configured to change the display content in response to at least one of the land information and an obstacle.

[0178] The human-powered vehicle 10 may be configured to further include a laser device. The laser device is configured to detect a laser beam emitted from the human-powered vehicle 10 in the first plane P. Surface information The ground surface information on the first plane P detected by the laser device is, for example, small irregularities, sand, etc. that cannot be captured by the imaging device 48. The control unit 62 determines the slipperiness of the area ahead based on the slipperiness of the area ahead estimated by the slipperiness estimation unit 72C and the ground surface information detected by the laser device.

[0179] The term "at least one" as used herein means "one or more" of the desired options. As an example, the term "at least one" as used herein means "only one option" or "both of two options" if the number of options is two. As another example, the term "at least one" as used herein means "only one option" or "any combination of two or more options" if the number of options is three or more. [Explanation of symbols]

[0180] 10...human-powered vehicle, 40...electric device, 42...alarm unit, 44...motor, 46...electric brake, 48...imaging device, 50...operation unit, 60...control device, 62...control unit, 64A...first memory unit, 64B...second memory unit, 72A...first plane estimation unit, 72B...passing difficulty estimation unit, 72C...slipperiness estimation unit, F...forward image.

Claims

1. A control device for a human-powered vehicle, A control unit configured to control an electric device of the human-powered vehicle, The control unit is a first mode for driving the vehicle off-road, the first mode being configured to control the electric device; In the first mode, a three-dimensional model of a forward image of a road is created based on the forward image of the road captured by an imaging device; estimating, based on the three-dimensional model, a plane that intersects with a traveling direction of the human-powered vehicle and is located a predetermined distance forward from the human-powered vehicle, as a first plane; Estimating at least one of land information and obstacles in the first plane; A controller configured to control the powered device in response to the estimated terrain information and the at least one of the obstacles.

2. The control device according to claim 1 , wherein the control unit includes a passage difficulty estimating unit configured to estimate a passage difficulty level for the human-powered vehicle based on the land information and the at least one of the obstacles.

3. The control device according to claim 2 , wherein the passing difficulty level estimation unit is configured to estimate the passing difficulty level in accordance with information about a rider.

4. A control device for a human-powered vehicle, comprising: A control unit configured to control an electric device of the human-powered vehicle, The control unit is a first mode for driving the vehicle off-road, the first mode being configured to control the electric device; In the first mode, at least one of land information and obstacles is estimated according to a forward image of a roadway acquired by an imaging device, and the electric device is controlled according to the estimated at least one of the land information and the obstacles, the land information is on a first plane intersecting a traveling direction of the human-powered vehicle, the obstacle is in the first plane; the control unit includes a passage difficulty estimation unit configured to estimate a passage difficulty level for the human-powered vehicle based on the land information and at least one of the obstacles, The control device, wherein the passing difficulty estimation unit is configured to estimate the passing difficulty in accordance with information related to a rider.

5. The control device according to claim 3 or 4, wherein the control unit is configured to control the electrically-powered device in accordance with the estimated passage difficulty level.

6. The electrically-powered device includes an alarm unit, The control device according to claim 5 , wherein the control unit is configured to control the notification unit to notify the information related to the estimated passing difficulty level.

7. The electrically-powered device includes an alarm unit, The control device according to claim 1 , wherein the control unit is configured to control the notification unit to notify the land information and the information relating to at least one of the obstacles.

8. the at least one of the terrain information and the obstacle comprises the terrain information; The control device according to claim 1 , wherein the land information includes at least one of topographical information on the first plane and ground surface information on the first plane.

9. the at least one of the topographical information and the ground surface information includes the topographical information; A first storage unit that stores two-dimensional image information relating to the topographical information, The control device according to claim 8 , wherein the control unit is configured to estimate the terrain information by comparing the forward image with the image information.

10. A control device for a human-powered vehicle, comprising: A control unit configured to control an electric device of the human-powered vehicle, The control unit is a first mode for driving the vehicle off-road, the first mode being configured to control the electric device; In the first mode, at least one of land information and obstacles is estimated according to a forward image of a roadway acquired by an imaging device, and the electric device is controlled according to the estimated at least one of the land information and the obstacles, the land information is on a first plane intersecting a traveling direction of the human-powered vehicle, the obstacle is in the first plane; the at least one of the terrain information and the obstacle comprises the terrain information; The land information includes at least topographical information in the first plane, A control device, wherein the control unit is configured to estimate a cross-sectional view on the first plane based on the forward image, and to estimate the topographical information from the cross-sectional view.

11. Further comprising a first storage unit for storing two-dimensional image information, the image information includes a plurality of figures corresponding to the topographical information; The control device according to claim 10 , wherein the control unit is configured to estimate the topographical information by comparing the cross-sectional view with the plurality of figures.

12. The control device according to claim 1 , wherein the control unit comprises a first plane estimator configured to estimate the at least one of the land information and the obstacle from the forward image.

13. The control device of claim 12 , wherein the first plane estimator comprises an artificial intelligence processor.

14. The artificial intelligence processing unit is Identifying an object on the road based on the forward image; The control device of claim 13 , configured to estimate the at least one of the terrain information and the obstacles based on the identified object.

15. The control device according to claim 1 , wherein the first plane is perpendicular to the direction of travel.

16. The control device according to claim 1 , wherein the control unit is configured to control the electrically powered device depending on the estimated terrain information and a distance to the at least one of the obstacles.

17. Further comprising a second storage unit that stores the determination information, The control device according to any one of claims 1 to 16, wherein the control unit is configured, when detecting a suspected obstacle based on the forward image, to estimate, based on the determination information, whether or not the detected suspected obstacle corresponds to the obstacle.

18. The control device according to claim 1 , wherein the control unit includes a slipperiness estimation unit configured to estimate slipperiness of the human-powered vehicle according to the at least one of the land information and the obstacle.

19. The control device of claim 18 , wherein the controller is configured to control the powered device in response to the slipperiness.

20. the electric powered device includes a motor configured to provide propulsive force to the human powered vehicle; The control device of claim 19 , wherein the controller is configured to control the motor in response to the slipperiness.

21. the electric device includes an electric brake that brakes the human-powered vehicle, The control device according to claim 19 or 20, wherein the control unit is configured to control the electric brake depending on the slipperiness.

22. The control device according to claim 1 , wherein the control unit is configured to be able to select one of a plurality of modes including the first mode.

23. The control device according to claim 22 , wherein the control unit is configured to be able to select the first mode in response to an operation input to an operation unit.

Images