METHOD FOR CONTROLLING AN OBJECT OF A VEHICLE THAT IS ROTATING ABOUT AT LEAST ONE AXIS

Abstract

The invention relates to a method for controlling an object (100, 110, 210) of a vehicle (200) rotatable about at least one axis (x, y, z), comprising: Determining an object position and an initial orientation setting of the object (100, 110, 210); Receiving sensor-acquired measurement data over a specified period, representing a hand pose and hand position (x0, y0, z0) of a user's hand (120); Determining a first hand position (x0, y0, z0) relative to the object position and Estimating a first hand pose of hand (120) using the measurement data; If the estimation of the first hand pose has revealed that the first hand pose represents a grasping pose: Determine a second hand position (x1, y1, z1) in relation to the object position using the measurement data; Determining movement data of the hand (120) representing a lateral movement of the hand from the first hand position (x0, y0, z0) to the second hand position (x1, y1, z1); Moving the object (100, 110, 210) by means of an electromechanical drive (105, 115, 220) about at least one axis (x, y, z) from the first orientation setting to a second orientation setting using the determined movement data of the hand (120).

Description

[0001] The present invention relates to a method, particularly a computer-implemented method, for controlling a vehicle object rotatable about at least one axis. The invention further relates to a device, a motor vehicle, and a computer program configured to execute the method.

[0002] While classic human-machine interfaces (HMIs) are typically based on contact-based interaction between a user and a corresponding control element, such as a physical switch, touch-sensitive surface, or display, HMIs are now known that sensorially detect a gesture performed by a human user in free space without physical contact with an HMI device. This sensory detection of such gestures, also referred to as "free-space gestures," can be achieved, for example, using a suitable camera. Mathematical methods, particularly image recognition techniques, are then used to infer the intended user input from the sensorially captured data.

[0003] Particularly in the context of vehicle-related applications, such MMIs capable of recognizing free-space gestures can be used to input commands for operating the vehicle or a subsystem thereof. Furthermore, it is also possible that the free-space gestures relate to the vehicle's surroundings, such as pointing at an interesting external object visible from the vehicle, and the recognition of such a free-space gesture serves to provide input for a system that is to deliver information related to the object, or to cause the vehicle to react accordingly.

[0004] Gesture recognition systems are known for implementing such contactless MMIs. These systems employ calibrated 2D sensors to detect and track points along the contour of a user's hand—a hand pose—associated with specific features, particularly from above and the side. Based on the detected points, a pointing direction associated with the gesture performed in three-dimensional space can then be estimated. Such systems depend on the recognition of easily distinguishable features (points, especially reference points) of the human hand and require fixed and calibrated hardware, advantageously with two sensors. Furthermore, the computational effort for such gesture recognition, especially gesture tracking, is considerable.

[0005] The present invention is based on the objective of enabling simplified control, in particular with lower computational effort compared to gesture control, of an object of a vehicle that can be rotated about an axis using a hand movement.

[0006] The solution to this problem is achieved according to the teaching of the independent claims. Various embodiments and further developments of the invention are the subject of the dependent claims.

[0007] A first aspect of the solution relates to a method, particularly a computer-implemented method, for controlling an object rotatable about at least one axis, in particular a vehicle mirror, which preferably has two axes of rotation, of a vehicle, in particular a motor vehicle, comprising: (i) determining an object position and a first orientation setting of the object; (ii) receiving sensor-acquired measurement data over a predetermined period, representing a hand pose and hand position of a user's hand; (iii) determining a first hand position relative to the object position and estimating a first hand pose of the hand using the measurement data; (iv) if the estimation of the first hand pose shows that the first hand pose represents a grasping pose: (v) determining a second hand position relative to the object position using the measurement data;(vi) Determining hand motion data representing a lateral movement of the hand from the first hand position to the second hand position; (vii) Moving the object by means of an electromechanical drive about one of the axes from the first orientation setting to a second orientation setting using the determined hand motion data.;

[0008] Any terms used herein, such as "comprises," "includes," "includes," "features," "has," "with," or any other variant thereof, are intended to cover non-exclusive inclusion. For example, a method or apparatus that includes or features a list of elements is not necessarily limited to those elements but may include other elements not expressly listed or inherent in such method or apparatus.

[0009] Furthermore, unless explicitly stated otherwise, "or" refers to an inclusive "or" and not an exclusive "or". For example, a condition A or B is satisfied by one of the following: A is true (or present) and B is false (or not present), A is false (or not present) and B is true (or present), and both A and B are true (or present).

[0010] The terms "ein" or "eine," as used here, are defined as "one or more." The terms "ein anderer" and "ein Weitere," as well as any other variant thereof, are to be understood as "at least one more."

[0011] The term "plural", as used here, is to be understood in the sense of "two or more".

[0012] The terms "configured" or "set up" to perform a specific function (and their respective variations), as used here, mean that the device in question is already in a configuration or setting in which it can perform the function, or at least that it is adjustable—i.e., configurable—so that it can perform the function after appropriate adjustment. Configuration can be achieved, for example, by adjusting parameters of a process sequence or by using switches or similar devices to activate or deactivate functionalities or settings. In particular, the device can have several predefined configurations or operating modes, allowing configuration to be performed by selecting one of these configurations or operating modes.

[0013] The term "hand pose" as used in the invention refers in particular to the position of a human hand and the associated fingers of a user at any given time. In contrast to a gesture, especially a free-space gesture, which involves a movement that may contain a plurality of hand poses at different times, the hand pose is therefore static.

[0014] The term "image sensor," as used here, refers specifically to an electro-optical sensor, particularly one in a camera, capable of capturing a scene. Specifically, the image sensor can be configured to detect or measure electromagnetic signals and convert them into electrical signals. These sensors can be charge-coupled devices (CCDs), radar sensors, lidar sensors, or other types. In particular, the image sensor can be a 3D image sensor capable of capturing a scene in three spatial dimensions, thus enabling, in particular, the measurement of distances within the scene.Furthermore, such a sensor can also be configured to emit electromagnetic signals to an object and to detect the electromagnetic signals reflected back from that object, so that information about the object can be obtained from the emitted and reflected electromagnetic signals in a subsequent analysis. Such sensors are used in so-called TOF (Time-of-Flight) cameras.

[0015] The term "control unit," as used here, refers in particular to an electronic device that controls the operation of a vehicle system, especially by means of a processor, particularly a CPU. Specifically, the control unit may include a transmitter and receiver for sending and receiving wireless signals, such as electromagnetic signals, and / or wired signals, such as electrical signals, via cables. Such a control unit may, in particular, include a microprocessor for analyzing received and / or previously stored data and / or for initiating a control process.

[0016] The term "reference point" as used in the invention refers in particular to a point on a user's hand or on an object, defined by its position, especially its spatial coordinates, and by which the position of the hand or object can be specified. In particular, such a reference point can be a position centered on the palm of a hand or on the base of the object and / or at the center of gravity of the hand or object. In particular, the reference point can be located at the tip of a finger.

[0017] For the purposes of this invention, the term "object" refers in particular to a physical component of a vehicle, especially a motor vehicle, which is arranged on the vehicle and is partially movable such that its position can be adjusted by movement. In particular, the object may be a vehicle mirror whose orientation is changed by rotation about an axis. In particular, the object may also be ventilation slots in the interior of the vehicle, the direction of airflow into the interior of the vehicle can be adjusted by rotating the ventilation slots, whereby the rotation of the ventilation slots changes their orientation.

[0018] The method described in the first aspect enables the direct movement of a rotatable object around an axis by a hand movement, without touching the object. A lateral hand movement is converted into a rotational movement of the object around its axis, with the rotation being controlled by an electromechanical drive. This method allows for the rotational movement of the object to be controlled by a lateral hand movement with comparatively little effort, particularly in terms of computational effort and the hardware required for data acquisition, and especially allows for intuitive control. In particular, the hand pose can be estimated using an algorithm, especially a machine learning-based algorithm. Specifically, the detected hand pose can be compared with known hand poses, and the current hand pose can be estimated from this comparison.Furthermore, the position of the object within the vehicle interior can be determined by measuring the interior and ascertaining the positions of other objects and their relative positions. The object's position can then be retrieved from a database or determined using the method described above. The object's first and second alignment settings can be determined via the respective settings of the electromechanical drive.

[0019] Preferred embodiments of the method are described below, which, unless expressly excluded or technically impossible, can be combined with each other and with the other aspects described.

[0020] In some embodiments, the method further includes: (i) estimating a second hand pose using the measurement data; (ii) stopping the movement of the object when the estimation of the second hand pose indicates that the second hand pose represents a release from the gripping pose. This allows the object movement to be stopped using a single hand pose. This enables the user to initiate, move, and stop the object movement by releasing the gripping pose with one hand.

[0021] In some embodiments, the method further includes: (i) determining a hand reference point; (ii) using the determined hand reference point to determine the first hand position and the second hand position. This enables a more precise determination of the hand position. This, in turn, allows the determination of the hand's motion data and subsequently the movement of the object to be carried out with improved accuracy.

[0022] In some embodiments, the hand reference point is determined to be the center point of the user's palm, particularly the inner palm. This allows for intuitive movement of the vehicle mirror. For example, a user may be accustomed to manually adjusting the interior mirror by grasping it with their hand to rotate or adjust it. In this situation, the palm of the hand is centrally located opposite the interior mirror. Therefore, in the present method, where the center point of the palm, particularly the inner palm, is used as the hand reference point, the user can intuitively adjust the interior mirror's alignment with a comparable movement.

[0023] In some embodiments, the end of a finger, particularly a fingertip, especially the tip of an index finger, is used as the hand reference point. This allows for particularly precise control of the object, as the hand's movement data can be determined more accurately. This is because, firstly, a finger can naturally and intuitively perform a pointing function. Secondly, because a finger also has a small cross-sectional area, and therefore the pointing function or movement can be controlled more precisely by the user than by the entire hand.

[0024] In some embodiments, the method further comprises: (i) determining an object reference point of the object, in particular the center point of a base of the object; (ii) using the determined object reference point to determine the object position. This enables a more precise determination of the object position. This allows the hand position relative to the object position to be determined more accurately, which in turn allows for a more precise determination of the hand's movement data and thus more accurate movement of the object.

[0025] In some embodiments, a plurality of additional hand positions are determined in succession, and the motion data is determined using these additional hand positions. This allows for a more precise determination of the hand's motion data through the additionally determined plurality of hand positions. This, in turn, enables more precise movement of the object by the hand movement.

[0026] In some embodiments, the method further comprises: (i) estimating a third hand pose using the measurement data; (ii) wherein the third hand pose represents a pointing pose in the direction of an object of the vehicle, the estimation of the third hand pose occurring before the estimation of the first hand pose; (iii) determining the object toward which the pointing pose is directed; (iv) moving the object toward which the pointing pose is directed. This allows the user to intuitively and easily select an object using a hand pose, which can then be moved by changing the position of the hand.

[0027] In some embodiments, the estimation of the first hand pose is repeated at predetermined time intervals as long as the estimation of the first hand pose indicates that the first hand pose does not represent a grasping pose. This allows the process to continue automatically until a grasping pose has been estimated, rather than having to be completely restarted if no grasping pose has yet been estimated.

[0028] In some embodiments, the object is rotatable about three spatial axes, in particular about a center of rotation, and the method further comprises: (i) estimating a plurality of successive fourth-hand poses using the measurement data, wherein the plurality of the fourth-hand poses collectively represent a rotation gesture; (ii) moving the object taking into account the determined rotation gesture. This enables intuitive simultaneous rotation about multiple axes for an object rotatable about three spatial axes, such as an interior mirror.

[0029] A second aspect of the solution concerns a device for controlling an object, wherein the device is configured to carry out the procedure according to the first aspect.

[0030] In some embodiments, the device comprises: (i) an electromechanical drive mechanically coupled to the object, enabling the object to be rotated about an axis; (ii) an interior camera of the vehicle configured to sensorially acquire measurement data representing a hand pose and hand position of a user of the vehicle; (iii) a control unit configured to: (iii-1) determine an object position and an initial orientation setting of the object; (iii-2) determine an initial hand position relative to the object position and estimate an initial hand pose using the measurement data; (iii-3) if the estimation of the initial hand pose indicates that the initial hand pose represents a grasping pose: (iii-4) determine a second hand position relative to the object position using the sensorially acquired measurement data over a predetermined period;(iii-5) Determining hand motion data representing a lateral movement of the hand from the first hand position to the second hand position; (iii-6) Moving the object by means of an electromechanical drive about one of the axes from the first orientation setting to a second orientation setting using the hand motion data.;

[0031] A third aspect of the solution concerns a vehicle, in particular a motor vehicle, having a device according to the second aspect.

[0032] A fourth aspect of the solution concerns a computer program with instructions which, when executed on a device according to the second aspect, cause it to carry out the procedure according to the first aspect.

[0033] The computer program can be stored, in particular, on a non-volatile data carrier. Preferably, this is a data carrier in the form of an optical data carrier or a flash memory module. This can be advantageous if the computer program itself is to be handled independently of a processor platform on which the one or more programs are to be executed. In another implementation, the computer program can exist as a file on a data processing unit, in particular on a server, and be downloadable via a data connection, for example, the internet or a dedicated data connection, such as a proprietary or local network. Furthermore, the computer program can comprise a plurality of interacting individual program modules.

[0034] The device according to the second aspect of the invention can accordingly include a program memory in which the computer program is stored. Alternatively, the device can also be configured to access an external computer program, for example on one or more servers or other data processing units, via a communication connection, in particular to exchange data with it that is used during the execution of the method or computer program or represents outputs of the computer program.

[0035] The features and advantages explained in relation to the first aspect of the solution also apply to the other aspects described.

[0036] Further advantages, features and application possibilities will result from the following description of preferred embodiments in conjunction with the figures.

[0037] This shows Fig. 1A schematically a front view of a vehicle mirror and a hand pose of a user's hand; Fig. 1B schematically a side view of a vehicle mirror and a hand pose of a user's hand; Fig. 2. A schematic top view of a motor vehicle; and Fig. 3. A schematic flowchart to illustrate an embodiment of a method for controlling a vehicle mirror rotatable about an axis.

[0038] The same reference symbols are used throughout the figures for the same or corresponding elements.

[0039] In Fig. Figure 1A schematically shows a front view of a vehicle mirror 100, 110, in particular a left side mirror 100 or a right side mirror 110. The vehicle mirror 100, 110 has a substantially rectangular base, with the corners possibly being rounded. The vehicle mirror 100, 110 can be rotated about two axes x, y. This is indicated by the axes in the x-direction and in the y-direction. The point where the axes (x, y) intersect is referred to below as the rotation point RP. Possible rotations of the vehicle mirror 100, 110 are carried out automatically by an electromechanical drive 105, 115, in particular an electromechanical actuator, which is mechanically coupled to the respective side mirror 100, 110. In this arrangement, one electromechanical drive 105 is mechanically coupled to the left side mirror 100 and the electromechanical drive 115 is mechanically coupled to the right side mirror 110.Each of the electromechanical drives is designed to effect a rotation of the respective vehicle mirror 100, 110 around the x-axis and / or around the y-axis.

[0040] Furthermore, a hand pose of a user's hand 120 (not shown here) is depicted. The opposing arrows for hand 120 indicate that the thumb and index finger of hand 120 move towards each other, forming a grasping pose. Similarly, several fingers can form a grasping pose with the thumb. This grasping pose can trigger a coupling of the hand movement with a movement of the respective vehicle mirror 100, 110. Subsequently, the vehicle mirror 100, 110 can then be moved by the hand movement. The necessary device features for this are described in Fig. 2 described. The execution of a procedure for moving the vehicle mirror 100, 110 by means of a hand movement is described in the procedure according to Fig. 3 described.

[0041] In Fig. Figure 1B is a schematic side view of a vehicle mirror 100,110 according to Fig. Figure 1A shows this. Additionally, a virtual lever 130 is shown, illustrating that a hand movement is directly transferred to a movement of the vehicle mirror 100, 110. The hand is in hand position p0 (x0, y0, z0) at time t0 when hand 120 assumes a grasping pose. When hand 120 moves, it moves from position p0 to position p1 (x1, y1, z1). This is illustrated by the arrows, indicating that the movement can occur in two directions with respect to the y-axis. In the example shown, this movement represents a rotation of the vehicle mirror 100, 110 about the y-axis, which is effected via the virtual lever 130. This virtual lever 130 corresponds to a mathematical transformation from the hand movement to a movement of the vehicle mirror 100, 110. This will be explained in detail in Figure 1. Fig. 3 described.

[0042] In Fig. Figure 2 schematically shows a top view of a motor vehicle 200. The motor vehicle 200 has a left exterior mirror 100, a right exterior mirror 110, and an interior camera 240. As to Fig. As explained in Figure 1, the left exterior mirror 100 can be controlled by an electromechanical drive 105 and the right exterior mirror 110 by an electromechanical drive 115. Each of the electromechanical drives 105, 115 has two electric motors (not shown here) to enable rotation about the x-axis and the y-axis. This is explained in Figure 1. Fig. Figure 1 is shown enlarged. Furthermore, an interior mirror 210 is arranged in the interior of the motor vehicle 200. The interior mirror 210 can be controlled by an electromechanical drive 220 and thereby rotated about one or more of the axes x, y, z, shown schematically by the coordinate system, i.e., about three spatial axes. Accordingly, the electromechanical drive 220 for the interior mirror 210 has three electric motors (not shown here).

[0043] Furthermore, the motor vehicle 200 has a control unit 230 which is connected via signaling to the electromechanical drive 105 of the left exterior mirror 100, to the electromechanical drive 115 of the right exterior mirror 110, and to the electromechanical drive 220 of the interior mirror. This allows the two exterior mirrors 100 and 110 and the interior mirror 210 to be automatically controlled via the control unit 230.

[0044] The interior camera 240 can detect the movements, positions, and poses of a user's hand 120. The detected movements, corresponding hand positions, and poses can then be transmitted to the control unit 230 for evaluation. The interior camera 240 can also detect a pointing pose of the hand 120. Such a pointing pose represents the hand pointing towards an object 100, 110, or 210 of the vehicle 200. This is schematically represented by the arrows pointing to the left exterior mirror 100, the interior mirror 210, and the right exterior mirror 110. The pointing pose allows the user to select an object to be moved. This object can be one of the aforementioned vehicle mirrors 100, 110, or 210, or another object that can be rotated around an axis.

[0045] In Fig. 2 is the hand 120 in relation to the schematically depicted occupants of the motor vehicle 200, detached from the occupants and enlarged to the size of the occupants or the driver for reasons of recognizability.

[0046] The control device 230 can in particular include an estimation device (not shown here) configured to estimate a hand pose. The estimation device can in particular be a computer, which is equipped in particular with a processor platform and a program and data memory as well as a data output for outputting computer-defined output data, in particular in the form of hand poses. A computer program consisting of one or more program modules can be stored in the program memory and is configured, when executed on the processor platform, to perform the method according to the invention, for example as described above. Fig. 3 described, to be carried out.

[0047] In Fig. Figure 3 shows a schematic flowchart 300 to illustrate an embodiment of a method for controlling a vehicle mirror rotatable about an axis.

[0048] In a first step S310 of the procedure, a vehicle mirror position is determined in a 3D coordinate system and an initial alignment adjustment of the vehicle mirror 100, 110, 210, in particular the left exterior mirror 100 or the right exterior mirror 110, is made. This can be done by reading a previously determined position from a memory (not shown here) of the motor vehicle 200.

[0049] The current vehicle mirror rotation setting at time t0 is determined in spherical coordinates (r'0, φ'0, θ'0).

[0050] In a further step S320 of the procedure, sensor-based acquisition of measurement data is performed, representing a hand pose and hand position of a user. For this purpose, an interior camera 240 of the vehicle 200 is used, as described in Fig. 2 described, used.

[0051] In a further step S330 of the procedure, a first hand position p0 (x0, y0, z0) is determined with respect to the vehicle mirror position, and a first hand pose of the hand in the first position p0 (x0, y0, z0) is estimated using the measurement data. For this purpose, a known estimation algorithm can be used with previously stored reference hand poses.

[0052] The current hand position p0 also defines a distance between hand 120 and the vehicle mirror 100, 110, 210, or rather its rotation point RP, thereby forming a virtual lever 130 between the hand and the vehicle mirror 100, 110, 210. The hand position p0, or one end of the virtual lever, is determined in spherical coordinates (r0, φ0, θ0). The other end of the virtual lever corresponds to the rotation point RP of the vehicle mirror 100, 110, 210.

[0053] As in Fig. As shown in Figure 1B, for easier illustration, a virtual lever 130 can be constructed, extending from a rotation point RP, where the axes x, y, z about which the vehicle mirrors 100, 110, 210 can be rotated, to the user's hand 120. This virtual lever 130 can be moved by a movement of the hand 120, thereby moving or rotating the vehicle mirror 100, 110, 210. A hand movement is thus directly translated into a movement of the vehicle mirror 100, 110, 210 in the sense of a change in its rotation about one of the axes x, y.

[0054] The rotation point RP can correspond to the center of the coordinate system for the vehicle mirror 100, 110, 210. It is necessary that the coordinate system of the vehicle mirror 100, 110, 210 is known relative to a global reference coordinate system in which the hand movements occur. This allows all hand positions and movements to be transformed into the vehicle mirror coordinate system. It is further assumed that the space in which the system is located, i.e., the user and the vehicle mirror 100, 110, 210, are in the global coordinate system.

[0055] For a point p = (x, y, z) corresponding spherical coordinates (r, θ, φ) can be determined.

[0056] Here, r describes the length or distance to an origin or, as in this case, to the rotation point RP, θ describes the lateral angle between the projection of p onto the xz plane and the z-axis, and φ describes the height of p, i.e., the angle between p and the xz plane.

[0057] In a vehicle mirror 100, 110, 210 which is controlled by two electric motors of an electromagnetic drive 105, 115, 220, a rotation can be parameterized by θ and φ.

[0058] A virtual lever 130 extends, as in Fig. 1B shows the rotation point RP of the vehicle mirror 100, 110, 210 and coincides with a unit vector z of the vehicle mirror 100, 110, 210 coordinate system when the vehicle mirror 100, 110, 210 is in a neutral position, i.e. without rotational deflection.

[0059] In a further step S340 of the procedure, the subsequent steps are carried out if the estimation of the first hand pose has shown that the first hand pose represents a grasping pose. Otherwise, the procedure continues with step S320.

[0060] In a further step S350 of the procedure, a second hand position is determined in relation to the vehicle mirror position using the measurement data.

[0061] In a further step S360 of the procedure, motion data of hand 120 is determined, representing a lateral movement of the hand from the first hand position p0 to the second hand position p1, using the sensor-acquired measurement data over a predefined period. Hand position p0 and hand position p1 (x1, y1, z1) can then be converted into the corresponding spherical coordinates (r1, φ1, θ1).

[0062] In a further step S370 of the procedure, the vehicle mirror 100, 110, 210 is moved by an electromechanical drive 105, 115, 220 about one of the axes x, y, z from the first alignment setting to a second alignment setting using the movement data of the hand.

[0063] Comparing the spherical coordinates of p0 to p1 yields a hand movement of the user, which can be described by θ1 - θ0 and φ1 - φ0. From this, a rotation of the vehicle mirror due to the hand movement around the respective axes (x, y) can be determined as follows: θ'1 = θ'0 + (θ1 - θ0) and φ'1 = φ'1 + (φ1 - φ0).

[0064] When the vehicle mirror 100, 110, 210 is rotated, the parameters θ and φ, which parameterize the rotation of the vehicle mirror 100, 110, 210, coincide exactly with the spherical coordinates θ and φ of the virtual lever 130 in the coordinate system of the vehicle mirror. This establishes a direct relationship between the spherical coordinates of the normal plane and the two parameters (states of the electric motors) that implement the rotation of the vehicle mirror 100, 110, 210.

[0065] The procedure or movement of the vehicle mirror 100, 110, 210 can be terminated by a hand pose that represents a solution to the gripping position.

[0066] The present method can also be used to control the vehicle's interior mirror 210, in particular about its three spatial axes x, y, z. Furthermore, the method can be used to control another object of the vehicle 200 besides a vehicle mirror 100, 110, 210, for example, ventilation slots that are also rotatable about two axes. The object can also include an external camera, for example, a parking camera.

[0067] While at least one exemplary embodiment has been described above, it should be noted that a large number of variations exist. It should also be noted that the described exemplary embodiments are merely non-limiting examples, and it is not intended to restrict the scope, applicability, or configuration of the devices and methods described herein. Rather, the preceding description will provide the person skilled in the art with guidance for implementing at least one exemplary embodiment. It is understood that various modifications to the function and arrangement of the elements described in an exemplary embodiment can be made without derogating from the subject matter defined in the appended claims and their legal equivalents. REFERENCE MARK LIST 100, 110 Left, right wing mirror 105, 115 Electromechanical drive for left, right exterior mirror 120 Hand 130 Virtual Lever RP Rotation Point p0, p1 Hand positions x n , y n , z n Hand positions, Cartesian coordinates r n , φ n , θ n Hand positions, spherical coordinates 200 motor vehicles 210 Interior mirror 220 Electromechanical drive interior mirror 230 Control unit 240 Interior camera 300 Flowchart S310 Determine vehicle mirror position and alignment setting S320 Receiving measurement data S330 Determine first hand position and estimate hand pose S340 Perform further procedure steps if hand pose is grasping pose S350 Determine second hand position S360 Determining movement data hand S370 Moving vehicle mirrors

Claims

[1] Method for controlling an object (100, 110, 210) of a vehicle (200) rotatable about at least one axis (x, y, z), comprising: Determining an object position and an initial orientation setting of the object (100, 110, 210); Receiving sensor-acquired measurement data over a specified period, representing a hand pose and hand position (x0, y0, z0) of a user's hand (120); Determining a first hand position (x0, y0, z0) relative to the object position and Estimating a first hand pose of hand (120) using the measurement data; If the estimation of the first hand pose has revealed that the first hand pose represents a grasping pose: Determine a second hand position (x1, y1, z1) in relation to the object position using the measurement data; Determining movement data of the hand (120) representing a lateral movement of the hand from the first hand position (x0, y0, z0) to the second hand position (x1, y1, z1); Moving the object (100, 110, 210) by means of an electromechanical drive (105, 115, 220) about at least one axis (x, y, z) from the first orientation setting to a second orientation setting using the determined movement data of the hand (120). [2] Method according to claim 1, further comprising: Estimating a second hand pose using the measurement data; Terminating the movement of the object when the estimation of the second hand pose has shown that the second hand pose represents a release from the grasping pose. [3] Method according to claim 1 or 2, further comprising: Determining a hand reference point of the hand (120); Using the determined reference point to determine the first hand position and the second hand position. [4] Method according to claim 3, wherein the center point of a palm of the user's hand (120) is determined as the hand reference point. [5] Method according to claim 3, wherein the end region of a finger of the user's hand (120) is determined as the hand reference point. [6] Method according to any of the preceding claims, further comprising; Determining an object reference point of the object (100, 110, 210); Using the determined object reference point to determine the object position. [7] Method according to one of the preceding claims, wherein a plurality of temporally successive further hand positions are determined, and wherein the motion data are determined using the further hand positions. [8] Method according to any of the preceding claims, further comprising: Estimating a third hand pose using the measurement data; wherein the third hand pose represents a pointing pose in the direction of an object (100, 110, 210) of the vehicle (200), wherein the estimation of the third hand pose occurs before the estimation of the first hand pose; Identifying the object towards which the pointing pose is directed; the movement of the object to which the pointing pose is directed takes place. [9] Method according to any of the preceding claims, wherein the estimation of the first hand pose is repeated at predetermined time intervals as long as the estimation of the first hand pose has shown that the first hand pose does not represent a grasping pose. [10] Method according to any of the preceding claims wherein the object is rotatable about two or three spatial axes (x, y, z), wherein the method further comprises: Estimating a plurality of temporally successive fourth-hand poses using the measurement data, where the majority of the fourth-hand poses collectively represent a rotational gesture; Moving the object (100, 110, 210) taking into account the determined rotation gesture. [11] Device for controlling an object (100, 110, 210) of a vehicle (200), wherein the device is configured to carry out the method according to one of the preceding claims. [12] Device according to claim 11, comprising: An electromechanical drive (105, 115, 220) that is mechanically coupled to the object (100, 110, 210) and by which the object can be rotated about at least one axis (x, y, z); An interior camera (240) of the vehicle (200) which is set up to sensorially capture measurement data representing a hand pose and hand position of a hand (120) of a user of the vehicle (200); A control unit (230) that is set up: Determining an object position and an initial orientation setting of the object (100, 110, 210); Determining a first hand position (x0, y0, z0) relative to the object position and Estimating a first hand pose of hand (120) using the measurement data; If the estimation of the first hand pose has revealed that the first hand pose represents a grasping pose: Determining a second hand position (x1, y1, z1) in relation to the object position using the sensor-acquired measurement data over a specified period; Determining movement data of the hand (120) representing a lateral movement of the hand from the first hand position (x0, y0, z0) to the second hand position (x1, y1, z1); Moving the object (100, 110, 210) by means of an electromechanical drive (105, 115, 220) about at least one axis (x, y, z) from the first orientation setting to a second orientation setting using the determined movement data of the hand (120). [13] Vehicle comprising a device according to one of claims 11 to 12. [14] Computer program with instructions which, when executed on a device according to one of claims 11 to 12, cause the device to execute the method according to one of claims 1 to 10.

Images