Planning trajectory of robot
By collecting real environmental data and combining simulated environment algorithms, a three-dimensional model and robot model are established to plan and optimize collision-free trajectories, the trajectory planning problem in the real environment is solved, and fast and reliable trajectory planning and safety improvement are achieved.
Patent Information
- Application Number
- CN202380027939.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2022-03-15
- Filing Date
- 2023-03-13
- Publication Date
- 2024-11-12
AI Technical Summary
In real environments, robot trajectory planning is difficult to avoid obstacle collisions, and the existing technology relies on manual debugging to be time-consuming and has high experience requirements. Unmodeled or incorrectly modeled real obstacles will cause planned trajectories in the simulated environment to be in the real environment. Difficult to implement.
The real environment data is collected through the acquisition device, a three-dimensional environmental model and robot model are established, and the collision-free trajectory is planned using simulated environmental algorithms, and virtually represent and optimize in augmented reality through visualization devices, combining pre-set quality standards such as time, energy and Distance, select the best track.
It realizes rapid, simple and reliable planning of collision-free robot trajectories, reducing debugging complexity and time-consuming, and improving the matching and security of the trajectory with the real environment.
Smart Images

Figure CN118946435A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to a method and a system for planning a robot trajectory and a computer program or a computer program product for executing the method. Background Art
[0002] In the simulation environment, in particular by means of an optimizer, it is advantageously possible to plan in advance a trajectory of the robot which enables the robot to avoid collisions with obstacles which are modeled in a computer-implemented manner in the simulation environment.
[0003] In the real environment, this is currently done manually according to internal corporate practices, which is not only (more) time-consuming, but also requires the debugger to have extensive experience. On the other hand, if, for example, real obstacles are not modeled or are modeled incorrectly or are ignored after the simulation environment is created, the trajectory planned in advance in the simulation environment is difficult to execute in the real environment. Summary of the invention
[0004] The object of the present invention is to improve the operation of a robot, in particular by planning the trajectory of the robot.
[0005] The object of the invention is achieved by a method having the features of claim 1. Claims 13 and 14 claim a system or a computer program or a computer program product for carrying out the method described here. The dependent claims relate to preferred developments.
[0006] According to one embodiment of the present invention, a method for planning a trajectory of a robot ("robot trajectory") comprises the following steps:
[0007] - collecting data of the real environment of the robot by means of a collection device, in one embodiment a mobile collection device, in an extension a portable collection device, in particular a collection device that can be carried by a person;
[0008] - based on the acquired data, in one embodiment by at least one approximation of the features, in particular the points, acquired by the acquisition device, determining a computer-implemented three-dimensional model of the environment;
[0009] - based on the environment model and the computer-implemented robot model, planning a first trajectory of the robot to avoid collision between the robot model and the environment model; and
[0010] - Visualizing a virtual representation of the planned first trajectory in augmented reality by means of a visualization device.
[0011] In one embodiment, by creating an environment model of the real environment with the aid of the acquisition device or the data acquired by the acquisition device and using it for planning, a collision-free trajectory can be advantageously planned in advance theoretically using a known simulation environment algorithm or a trajectory planning tool of software technology. It is particularly advantageous that the robot can avoid collisions with the environment along the trajectory with the aid of a known simulation environment algorithm or a software technology optimization tool, and at the same time, it is also optimal to a certain extent with respect to a pre-set quality standard, for example, within a pre-set accuracy, number of iterations, calculation time, possibility of variation, etc. Accordingly, in one embodiment, the first trajectory is planned by optimizing a pre-set one-dimensional or multi-dimensional quality standard. Here, avoiding collisions can be regarded as a boundary condition in one embodiment, and as a part of the quality standard in another embodiment, in particular in the form of a penalty function, for example, in the following manner: a trajectory with collisions is not allowed during the optimization process; or a collision greatly deteriorates the value of the quality standard, so that the corresponding trajectory is not optimal and is therefore abandoned. By means of the visualization, the planner can advantageously check the planned trajectory in augmented reality and thereby in particular identify problems which may be caused, for example, by changes in the environment which occurred after the environment was detected and which were not taken into account during planning, inaccurate robot modeling, or incorrect trajectory planning.
[0012] In one embodiment, the quality criterion depends on the time required for the robot to travel the trajectory, and / or on the energy required for the robot to travel the trajectory, and / or on the distance between the robot and the environment. In an extended solution, it depends on the minimum distance between the robot and the environment while the robot travels the trajectory. In particular, the (first) trajectory can be planned so that the time required for the robot to travel the trajectory is minimized, the energy required for the robot to travel the trajectory is minimized, the minimum distance or average distance between the robot and the environment while the robot travels the trajectory is maximized, etc. In particular, a mixed, preferably weighted quality criterion can be used, which takes two or more of the above aspects and / or other aspects into account, such as the speed, acceleration and / or sway of the robot, etc.
[0013] In one embodiment, a particularly advantageous trajectory can thus be planned for the robot.
[0014] In addition to or alternatively to the above optimization, in one embodiment, the method may include the following steps:
[0015] - based on the environment model and the model of the robot, planning one or more further trajectories of the robot (respectively) to avoid collisions between the robot model and the environment model;
[0016] - visualizing the virtual representation of the planned further trajectory together with the virtual representation of the first trajectory in augmented reality by means of the visualization device; and
[0017] - Based on user input, selecting a trajectory from a set comprising the first trajectory and the further trajectory(s).
[0018] In one specific embodiment, the user input is performed by means of a visualization device.
[0019] By planning and visualizing two or more (each theoretically) collision-free trajectories, in one embodiment, possible alternatives can be advantageously provided to the planner, who can then select a particularly advantageous alternative from among them by means of or in augmented reality after checking the alternatives by means of user input. The selected trajectory and / or the trajectory planned by means of optimization can then be driven over with the real robot in a subsequent method step, or the method includes this step. As a result, the planner can plan collision-free trajectories that are advantageous from his point of view particularly easily, quickly and / or reliably, wherein the planner can in particular discard trajectories that are theoretically collision-free but that he finds to have collisions or other weaknesses based on the visualization in augmented reality.
[0020] In one embodiment, the first trajectory and / or the one or more further trajectories are (respectively) planned based on one or more predefined trajectory points, in an extended solution based on a predefined initial trajectory. In one embodiment, the individual trajectories are planned to extend through one or more predefined trajectory points. In this extended solution, the predefined initial trajectory is used as a starting point for trajectory planning, in particular optimization.
[0021] In one embodiment, by using predefined trajectory points, the planned trajectory can be particularly advantageously adapted to the real environment; in one embodiment, by using a predefined initial trajectory, trajectory planning, in particular optimization, can be particularly advantageously converged and / or particularly advantageous alternatives can be provided to the user for selection. In one embodiment, the user can first predefine an initial trajectory, based on which the first trajectory and / or (a plurality of) further trajectories are planned, in an extension by automatic modification. In this way, the (initial) trajectory predefined by the user can be (re)planned or modified to a collision-free trajectory, preferably an optimal or optimized trajectory with respect to a predefined quality criterion.
[0022] In one embodiment, the predetermined trajectory point(s), in one embodiment of the further development a predetermined initial trajectory, is predetermined by driving towards or past a real robot, in one embodiment by manually guided driving towards or past a real robot, preferably using a robot for which the trajectory is planned. In one embodiment, manually guided driving towards or past includes manually moving the robot by exerting a force on the robot.
[0023] In one embodiment, the planned trajectory can thus be adapted particularly advantageously to the real environment or the robot.
[0024] Additionally or alternatively, in one embodiment, the predetermined trajectory point(s), in one embodiment of the development a predetermined initial trajectory, is predetermined with the aid of a simulation environment and / or by off-line programming.
[0025] In one specific embodiment, trajectory planning, in particular optimization, can thereby converge particularly advantageously and / or provide a user with particularly advantageous alternatives for selection.
[0026] In one embodiment, the robot has: a robot arm with three or more, preferably at least six, in one embodiment at least seven joints, in an extended version, revolute joints, which connect the movable members of the robot to one another and can be moved by drives, in particular motors, of the robot; and / or a movable base, in particular a base that can be moved by means of at least one drive, in particular a motor, of the robot. For such a robot, the present invention is particularly advantageous, in particular because of the complex trajectories that may exist. In one embodiment, a robot-guided tool or workpiece forms the (distal) movable member of the robot in the sense of the present invention, or the model of the robot (also) includes a model of the robot-guided tool or workpiece.
[0027] In one embodiment, the three-dimensional environment model comprises data, in particular permanently or temporarily stored, which specifies or describes one or more three-dimensional contours or geometries of the real environment of the robot, in particular a robot cell, a manufacturing plant or a storage warehouse or the like.
[0028] In one embodiment, the model of the robot includes, in particular, long-term or temporarily stored data that illustrate or describe the three-dimensional contour or geometry of the (real) robot, in particular one or more of its movable members. As described above, in one embodiment, a robot-guided tool or workpiece forms a (distal) movable member of the robot in the sense of the present invention, or the model of the robot (also) includes a model of the robot-guided tool or workpiece.
[0029] In one embodiment, the acquisition device is arranged on the visualization device, in an extension it is arranged integrated or detachably on the visualization device. Thus, in one embodiment, the environment model can be advantageously determined on the spot or immediately before planning or visualization, and is therefore particularly up-to-date, and the trajectory can thus be planned particularly advantageously.
[0030] In one embodiment, the acquisition device for acquiring data is moved translationally and / or rotationally relative to the real environment, in particular by a planner operating the visualization device. Thus, in one embodiment, larger areas and / or environments of the environment can be acquired (more) accurately and thus trajectories can be planned particularly advantageously.
[0031] In one embodiment, the acquisition device has one or more contactless measuring distance meters, in an extension, one or more radar distance meters, one or more ultrasonic distance meters and / or one or more lidar distance meters. Thus, in one embodiment, the environment model can be determined (more) accurately and the trajectory planning can therefore be particularly advantageous. In this case, lidar distance meters are particularly preferred because of their compact design and precise measurement.
[0032] Additionally or alternatively, in one embodiment, the acquisition device has: one or more cameras, in one embodiment a 3D camera system, in one embodiment, the 3D camera system having at least two or more stereo cameras, a triangulation system, at least one TOF camera, at least one interferometry camera, at least one light field camera, etc., in which at least one light source images a defined pattern on the environment and at least one camera preferably records the pattern from another perspective; and / or an image processing device. As a result, in one embodiment, the environment can be acquired (more) quickly and the method can therefore be carried out particularly quickly and / or a larger environment can be taken into account.
[0033] In one embodiment, in addition to determining based on the acquired data of the real environment, the environment model is determined based on pre-set target data of the environment, in an extended solution based on CAD data of the environment. In one embodiment, by taking into account such data, the environment model can be determined (more) quickly and / or (more) accurately.
[0034] In one embodiment, the model of the robot is determined based on predefined target data of the robot, in an extended solution based on CAD data of the robot, and / or based on measurements of the robot. In one embodiment, by taking into account such data, the model of the robot can be determined (more) quickly and / or (more) accurately. In one embodiment, the model of the robot has or gives, for different sections, in particular points, of the planned trajectory, the postures of the robot limbs relative to each other and / or relative to a reference system fixed to the environment, which are determined according to the planned trajectory. In one embodiment, a posture or attitude in the sense of the present invention includes a one-dimensional, two-dimensional or three-dimensional position and / or a one-dimensional, two-dimensional or three-dimensional orientation.
[0035] As described above, in one embodiment, a robot-guided tool or workpiece forms a movable member of the robot in the sense of the present invention. Accordingly, in one embodiment, the model of the robot has a computer-implemented model of the robot-guided tool or workpiece as a movable member of the robot. Thus, in one embodiment, the risk of a robot-guided tool or workpiece colliding with the environment can be advantageously reduced. Accordingly, in one embodiment, the model of the robot is determined based on pre-set target data of the tool or workpiece, in an extended solution CAD data, and / or based on measurements of the tool or workpiece.
[0036] In one embodiment, the environment model has one or more geometric primitives, which correspond to a real environment obstacle, especially to multiple real environment obstacles, according to a predetermined relationship, especially a spatial posture, and accordingly, at least one geometric primitive corresponds to the real environment obstacle according to a predetermined relationship, especially a spatial posture. Additionally or alternatively, in one embodiment, the model of the robot has one or more geometric primitives, which correspond to a robot limb, especially to multiple robot limbs, preferably at least one end effector, according to a predetermined relationship, especially a spatial posture, and accordingly, at least one geometric primitive corresponds to the robot limb according to a predetermined relationship, especially a spatial posture. Thus, in one embodiment, a collision-free trajectory can be planned (more) quickly. In one embodiment, the geometric primitive in the sense of the present invention is a polyhedron, especially a prism, especially a cuboid, or a cylinder, a cone, an ellipsoid, especially a sphere, etc. Thus, in one embodiment, a collision-free trajectory can be planned particularly quickly.
[0037] In one embodiment, the environment model is determined by at least one approximation of features, in particular points, acquired by the acquisition device, particularly preferably of a point cloud acquired by the acquisition device, in an extended solution by means of one or more grids and / or one or more approximation surfaces, in particular flat approximation surfaces and / or one or more curved approximation surfaces, in one embodiment, such grids or approximation surfaces are determined by means of compensation functions, in particular interpolation or extrapolation functions, smoothing functions and / or other fitting functions of the points acquired by the acquisition device, in particular the environment model can have such approximations. In one embodiment, by means of such approximations, the environment can be modeled particularly advantageously, particularly quickly and / or precisely.
[0038] In one embodiment, the environment model is determined based on the robot, in particular by means of data of the robot collected, in particular collected by a collection device, and / or based on a model of the robot. In an extension, the robot, which may have been collected along with the real environment data of the robot when collected by the collection device, is at least partially eliminated or hidden. In this way, in one embodiment, the environment model can be improved.
[0039] In one embodiment, the environment model is determined based on the selection of the environment area by the planner. In one embodiment, the environment model does not take into account the environment area selected by the planner, in one embodiment, it is not acquired by means of the acquisition device, and / or the environment model only takes into account the environment area selected by the planner, in one embodiment, only this environment area is acquired by means of the acquisition device. In this way, in one embodiment, the environment model can be improved and / or (more) quickly determined.
[0040] In one embodiment, the visualization device is a mobile visualization device, in particular a visualization device that can be carried (by a person, preferably with one hand), and in one embodiment, the visualization device comprises: a handheld device, preferably a handheld device, a tablet, a smartphone, a notebook, etc.; and / or glasses, in particular AR (augmented reality) glasses. Thus, in one embodiment, acquisition, planning and / or visualization can be performed locally or on site and thus improved. In one embodiment, the visualization device is designed (in terms of hardware technology and / or software technology) for controlling a robot or is (also) used for this purpose. Thus, in one embodiment, commissioning can be performed (more) quickly and / or (more) safely.
[0041] In one embodiment, the (visualized) virtual representation of the planned first trajectory and / or (one or more) further trajectories (respectively) comprises: a route fixed to a reference point of the robot, preferably an end effector of the robot, in one embodiment a continuous route; and / or a description of one or more, in particular all, movable limbs of the robot, in one embodiment described with the aid of or through geometrical primitives of the robot model. In one embodiment, this description of one or more limbs of the robot changes during the visualization depending on the (respectively) planned or visualized trajectory, and accordingly, this virtual representation can in particular comprise a virtual simulation of the robot or a description of the movement of one or more limbs of the robot when driving through the trajectory.
[0042] In one embodiment, by visualizing the route, the planned trajectory can be checked (more) quickly and / or (more) reliably, in particular the inspector can check or judge the trajectory (more) simply, (more) intuitively and / or (more) quickly.
[0043] In one embodiment, during the visualization of a virtual representation of a first trajectory and / or (one or more) further trajectories, one or more parameters of the trajectory are (respectively) output; in one embodiment, a speed and / or at least one parameter, such as a speed, is output for at least one segment of the trajectory, in particular a segment, in particular a point, selected by a planner, and / or at least one parameter, such as a speed, is output for a segment, in particular a point, of the trajectory that has just been or is being simulated being driven over or driven towards during the visualization.
[0044] In one embodiment, the output of the parameter is carried out in digital, acoustic and / or symbolic form. For example, the direction of travel can be output by an arrow; the TCP speed can be output by a corresponding digital indication, or by sound output, in particular a sound with respect to a reference sound, which can in particular correspond to a zero value or a reference value of the parameter.
[0045] Thus, in one embodiment, a planner may check or assess the trajectory (more) quickly and / or (more) reliably.
[0046] The present invention can be used particularly advantageously during the commissioning process of a robot or for the purpose of commissioning a robot and / or for transfer trajectories intended to move the robot from a starting position to a target position without colliding with the environment, since it can particularly advantageously increase safety and / or reduce effort and / or time for the commissioning process and the transfer trajectories, but the present invention is not limited thereto.
[0047] According to one embodiment of the present invention, a system is provided, which is particularly designed in terms of hardware technology and / or software technology, particularly programming technology, for carrying out the method described herein and / or comprises:
[0048] - a collection device for collecting real environment data of the robot, in particular a mobile collection device, in particular a portable collection device;
[0049] - means for determining a computer-implemented three-dimensional environment model based on the acquired data, in particular by means of at least one approximation of the features, in particular points, acquired by the acquisition device;
[0050] - means for planning a first trajectory of the robot based on the environment model and the computer implemented robot model to avoid collision between the robot model and the environment model; and
[0051] - Visualization means for visualizing a virtual representation of the planned first trajectory in augmented reality.
[0052] In one embodiment, the system or apparatus thereof comprises:
[0053] - an optimizer for planning the (first) trajectory by optimizing a predefined quality criterion, wherein the quality criterion preferably depends on the time and / or energy required for the robot to travel the trajectory and / or the distance of the robot from the environment; and / or
[0054] - means for planning one or more further trajectories of the robot based on the environment model and the robot model to avoid collisions between the robot model and the environment model, wherein the visualization means visualizes a virtual representation of the planned further trajectories together with the virtual representation of the first trajectory in augmented reality or is designed for this purpose or is used for this purpose; and means for selecting a trajectory from a set comprising the first trajectory and the further trajectory(s) based on a user input; and / or
[0055] - a device for planning a first trajectory and / or (multiple) further trajectories based on at least one predetermined trajectory point, in particular a predetermined initial trajectory, in particular a device for presetting the at least one trajectory point, in particular a predetermined initial trajectory, by means of a real robot driving towards or passing, in particular manually guided driving towards or passing, with the aid of a simulation environment and / or by means of offline programming; and / or
[0056] - means for determining a model of the robot based on predefined target data of the robot, in particular CAD data and / or measurements of the robot; and / or
[0057] - means for determining an environment model based on data of the robot, in particular collected by the collection device, and / or based on a model of the robot and / or based on a planner's selection of an environment area; and / or
[0058] - a device for outputting at least one parameter of the trajectory, in particular the speed, in particular in digital, acoustic and / or symbolic form, during the visualization of a virtual representation of a first trajectory and / or of at least one further trajectory and / or for at least one selected section, in particular point, of the trajectory and / or for a section, in particular point, of the trajectory that is simulated being travelled over or towards during the visualization.
[0059] The system and / or device within the meaning of the present invention can be implemented in hardware technology and / or software technology, in particular having: at least one processing unit, in particular a digital processing unit, in particular a microprocessor unit (CPU), a graphics card (GPU), etc., preferably connected to a storage system and / or a bus system for data or signals; and / or one or more programs or program modules. The processing unit can be designed to: process instructions implemented as a program stored in the storage system; to collect input signals from a data bus; and / or to send output signals to the data bus. The storage system can have one or more, in particular different storage media, in particular optical, magnetic, solid and / or other non-volatile media. The program can be provided to embody or implement the method described herein, so that the processing unit can perform the steps of the method and thus in particular plan (multiple) trajectories and / or control the robot when the robot travels through the trajectory. In one embodiment, the computer program product can have, can in particular be a computer-readable, non-volatile storage medium for storing programs or instructions or a storage medium on which a program is stored or on which instructions are stored. In one embodiment, execution of the program or the instructions by a system or a controller, in particular a computer or an array of multiple computers, will allow the system or the controller, in particular one or more computers, to implement the method described herein or one or more steps thereof, or the program or the instructions are designed for this purpose.
[0060] In one embodiment, one or more steps, in particular all steps, of the method are performed completely or partially automatically, in particular by the system or a device thereof.
[0061] In one specific embodiment, the system comprises a robot.
[0062] In one embodiment, the method comprises the following steps:
[0063] - Based on the user input, the first trajectory and / or the further trajectory(s), respectively, are modified, in one development, a trajectory selected from the first trajectory and the one or more further trajectories is modified.
[0064] In one embodiment, the planner can thus advantageously adapt the respective trajectory to the actual environment and / or to changed boundary conditions and / or to additional requirements.
[0065] Additionally or alternatively, in one embodiment, the method comprises the following steps:
[0066] - Driving with the robot along the planned trajectory, optionally the selected and / or modified trajectory.
[0067] Thus, in one embodiment, the planner can advantageously use the real robot to check the corresponding trajectory.
[0068] In one embodiment, the quality criteria used in the optimization are pre-set based on user input. For example, the user or planner can select one or more (sub) criteria and / or their weights from a pre-set set.
[0069] Accordingly, in one embodiment, the system or its device comprises:
[0070] - means for modifying the first trajectory and / or at least one further, in particular selected, trajectory based on a user input; and / or
[0071] - means for driving the robot along a trajectory, a trajectory which has been selected and / or modified if necessary; and / or
[0072] - Means for presetting quality criteria based on user input.
[0073] In one embodiment, the method also includes operating the robot by using the robot to travel along a trajectory, a possibly selected and / or modified trajectory, and can therefore be particularly a method for operating a robot. Accordingly, in one embodiment, the system can also be a system for operating a robot. BRIEF DESCRIPTION OF THE DRAWINGS
[0074] Further advantages and features are given by the dependent claims and the embodiments. To this end, a partial schematic diagram is shown:
[0075] Figure 1 A system for planning a trajectory of a robot according to an embodiment of the present invention; and
[0076] Figure 2 A method for planning a trajectory according to an embodiment of the present invention. DETAILED DESCRIPTION
[0077] Figure 1 A system is shown in which a planner 4 checks a planned trajectory of a robot 1 using a visualization device in the form of AR glasses 2 or a tablet 3 .
[0078] In step S10 (see Figure 2 ), the real environment 6 of the robot is collected by a collection device 5A or 5B, such as a 3D camera system, a lidar sensor, etc., which is preferably arranged integrally or detachably on the visualization device 2 or 3, and the computer-implemented environment model is determined in step S20 using these data. In a variant not shown, the environment model can also be created additionally based on target data of the environment.
[0079] In step S30, a first trajectory of the robot is planned based on the environment model and the robot model implemented by the computer to avoid collision between the robot model and the environment model.
[0080] Accordingly, in one embodiment, the first trajectory is planned by means of an optimization of a predetermined quality criterion, which is, for example, a mixed quality criterion in the form of a weighted sum of at least two of the following: the time required to travel over the trajectory, the energy required to travel over the trajectory, the minimum distance occurring between the robot (optionally with a robot-guided tool or workpiece) and the environment when traveling over the trajectory, the maximum speed occurring when traveling over the trajectory, the maximum acceleration occurring when traveling over the trajectory, the maximum jolt occurring when traveling over the trajectory, and / or other sub-criterions. In this case, collision avoidance can advantageously be taken into account as a boundary condition or an additional sub-criterion during the optimization. This is of course purely exemplary and does not limit the invention to such an optimization. In one embodiment, the planner predefines the quality criterion by user input.
[0081] In one embodiment, in step S30 , in addition to the first trajectory of the robot, one or more further, optional collision-free trajectories of the robot are planned.
[0082] In step S40, a virtual representation of the first trajectory and, if necessary, of the further (multiple) trajectories is visualized in augmented reality by means of the visualization device 2 or 3, for example the route of a TCP as a line and / or geometrical elements when simulating driving over the (corresponding) trajectories, wherein in one embodiment these trajectories are simulated being driven over in parallel and in another embodiment they are simulated being driven over sequentially.
[0083] With the aid of the visualized virtual representation(s), the planner 4 can check in step S40 whether the planned trajectory meets(its) requirements, for example is also collision-free in augmented reality.
[0084] If necessary, the planner selects a trajectory from the set including the first trajectory and the additional trajectory(s) in step S50 through user input, and / or modifies the first trajectory or the selected trajectory through user input.
[0085] In step S60 , the checked, possibly selected or modified trajectory can then be driven over with the real robot.
[0086] Although exemplary embodiments have been described in the foregoing description, it should be noted that many variations are possible. It should also be noted that the exemplary embodiments are merely examples and should not constitute any limitation on the scope of protection, application and configuration. On the contrary, the foregoing description can provide a person skilled in the art with a teaching for converting at least one exemplary embodiment, wherein various changes, in particular with respect to the functions and arrangements of the components, can be achieved without departing from the scope of protection of the present invention, such as can be obtained according to the claims and their equivalent feature combinations.
[0087] Reference numerals list
[0088] 1. Robot
[0089] 2 AR glasses
[0090] 3. Tablet
[0091] 4 Planners
[0092] 5A; 5B Collection device
[0093] 6 Environment
[0094] TCP Tool Center Point.
Claims
1. A method for planning a trajectory of a robot (1), comprising the following steps: - collecting (S10) data of the real environment (6) of the robot by means of a collecting device (5A; 5B), in particular a mobile collecting device, in particular a portable collecting device; - determining (S20) a computer-implemented three-dimensional environment model based on the acquired data, in particular by at least one approximation of the features, in particular the points, acquired by the acquisition means; - planning (S30) a first trajectory of the robot based on the environment model and the computer-implemented robot model to avoid collision between the robot model and the environment model; as well as - Visualizing ( S40 ) a virtual representation of the planned first trajectory in augmented reality by means of a visualization device.
2. The method according to claim 1, characterized in that The trajectory is planned with the aid of an optimization for a predefined quality criterion.
3. The method according to the preceding claim, characterized in that The quality criterion depends on the time and / or energy required for the robot to travel over a trajectory and / or the distance of the robot from the environment.
4. The method according to any one of the preceding claims, characterized in that The following steps are involved: - based on the environment model and the robot model, planning (S30) at least one further trajectory of the robot to avoid collisions between the robot model and the environment model; - visualizing the virtual representation of the planned further trajectory together with the virtual representation of the first trajectory in augmented reality by means of the visualization device (S40); and - selecting (S50) a trajectory from a set comprising said first trajectory and said further trajectory based on a user input; and / or Includes at least one of the following steps: - based on a user input, modifying (S50) said first trajectory and / or at least one further trajectory, in particular the chosen trajectory; and / or - driving ( S60 ) the trajectory, optionally the selected and / or modified trajectory, with the robot.
5. The method according to any one of the preceding claims, characterized in that The first trajectory and / or at least one further trajectory is planned based on at least one predetermined trajectory point, in particular a predetermined initial trajectory.
6. The method according to the preceding claim, characterized in that The at least one predetermined trajectory point, in particular the predetermined initial trajectory, is predetermined by driving towards or past a real robot, in particular a manually guided real robot, with the aid of a simulation environment and / or by offline programming.
7. The method according to any one of the preceding claims, characterized in that The acquisition device is arranged on the visualization device, and / or the acquisition device moves translationally and / or rotationally relative to the real environment and / or is moved manually in order to acquire data, and / or the acquisition device has: at least one non-contact measurement rangefinder, in particular at least one lidar rangefinder, radar rangefinder or ultrasonic rangefinder; and / or at least one camera, in particular a 3D camera system; and / or an image processing device.
8. The method according to any one of the preceding claims, characterized in that The environment model has at least one three-dimensional geometric element that corresponds to a real environmental obstacle in a predetermined relationship; and / or the robot model is determined based on predetermined target data of the robot, in particular CAD data and / or measurements of the robot; and / or the robot model has at least one three-dimensional geometric element that corresponds to a limb of the robot in a predetermined relationship; and / or the robot model has a computer-implemented model of a robot-guided tool or workpiece that serves as a movable limb of the robot.
9. The method according to any one of the preceding claims, characterized in that The environment model is determined based on the robot, in particular data of the robot acquired by means of the acquisition device, and / or based on the robot model and / or based on a planner's selection of the surrounding area.
10. The method according to any one of the preceding claims, characterized in that The visualization device is a mobile visualization device, in particular a portable visualization device, in particular with a handheld device, in particular a smartphone and / or glasses, and / or the visualization device is designed to control the robot.
11. The method according to any one of the preceding claims, characterized in that The virtual representation of the first trajectory and / or the at least one further trajectory comprises: a reference point fixed to the robot, in particular an end effector, an in particular continuous route, and / or a description of one or more, in particular all, movable limbs of the robot, in particular a simulation of the robot as it travels along the trajectory.
12. The method according to any one of the preceding claims, characterized in that During visualization of the virtual representation of the first trajectory and / or of the at least one further trajectory, at least one parameter of the trajectory, in particular the speed, is output; and / or for at least one selected segment, in particular a point, of the trajectory, and / or for a segment, in particular a point, of the trajectory that is simulated being travelled over or towards during visualization, at least one parameter is output, in particular in a digital and / or acoustic and / or symbolic manner.
13. A system for planning a trajectory of a robot (1), the system being designed to carry out the method according to any one of the preceding claims and / or comprising: - a collection device for collecting data of the real environment of the robot, in particular a mobile collection device, in particular a portable collection device; - means for determining a computer-implemented three-dimensional model of the environment based on the acquired data, in particular by at least one approximation of the features, in particular points, acquired by said acquisition means; - means for planning a first trajectory of the robot based on the environment model and the computer-implemented model of the robot to avoid collision between the robot model and the environment model; as well as - Visualization means for visualizing a virtual representation of the planned first trajectory in augmented reality.
14. A computer program or a computer program product, wherein: The computer program or computer program product comprises instructions, in particular stored on a computer-readable and / or non-volatile storage medium, which instructions, when executed by one or more computers or a system according to claim 13, cause the one or more computers or the system to perform a method according to any one of claims 1 to 12.
