WO2023213989A1 - Verfahren zum vorbereiten und ausführen von aufgaben mithilfe eines roboters, roboter und computerprogramm - Google Patents
Verfahren zum vorbereiten und ausführen von aufgaben mithilfe eines roboters, roboter und computerprogramm Download PDFInfo
- Publication number
- WO2023213989A1 WO2023213989A1 PCT/EP2023/061892 EP2023061892W WO2023213989A1 WO 2023213989 A1 WO2023213989 A1 WO 2023213989A1 EP 2023061892 W EP2023061892 W EP 2023061892W WO 2023213989 A1 WO2023213989 A1 WO 2023213989A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- robot
- action
- user
- module
- action sequence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Program-controlled manipulators
- B25J9/16—Program controls
- B25J9/1656—Program controls characterised by programming, planning systems for manipulators
- B25J9/1661—Program controls characterised by programming, planning systems for manipulators characterised by task planning, object-oriented languages
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/40—Robotics, robotics mapping to robotics vision
- G05B2219/40391—Human to robot skill transfer
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/40—Robotics, robotics mapping to robotics vision
- G05B2219/40392—Programming, visual robot programming language
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/40—Robotics, robotics mapping to robotics vision
- G05B2219/40397—Programming language for robots, universal, user oriented
Definitions
- the invention relates to a method for preparing and executing tasks using a robot.
- the invention also relates to a robot for carrying out tasks.
- the invention also relates to a computer program.
- the document DE 10 2017 209 032 A1 relates to a method for controlling a robot.
- the document DE 10 2017 209 032 A1 proposes to determine various actions that can be carried out by the robot, to restrict the actions that can be carried out by the robot according to at least one precondition and to display this limited number of actions that can be performed by the robot on a display device so that the user can select an action to be performed from this limited number.
- the document DE 10 2021 104 883 B3 relates to a method for robot-assisted execution of tasks, wherein a robot is controlled in a shared manner in a first support mode using a user module and is autonomously controlled in a user-monitored manner in a second support mode using an automation module.
- a robot is controlled in a shared manner in a first support mode using a user module and is autonomously controlled in a user-monitored manner in a second support mode using an automation module.
- adjustable autonomy particularly in the context of assistive robotics, the user module and the automation module are represented within a shared control module and use the same action representation.
- German patent application filed on February 25, 2022 with the official file number 10 2022 104 525.0 relates to a method for carrying out tasks using a robot, the robot being controlled in a first execution mode and in at least one further execution mode, with one on an action goal-directed action sequence is generated and executed and the same action representations are used to control the robot in the first execution mode and in the at least one further execution mode.
- the invention is based on the object of providing a method mentioned at the outset or of improving it structurally and/or functionally.
- the invention is based on the object of providing a robot mentioned at the outset or of improving it structurally and/or functionally.
- the invention is based on the object of providing a computer program mentioned at the outset or of improving it structurally and/or functionally.
- the method can be used to control the robot.
- “control” refers in particular to control technology and/or control technology.
- Tasks to be carried out can be tasks that a user and/or a robot can/can carry out.
- Tasks to be carried out can be tasks in which a robot supports a user.
- the method may be used to control the robot in cooperation with a human user who uses the robot to assist in performing tasks (robotic tasks with a human-in-the-loop, RTHL).
- the method may be used using at least one
- the process can be carried out using a control device on the robot.
- An action goal can be performing or completing a specific task.
- An action goal can be an overall goal.
- An action goal can be achieved by performing appropriate actions.
- An action goal can be achieved by performing appropriate actions sequentially.
- Actions to be carried out and/or executed can form an action sequence.
- An action sequence can include the actions to be carried out and/or executed to achieve the action goal or can be formed by these actions.
- An action sequence can be generated in a planning phase.
- An action sequence can be generated by creating, selecting, composing, lining up, listing, and/or ordering.
- An action sequence can be a symbolic plan.
- the symbolic plan can contain all the symbolic transitions necessary to achieve an action goal.
- An action sequence can be generated using a symbolic planner.
- An action sequence directed toward an action goal may be an action sequence designed to accomplish the action goal.
- An action sequence can be generated and/or executed to achieve the action goal.
- a sequence of actions can be neither predetermined nor fixed.
- An action sequence can be planned to achieve an action goal.
- An action sequence can be individually planned to achieve a specific action goal. At least one action and at least one further action of the action sequence can be carried out at least partially in parallel with one another.
- the environmental information can be generated and/or provided using a mathematical model.
- the environmental information may be generated and/or provided using a mathematical model of the environment.
- the environment may include the robot, parts of the robot and/or objects present in a work area of the robot.
- Environmental information can be information about the robot, parts of the robot and/or objects present in a work area of the robot.
- Environmental information can be information about a state of the robot, about a state of parts of the robot and / or about a state of objects present in a work area of the robot at a certain point in time.
- Environmental information can describe current properties of the robot, parts of the robot and/or objects present in a work area of the robot.
- the environmental information can be used in an action sequence.
- the environment information can be generated, provided and/or used as object definitions.
- Data used to generate an action sequence can be called input data.
- Input data may include action definitions and/or object definitions.
- Action definitions can define actions.
- the actions can be part of an action sequence.
- Object definitions can define objects.
- Object definitions can include environmental information.
- An action goal can be determined taking into account a user command.
- a user command may be based on input and/or selection by a user.
- a user command can be an input or selection of an action target by a user.
- the user command probability may be a probability that an action goal will be entered or selected by a user.
- the user command probability can be determined taking into account environmental information.
- a likely action goal can be an action goal that a user is likely to enter or select.
- a likely action goal can be a specific task that a user is likely to perform or complete.
- the following steps can be carried out for a selection by the user: determining possible action goals, restricting a number of the determined possible action goals taking into account at least one precondition and/or offering the limited number of action goals in order to enable the user to make a selection.
- the limited number of action goals may be presented to the user by displaying them on a display device.
- the precondition can be a global precondition, which states in particular that an action sequence aimed at an action goal can only be carried out after a required preceding action sequence has been completed.
- the precondition can state that an action sequence can be completed with a limited number of actions, although this number can be adjustable.
- An action sequence can be defined as an exception and available to the user to choose from offered even though the number of actions required to complete that action sequence exceeds a permitted limited number.
- the precondition can state that only action sequences are displayed on objects to be manipulated that are less than an adjustable maximum distance from the robot.
- a blacklist with invalid action sequences can be created and the precondition can state that an action sequence that is on the blacklist may not be offered to the user for selection.
- a whitelist of required action sequences can be created and the precondition can state that an action sequence that is on the whitelist must be offered to the user for selection.
- the prerequisite may state that the robot may only be used in a limited spatial area, particularly within the user's home.
- the precondition can state that the user may only be offered action sequences to choose from that do not exceed a predetermined energy requirement.
- the method may include a preparation phase and an execution phase.
- the preparation phase can be completed before the execution phase.
- the execution phase can be completed after the preparation phase.
- the execution phase can be traversed following a user command to execute a likely action target.
- the execution phase can be passed through after a user command to execute an action goal that is not determined as a likely action goal, as soon as at least one preparatory action sequence directed at this action goal has been generated and executed in order to determine object-dependent constraints.
- several preparation action sequences can be generated.
- the Preparation phase allows multiple preparation action sequences to be generated for the same probable action goal.
- multiple preparation action sequences can be generated for different probable action goals.
- the at least one preparation action sequence can be saved.
- the at least one preparation action sequence can be saved for later modification and/or execution.
- the at least one preparation action sequence and/or the at least one execution action sequence can/can be generated in a planning phase.
- at least one preliminary action sequence can be generated.
- the at least one preliminary action sequence can be carried out and tested simulatively in the planning phase.
- the preliminary action sequence can be tested with different parameters.
- the at least one preliminary action sequence can be saved.
- the at least one preliminary action sequence can be saved for later modification and/or execution.
- An execution phase can be initiated with a user command. In the execution phase, a preliminary action sequence can be actually executed. In the execution phase, a preliminary action sequence aimed at an action goal selected by a user can be actually executed.
- object-dependent constraints can be determined and saved.
- Object-dependent constraints can be constraints caused by environmental objects.
- Environmental objects can be the robot, parts of the robot and/or objects present in a work area of the robot.
- Object-dependent constraints can be constraints that exist at a specific point in time.
- Object-dependent constraints can be constraints caused by the robot, by parts of the robot and/or by objects present in a work area of the robot.
- Execution phase the stored object-dependent constraints are used in at least one execution action sequence.
- the robot can be shared using the same action representations in a first support mode and controlled autonomously in a user-monitored manner in a second support mode.
- An assistance mode may be designed to perform tasks with robot assistance.
- the robot In the first support mode, the robot can be controlled in a shared manner.
- the robot In the first support mode, the robot can be shared controlled using a user module.
- the first support mode can also be referred to as “shared control”.
- the robot In the second support mode, the robot can be controlled autonomously in a user-monitored manner.
- the robot can be controlled autonomously in a user-monitored manner using at least one automation module.
- the second support mode can also be referred to as “supervised autonomy”.
- the user module and the automation module can be represented within a shared control module.
- At least one support mode may be configured to perform teleoperations.
- At least one assist mode may be designed to perform fully autonomous operations.
- At least one support mode can be designed for direct control of the robot.
- Shared control or “shared control” means in particular that the robot, in particular control variables of the robot, can be controlled shared by the user using a user module and/or autonomously using an automation module.
- the robot can be controlled partly using a user module and partly using an automation module.
- a split between a control using a user module and a control using an automation module can be changed in a controlled manner.
- a split between a control using a user module and a control using an automation module can be seamlessly changed.
- “Seamless” can be used here in particular mean that a change or a change takes place at least approximately without influence on the execution of the task.
- a share of control using a user module can range from almost 0% to almost 100% and a share of control using an automation module can range from almost 100% to almost 0%, with a share of control from a user module and a share of control from an automation module together always being 100%. be.
- approximately 10% of the control can be carried out by the user and approximately 90% by the robot's control device.
- the robot, in particular the control variables, can be controlled proportionally and/or divided along the degrees of freedom of movement. Shared control can be understood as a compromise between direct control and supervised autonomy, where the user directly and continuously controls only part of the task and leaves the rest to the robot.
- Monitored autonomy means in particular that the user has handed over the execution of a task to the robot and the robot carries out the task independently under supervision.
- Supervised autonomy traditionally includes two elements: First, declarative knowledge in the form of symbols that allows the robot to generate an abstract high-level plan. Second, procedural knowledge in the form of geometric operations that helps the robot create and execute low-level motion plans.
- a control module can be a virtual module and/or comprise virtual structures.
- the user module and/or the automation module may/can be a virtual module and/or comprise virtual structures.
- the user module and/or the automation module can be a structurally and/or functionally distinguishable or delimitable module.
- the automation module can be designed to control the robot autonomously.
- the automation module can be designed to complete tasks specified by task definitions.
- the automation module can be designed to generate input commands for autonomous control as an action representation.
- the user module can be designed to suit the robot control user commands.
- the user module may be configured to generate input commands for shared control as an action representation.
- the control module can plan movements and trajectories in the same virtual structures in the first support mode and in the second support mode. Input commands of the control module may use the same virtual structures in the first support mode and in the second support mode.
- the robot In the first support mode, the robot can be controlled by a user via virtual structures, in particular via a user module.
- the automation module can plan movements and trajectories in the same virtual structures in which a user generates commands. Automation module input commands and user module input commands can use the same virtual structures.
- a shared control module may include a user module and an automation module.
- the automation module can be integrated into the user module.
- the user module may include the automation module.
- a shared control module can also be referred to as a “shared control module with integrated autonomy” (English: Shared Control with Integrated Autonomy, SCIA).
- the user module and the automation module can use the same action representations with their respective input commands.
- the automation module can use the user module's action representations.
- the user module can use an action representation of the automation module.
- the action representations can be virtual structures and/or include virtual structures.
- output commands for controlling the robot can be generated based on input commands.
- output commands for controlling the robot can be generated based on input commands from the automation module and/or on input commands from the user module.
- the output commands can also be referred to as a robot control signal.
- the input commands may be commands within the common or shared control module.
- the input commands can be commands originating from the control module, for example from the automation module and/or from the user module.
- the input commands can be commands from which output commands are generated.
- the output commands can be generated directly based on input commands from the control module, for example based on input commands from the automation module and/or on input commands from the user module.
- the output commands can be generated without separate output commands from the control module, for example without separate output commands from the automation module and/or output commands from the user module.
- the output commands can be generated according to an active execution mode, for example according to an active support mode.
- the output commands can be generated based on input commands from an automation module and/or on input commands from the user module.
- the output commands can be generated based on input commands from the automation module.
- the output commands may be common or shared control module output commands.
- the output commands can be commands for controlling the robot.
- the output commands may be commands sent to the robot to control the robot.
- a change between the first support mode and the second support mode can be made possible based on input commands from the control module, for example based on input commands from the automation module and/or on input commands from the user module.
- the automation module can be activated and/or deactivated. Switching between the first support mode and the second support mode can be done in traded control.
- shared control with switching between the first support mode and the second support mode can also be referred to as “shared and traded control”.
- a transfer of the input commands of the automation module and/or the input commands of the user module can take place within a shared control module, in particular within virtual structures that a user also uses for input.
- Switching between the first support mode and the second support mode can be done by activating/deactivating the automation module.
- the automation module In the first support mode, the automation module may be disabled.
- the automation module In the second support mode, the automation module can be activated.
- the automation module can be disabled by default.
- the automation module can be activated and/or deactivated by a user command.
- the stored object-dependent constraints can be used in the first support mode and/or in the second support mode.
- the robot In the first support mode and/or in the second support mode, the robot can be controlled using a control module.
- the control module may be a common control module designed to control the robot in the first assistance mode and in the second assistance mode.
- the control module may be a split control module.
- a shared control module can have a first submodule and at least one further submodule.
- a shared control module may have a first submodule and a second submodule.
- a first submodule may be designed to control the robot in the first support mode.
- Another submodule can be designed to control the robot in the second support mode.
- a first submodule can be designed as a user module.
- a second submodule can be designed as an automation module.
- Different degrees of autonomy can be assigned to the robot in the first support mode and in the second support mode.
- the robot In the first support mode, the robot may be assigned a lower autonomy than in the second support mode.
- the robot In the second support mode, the robot can be assigned greater autonomy than in the first support mode.
- the first support mode and the second support mode may be executed sequentially, weighted sequential, parallel and/or weighted parallel.
- suitable action definitions can be selected from a large number of action definitions.
- the action definitions can be contained in an action database.
- the action database can be a central database.
- Declarative and/or procedural knowledge can be used when generating the action sequence.
- declarative and/or procedural knowledge from the action definitions can be used.
- finite state machines can be created in the form of shared control templates (SCTs).
- SCTs shared control templates
- the shared control templates can be designed to generate output commands from input commands of the control module, for example from input commands from the automation module and/or input commands from the user module.
- the common or shared control module can use shared control templates. States and transitions can form key elements between shared control templates. Each state can represent a different skill phase. Transitions between states can be triggered when certain predefined events occur between objects of interest in the workspace.
- Input commands from the control module for example Input commands from the automation module and/or input commands from the user module can be mapped to task-relevant robot movements using the shared control templates.
- the output commands can be generated by mapping the input commands of the control module, for example the input commands of the automation module and/or the input commands of the user module, to task-relevant robot movements.
- a shared control template can assist a user in achieving a task by providing object and task-specific mappings and constraints for each state of a skill.
- the FSM can monitor progress and trigger transitions between the different states.
- Autonomy can be implemented within an SCT. Autonomy can use this SCT.
- the automation module can be defined and transmit input commands to the SCT. While executing a task in the SCIA, control of the robot can always remain within an SCT and input authority can be switched between the automation module and the user module. This means that the SCT is independent of whether an input command comes from the automation module or the user module. Regardless of whether the input commands come from the automation module or from the user module, the same state transitions, input assignments, active boundary conditions and/or the same overall control can always be applied.
- the user command probability can be determined using a mathematical model.
- the user command probability can be determined using a stochastic model such as hidden Markov model, a directed acyclic graph such as Bayesian network, an undirected probabilistic model, a stochastic process such as Gaussian process, maximum entropy inverse optimal control or Laplace's method become.
- the preparatory action sequence and/or an action sequence that has not yet been carried out in the preparation phase can/can be carried out in reality and/or simulatively.
- the preparation phase can be carried out continuously.
- the preparation phase can be carried out at least substantially uninterrupted.
- the preparation phase can also be referred to as a preparation function.
- the preparation phase can be performed with low prioritization in relation to other tasks performed using the robot.
- the preparation phase can be carried out in the background.
- the preparation phase can continue to be executed while going through an execution phase.
- the preparation phase can be carried out while performing tasks using the robot. Performing other tasks using the robot may involve user commands.
- the preparation phase can be automatic and/or initiated by a user command.
- the preparation phase can be initiated by switching on the robot.
- the preparation phase can be initiated after completion of an execution phase.
- the preparation phase can be interrupted, resumed and/or ended.
- the preparation phase can be paused, resumed and/or ended automatically and/or by a user command.
- the preparation phase can be ended after initiating the execution phase.
- the robot may be designed to assist a user in performing tasks.
- the robot may be an autonomous mobile robot.
- the robot can be an assistance robot, a humanoid robot, a personal robot or a service robot.
- the robot can have kinematics.
- the robot may have joints and limbs.
- the robot may have actuators and sensors.
- the robot can have an input and/or output device for a user, which can also be referred to as a user interface.
- the input and/or output device can be designed to record user commands.
- the input and/or output device can be designed to offer a user action goals to choose from.
- the input and/or output device can be designed as a touchscreen.
- the robot can have a control device.
- the control device can have at least one processor, at least one main memory, at least one data memory and/or at least one signal interface.
- the control device and the input and/or output device can be connected to one another in a signal-transmitting manner.
- the computer program can be executable using the control device.
- the robot can be a real robot.
- the robot can be a simulated robot or a robot simulation.
- the robot may have a user-triggerable switching system.
- the switching system can serve to bring together at any time input commands of the control module, for example input commands of a first submodule, such as an automation module, and input commands of at least one further submodule, such as a user module, and/or between input commands of a first one Submodule, such as automation module, and input commands of at least one further submodule, such as user module.
- Switching between input commands of a first submodule, such as automation module, and input commands of at least another submodule, such as user module can be initiated by a user's input command to change the execution mode, for example a support mode.
- the computer program can be installed and/or executable on a control device of a robot.
- the computer program can be in the form of a computer program product.
- the computer program can be available on a data carrier as an installable and/or executable program file.
- the computer program can be used to be loaded into a working memory of a control device of a robot.
- the invention results in, among other things, a method for reducing robot planning times by pre-planning object-dependent constraints with joint control with integrated autonomy.
- the invention provides a rapid and iteratively refined feasibility test.
- the invention particularly includes the following features: a planning system for an assistance robot that can plan tasks in advance (A); the planning system takes the current state of the environment (including the robot) as input and estimates the n most likely actions to be selected (activated) by the user (B), performs feasibility checks (C), and stores environment-dependent constraints (D), which be able to get the robot to complete a task without colliding with obstacles or having problems with manipulation.
- the constraints stored in (D) can be used immediately when the user activates one of the checked actions, saving planning time (F).
- An action can be activated or started by the user via any user interface.
- the limitations in memory in (D) can support the execution of tasks in both shared control and supervised autonomy (E). If an action is activated by the user and none has been activated yet If object-specific constraints exist, these can be calculated at the latest at the moment of activation
- Fig. 1 shows a method for reducing robot planning times by determining object-dependent constraints with joint control with integrated autonomy in preparation for task execution and
- Fig. 2 Feasibility tests with simulated trajectories in preparation for task execution.
- FIG. 1 shows a process 100 of a method for reducing robot planning times by determining object-dependent constraints with joint control with integrated autonomy in preparation for task execution.
- the method includes a preparation phase 102 and an execution phase 104.
- a module 106 is used to determine constraints.
- the module 106 includes a model 108 of the environment, a submodule 110 for determining a user command probability, a submodule 112 for checking the feasibility of action sequences and a submodule 114 for storing determined constraints, such as 116, 118, 120.
- the module 106 is continuously executed in the background and uses environmental information 122, in particular information about a state of the robot 124, about a state of parts of the robot 124 and / or about a state of objects present in a work area of the robot 124, such as 126.
- the environmental information 122 is updated regularly.
- those action goals 128, 130, 132 are determined that a user 134 is most likely to select and these are acted upon probable action goals 128, 130, 132 directed preparation action sequences generated.
- these preparatory action sequences are carried out and tested, taking into account both objects 126 of the environment and a position of the robot 124, in particular with regard to obstacles such as 135, and possible collisions, in order to find feasible ways to achieve the action goals 128, 130, 132 to determine the obstacles 135 or areas outside a robot workspace.
- the object-dependent constraints 1 16, 1 18, 120, which limit the possible paths to achieving the action goals 128, 130, 132, are determined and stored using the submodule 1 14.
- the user 134 selects one of the action goals 128, 130, 132, whereupon a corresponding execution action sequence 136 is executed.
- the robot 124 is controlled autonomously in a user-monitored manner using a user interface 138 in shared control 140 or using a greedy algorithm 142 in monitored autonomy 144.
- the shared control input commands 140 and the supervised autonomy input commands 144 use the same action representation. This means that a seamless change between shared control 140 and monitored autonomy 144 can take place with immediate effect during the execution of the execution action sequence 136, which is indicated in time course 146 in FIG.
- FIG. 2 shows feasibility tests with simulated trajectories 200, 202, 204 in preparation for task execution using the example of a gripping task.
- the task is to create a feasible sequence of actions to achieve one a robot 206 placed cup 208 to find.
- the arrangement of the cup 208 in front of the robot 206 is shown in A.
- B, C and D show three scenarios with a bottle 210 as an obstacle. In scenario B there is no obstacle.
- scenario C an obstacle 212 lies in the periphery of the workspace 214.
- an obstacle 212 lies on a direct path between robot 206 and cup 208.
- a boundary 216 of the areas 218 in which a feasible action sequence can be carried out using the method according to the invention or can be found is shown in B, C and D with a dashed line.
- the areas 218 in C and D are each a subset of the area 218 in B.
- the starting position of the robot 206 and the position of the cup 208 to be gripped are determined and the objects are localized by detection.
- Preparatory action sequences are then created, executed and tested using the method according to the invention.
- trajectories 200, 202, 204 are scanned in two phases: First, in an exploration phase, an attempt is made to connect a starting position with action-related poses from the work space 214. such as B. Approach pose and grasping pose. The workspace 214 is completely scanned and updated after each scan until a feasible first trajectory section is found. If a feasible first trajectory section exists, the full scan is terminated and a control planner searches the local environment of this first trajectory section in an exploration phase, with the planner attempting to only add further approach and grasping poses. This continues up to the boundaries 216 of the area 218. The plan is complete if the distance is greater than a predetermined threshold. If this is not the case, the exploration phase is restarted. Exemplary trajectories 202, 204 with obstacle 212 are shown in B and C.
- May refers in particular to optional features of the invention. Accordingly, there are also further developments and/or exemplary embodiments of the invention which additionally or alternatively have the respective feature or features.
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Manipulator (AREA)
Abstract
Description
Claims
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE112023002127.9T DE112023002127A5 (de) | 2022-05-06 | 2023-05-05 | Verfahren zum vorbereiten und ausführen von aufgaben mithilfe eines roboters, roboter und computerprogramm |
| US18/863,253 US20250303565A1 (en) | 2022-05-06 | 2023-05-05 | Method for preparing and carrying out tasks by means of a robot, robot, and computer program |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE102022111400.7 | 2022-05-06 | ||
| DE102022111400.7A DE102022111400A1 (de) | 2022-05-06 | 2022-05-06 | Verfahren zum Vorbereiten und Ausführen von Aufgaben mithilfe eines Roboters, Roboter und Computerprogramm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2023213989A1 true WO2023213989A1 (de) | 2023-11-09 |
Family
ID=86378590
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/EP2023/061892 Ceased WO2023213989A1 (de) | 2022-05-06 | 2023-05-05 | Verfahren zum vorbereiten und ausführen von aufgaben mithilfe eines roboters, roboter und computerprogramm |
Country Status (3)
| Country | Link |
|---|---|
| US (1) | US20250303565A1 (de) |
| DE (2) | DE102022111400A1 (de) |
| WO (1) | WO2023213989A1 (de) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102017209032A1 (de) | 2017-05-30 | 2018-12-06 | Deutsches Zentrum für Luft- und Raumfahrt e.V. | Verfahren zum Steuern eines Roboters |
| WO2021040958A1 (en) * | 2019-08-23 | 2021-03-04 | Carrier Corporation | System and method for early event detection using generative and discriminative machine learning models |
| US20210200219A1 (en) * | 2019-12-26 | 2021-07-01 | X Development Llc | Robot plan online adjustment |
| DE102021104883B3 (de) | 2021-03-01 | 2022-06-15 | Deutsches Zentrum für Luft- und Raumfahrt e.V. | Verfahren zum roboterunterstützten Ausführen von Aufgaben, Roboter zum Unterstützen eines Benutzers beim Ausführen von Aufgaben und Computerprogrammprodukt |
Family Cites Families (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002034478A1 (fr) * | 2000-10-23 | 2002-05-02 | Sony Corporation | Robot pourvu de jambes, procede de commande du comportement d"un tel robot, et support de donnees |
| CN103433923A (zh) | 2007-01-12 | 2013-12-11 | 汉斯乔格·巴尔特斯 | 用于产生机器人的方法和系统 |
| US20100017026A1 (en) | 2008-07-21 | 2010-01-21 | Honeywell International Inc. | Robotic system with simulation and mission partitions |
| JP2012232363A (ja) * | 2011-04-28 | 2012-11-29 | Seiko Epson Corp | ロボット制御システム、ロボットシステム及びプログラム |
| US9358687B2 (en) | 2013-01-24 | 2016-06-07 | Mohammad Reza Emami | System, method and computer program for autonomously emulating robot manipulators of continuously-varying configurations |
| JP5862611B2 (ja) * | 2013-04-02 | 2016-02-16 | トヨタ自動車株式会社 | 作業変更装置、作業変更方法、及び作業変更プログラム |
| CN108602190B (zh) * | 2016-02-05 | 2022-02-18 | Abb瑞士股份有限公司 | 使用交互式命令控制工业机器人 |
| KR101858108B1 (ko) * | 2016-12-26 | 2018-05-16 | 한국생산기술연구원 | 로봇을 위한 동작 시뮬레이션 장치 및 방법 |
| EP3703604B1 (de) * | 2017-10-30 | 2025-08-06 | Intuitive Surgical Operations, Inc. | Systeme zur auswahl der platzierung von geführten ports |
| CN110297697B (zh) | 2018-03-21 | 2022-02-18 | 北京猎户星空科技有限公司 | 机器人动作序列生成方法和装置 |
| EP3587045A1 (de) | 2018-06-28 | 2020-01-01 | Siemens Aktiengesellschaft | Verfahren und vorrichtung zum rechnergestützten ermitteln von regelparametern für eine günstige handlung eines technischen systems |
| KR20220159392A (ko) * | 2020-03-27 | 2022-12-02 | 마코 서지컬 코포레이션 | 햅틱 인터페이스를 이용한 로봇 척추 수술 시스템 및 방법 |
| EP3978202A1 (de) | 2020-10-05 | 2022-04-06 | Siemens Aktiengesellschaft | Planen eines technischen prozesses aufweisend hierarchisch gegliederte aufgaben und parallelisierungsoptionen |
| DE102022104525B4 (de) * | 2022-02-25 | 2024-11-07 | Deutsches Zentrum für Luft- und Raumfahrt e.V. | Verfahren und Roboter zum Ausführen von Aufgaben und Computerprogramm |
| CA3214432A1 (en) * | 2022-09-27 | 2024-03-27 | Sanctuary Cognitive Systems Corporation | Systems, methods, and computer program products for automating tasks |
| WO2026006854A2 (en) * | 2024-06-28 | 2026-01-02 | Sarcos Corp. | Determination of task plans for robotic devices |
-
2022
- 2022-05-06 DE DE102022111400.7A patent/DE102022111400A1/de not_active Withdrawn
-
2023
- 2023-05-05 WO PCT/EP2023/061892 patent/WO2023213989A1/de not_active Ceased
- 2023-05-05 DE DE112023002127.9T patent/DE112023002127A5/de active Pending
- 2023-05-05 US US18/863,253 patent/US20250303565A1/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102017209032A1 (de) | 2017-05-30 | 2018-12-06 | Deutsches Zentrum für Luft- und Raumfahrt e.V. | Verfahren zum Steuern eines Roboters |
| WO2021040958A1 (en) * | 2019-08-23 | 2021-03-04 | Carrier Corporation | System and method for early event detection using generative and discriminative machine learning models |
| US20210200219A1 (en) * | 2019-12-26 | 2021-07-01 | X Development Llc | Robot plan online adjustment |
| DE102021104883B3 (de) | 2021-03-01 | 2022-06-15 | Deutsches Zentrum für Luft- und Raumfahrt e.V. | Verfahren zum roboterunterstützten Ausführen von Aufgaben, Roboter zum Unterstützen eines Benutzers beim Ausführen von Aufgaben und Computerprogrammprodukt |
Non-Patent Citations (7)
| Title |
|---|
| BUSTAMANTE SAMUEL ET AL: "Toward Seamless Transitions Between Shared Control and Supervised Autonomy in Robotic Assistance", IEEE ROBOTICS AND AUTOMATION LETTERS, IEEE, vol. 6, no. 2, 8 March 2021 (2021-03-08), pages 3833 - 3840, XP011847377, DOI: 10.1109/LRA.2021.3064449 * |
| D. S. LEIDNER: "Springer Tracts in Advanced Robotics", vol. 127, 2019, CHAM: SPRINGER INTERNATIONAL PUBLISHING, article "Cognitive Reasoning for Compliant Robot Manipulation" |
| DONGJIE LI ET AL: "Path planning research and simulation of planar 3R redundant robot", INDUSTRIAL ELECTRONICS AND APPLICATIONS, 2009. ICIEA 2009. 4TH IEEE CONFERENCE ON, IEEE, PISCATAWAY, NJ, USA, 25 May 2009 (2009-05-25), pages 2855 - 2858, XP031482558, ISBN: 978-1-4244-2799-4 * |
| G. QUEREA. HAGENGRUBERM. ISKANDARS. BUSTAMANTED. LEIDNERF. STULPJ. VOGEL: "Shared Control Templates for Assistive Robotics", 2020 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA, 2020, pages 7 |
| HUANG CHIEN-MING ET AL: "Anticipatory robot control for efficient human-robot collaboration", 2016 11TH ACM/IEEE INTERNATIONAL CONFERENCE ON HUMAN-ROBOT INTERACTION (HRI), IEEE, 7 March 2016 (2016-03-07), pages 83 - 90, XP032891047, DOI: 10.1109/HRI.2016.7451737 * |
| QUERE GABRIEL ET AL: "Shared Control Templates for Assistive Robotics", 2020 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), IEEE, 31 May 2020 (2020-05-31), pages 1956 - 1962, XP033826378, DOI: 10.1109/ICRA40945.2020.9197041 * |
| S. BUSTAMANTEG. QUEREK. HAGMANNX. WUP. SCHMAUSJ. VOGELF. STULPD. LEIDNER: "Toward seamless transitions between shared control and supervised autonomy in robotic assistance", IEEE ROBOTICS AND AUTOMATION LETTERS, vol. 6, no. 2, 2021, pages 3833 - 3840, XP011847377, DOI: 10.1109/LRA.2021.3064449 |
Also Published As
| Publication number | Publication date |
|---|---|
| DE112023002127A5 (de) | 2025-02-20 |
| US20250303565A1 (en) | 2025-10-02 |
| DE102022111400A1 (de) | 2023-11-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DE112018002565B4 (de) | System und Verfahren zum direkten Anlernen eines Roboters | |
| EP3623116A1 (de) | Verfahren und vorrichtung zur kollisionsfreien bewegungsplanung eines manipulators | |
| DE102019203214B4 (de) | Verfahren zum Betreiben eines Roboters in einem Multiagentensystem, Roboter und Multiagentensystem | |
| DE102019205651B3 (de) | Verfahren und System zum Ausführen von Roboterapplikationen | |
| DE102020212658A1 (de) | Vorrichtung und Verfahren zum Steuern einer Robotervorrichtung | |
| DE112019007579T5 (de) | Numerische-Steuerung-Vorrichtung und Maschinelles-Lernen-Gerät | |
| EP3857324B1 (de) | Dynamische verfeinerung von markern in einem autonomen weltmodell | |
| DE102018218081A1 (de) | Vorrichtung und Verfahren zur Ansteuerung eines Robotersystems | |
| Liu et al. | Learning to cooperate together: A semi-autonomous control architecture for multi-robot teams in urban search and rescue | |
| DE112021007017T5 (de) | Numerik-Steuervorrichtung und Numerik-Steuersystem | |
| DE112019007750T5 (de) | Umgebungskarten- Erzeugungsvorrichtung und -Verfahren, Vorrichtung zum Schätzen der lokalen Position, und autonomer beweglicher Körper | |
| DE102020214177A1 (de) | Vorrichtung und Verfahren zum Trainieren einer Steuerungsstrategie mittels bestärkendem Lernen | |
| DE112022002107T5 (de) | Systeme, vorrichtungen und verfahren zur entwicklung autonomer roboter | |
| EP3771522A1 (de) | Verfahren und manipulationssystem zur manipulation eines objekts durch einen roboter mittels vektorfelder | |
| DE102021104883B3 (de) | Verfahren zum roboterunterstützten Ausführen von Aufgaben, Roboter zum Unterstützen eines Benutzers beim Ausführen von Aufgaben und Computerprogrammprodukt | |
| WO2023161141A1 (de) | Verfahren und roboter zum ausführen von aufgaben und computerprogramm | |
| EP3812106B1 (de) | Roboteranordnung, verfahren zum betreiben der roboteranordnung, computerprogramm sowie maschinenlesbares speichermedium | |
| EP3760390B1 (de) | Durchführen einer vorgegebenen aufgabe mithilfe wenigstens eines roboters | |
| EP4449217A1 (de) | Zuweisen einer aufgabe an einen örtlich entfernten experten | |
| DE102022111400A1 (de) | Verfahren zum Vorbereiten und Ausführen von Aufgaben mithilfe eines Roboters, Roboter und Computerprogramm | |
| DE102022207800A1 (de) | Verfahren zum Trainieren einer Steuerungsrichtlinie zur Steuerung eines technischen Systems | |
| EP3741518B1 (de) | Verfahren und vorrichtung für eine automatisierte beeinflussung eines aktuators | |
| DE112018007703T5 (de) | Robotersteuerung | |
| EP3710900B1 (de) | Verfahren und system zum vorgeben bzw. lernen eines roboterbefehls | |
| DE112024000656T5 (de) | Robotersteuerungssystem, Robotersteuerungsverfahren und Robotersteuerungsprogramm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 23723570 Country of ref document: EP Kind code of ref document: A1 |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 10202400001218 Country of ref document: CH |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 112023002127 Country of ref document: DE |
|
| REG | Reference to national code |
Ref country code: DE Ref legal event code: R225 Ref document number: 112023002127 Country of ref document: DE |
|
| WWP | Wipo information: published in national office |
Ref document number: 112023002127 Country of ref document: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 23723570 Country of ref document: EP Kind code of ref document: A1 |
|
| WWP | Wipo information: published in national office |
Ref document number: 18863253 Country of ref document: US |