CN111300451A - High-intelligence shape shifting robot - Google Patents
High-intelligence shape shifting robot Download PDFInfo
- Publication number
- CN111300451A CN111300451A CN202010197497.6A CN202010197497A CN111300451A CN 111300451 A CN111300451 A CN 111300451A CN 202010197497 A CN202010197497 A CN 202010197497A CN 111300451 A CN111300451 A CN 111300451A
- Authority
- CN
- China
- Prior art keywords
- robot
- module
- execution
- highly intelligent
- intelligent
- 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.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1602—Programme controls characterised by the control system, structure, architecture
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
- B25J9/1697—Vision controlled systems
Abstract
The invention relates to the field of intelligent robots, in particular to a high-intelligent deformation robot, which comprises: the scene selection module is used for selecting different task scenes and extracting corresponding task information and executing actions; the navigation module is used for carrying out navigation control on the walking path according to the external environment information; the attitude change module is used for controlling the high-intelligent deformation robot to change the attitude in the navigation control process; the operation module is used for controlling the high-intelligence deformation robot to execute corresponding operation actions when the high-intelligence deformation robot moves to the execution position determined in the task information; and the execution module is used for controlling the driving motors of the mechanical limbs according to the control instructions output by the modules, so that the high-intelligent deformation robot is controlled to perform path navigation, posture change and corresponding operation action. The beneficial effects of the above technical scheme are: the self-adaptive control and switching of the humanoid robot between the standing posture and other postures according to tasks and scene change are achieved, and various tasks in the scene can be automatically completed according to external instructions.
Description
Technical Field
The invention relates to the field of intelligent robots, in particular to a high-intelligence deformable robot.
Background
In the prior art, the standing type humanoid robot can process complex and fine work due to the fact that the standing type humanoid robot comprises a complex mechanical arm and a body structure similar to a human body, and the crawling robot in the special-shaped robot can overcome walking obstacles in a complex environment and is limited in capability of completing high-precision operation tasks.
In the prior art, some deformation schemes exist for a humanoid robot, namely the robot is changed between a standing posture and other postures, but in the prior art, the posture of the robot is usually changed by an operator manually sending an instruction, the change mode is rigid, and the posture cannot be automatically changed according to the change of tasks or scenes, so that the application range of the robot is greatly limited, and the operation mode is complex.
With the continuous development of the robot application technology, a technical scheme that the robot setting can take the advantages of the two robots into consideration and the robot can change the posture in a self-adaptive manner due to different environments is urgently needed.
Disclosure of Invention
The invention provides a high-intelligent deformable robot, aiming at solving the problems that a human robot cannot change postures in a self-adaptive manner according to tasks and scene changes and can automatically complete various tasks in a scene according to external instructions.
The technical scheme specifically comprises the following steps:
a high-intelligence deformable robot comprises a main body, a head and a plurality of mechanical limbs, wherein a sensing unit is arranged in the head, a central control unit is arranged in the main body, and the central control unit is respectively connected with the mechanical limbs and the sensing unit;
the head is arranged above the main body;
the mechanical limbs include:
the first mechanical leg is connected with the left bottom of the main body in a steering way through a first connecting shaft;
the second mechanical leg is connected with the bottom of the right side of the main body in a steering way through a second connecting shaft;
the middle end of the first mechanical arm is provided with a first supporting part, and the first mechanical arm is connected with the top of the left side of the main body in a steering manner through a third connecting shaft;
the middle end of the second mechanical arm is provided with a second supporting part, and the second mechanical arm is connected with the top of the right side of the main body in a steering manner through a fourth connecting shaft;
the central control unit is internally preset with task information and execution actions respectively related to different task scenes, and comprises:
the scene selection module is used for selecting different task scenes according to an externally input instruction and extracting corresponding task information and the execution action according to the selected character scene;
the navigation module is used for carrying out navigation control on the walking path of the high-intelligent deformation robot according to the external environment information transmitted by the sensing unit;
the attitude change module is respectively connected with the scene selection module and the navigation module and is used for controlling the highly intelligent deformable robot to change the attitude according to the external environment information and the task information in the process of navigation control;
the operation module is connected with the scene selection module and used for controlling the highly intelligent deformation robot to execute corresponding operation actions according to the external environment information and the execution actions when the highly intelligent deformation robot moves to the execution position determined in the task information;
and the execution module is respectively connected with the navigation module, the attitude change module and the operation module, and is also connected with the driving motors of the mechanical limbs and is used for controlling the driving motors of the mechanical limbs according to the control instructions output by the modules so as to control the high-intelligent deformation robot to perform path navigation, attitude change and execute corresponding operation actions.
Preferably, the high-intelligence deformation robot is characterized in that a mechanical claw is arranged on each of the first mechanical arm and the second mechanical arm, and the mechanical claws are respectively arranged at the front end of the first mechanical arm and the front end of the second mechanical arm.
Preferably, the first mechanical arm and the second mechanical arm further include a plurality of joints, the joints and the gripper are respectively connected to one driving motor, and the driving motors are used for driving the joints and the gripper to rotate so as to control the highly intelligent deformable robot to change the posture and execute the operation action.
Preferably, the highly intelligent shape-changing robot, wherein the executing module comprises:
the torque calculation component is used for monitoring the real-time torque of the driving motor corresponding to each joint in real time, comparing the real-time torque with a corresponding preset torque stored in advance, and correcting the real-time torque according to the preset torque;
and the motor control component is connected with the torque calculation component and used for controlling the driving motor according to the corrected real-time torque so as to enable each joint and each mechanical claw to be positioned on the corresponding motion track.
Preferably, the highly intelligent deformable robot, wherein the navigation module comprises:
the model building component is used for building an external environment model where the highly intelligent deformation robot is currently located according to the external environment information;
the object capturing component is used for continuously capturing an execution object corresponding to the task scene according to the external environment information and the task information;
and the path planning component is respectively connected with the model building component and the object capturing component and used for constructing a walking path from the current position of the high-intelligence deformation robot to the position of the execution object in real time according to the external environment model and the execution object and outputting a corresponding control instruction in real time according to the walking path.
Preferably, the highly intelligent deformable robot includes the execution target and an operation posture of the highly intelligent deformable robot when the execution target is operated in the task information;
the attitude change module controls the highly intelligent transformable robot to change the attitude according to the operation attitude.
Preferably, the high-intelligence deformable robot further comprises:
the obstacle avoidance component is respectively connected with the model building component and the path planning component and is used for detecting in real time according to the external environment model and the walking path to obtain obstacle information;
the path planning component adjusts the walking path of the high-intelligent deformation robot in real time according to the obstacle information;
and the attitude change module controls the highly intelligent deformable robot to change the attitude according to the obstacle information so that the highly intelligent deformable robot smoothly passes through the obstacle.
Preferably, the highly intelligent robot comprises a state feedback sensor arranged at the end of each mechanical limb of the highly intelligent robot, and when the highly intelligent robot executes an operation action, the state feedback sensor feeds back the current execution state to the central control unit;
the operation module specifically includes:
an operation feedback section for continuously acquiring the execution state;
an operation adjusting component connected with the operation feedback component and used for:
adjusting a control command related to an operation action when the execution state indicates that the operation action cannot be completed temporarily; and
and outputting a control instruction for abandoning the execution of the operation action when the execution state indicates that the operation action cannot be realized.
Preferably, the sensing unit comprises an environment acquisition module and a head control module, the environment acquisition module is used for acquiring the external environment information, and the head control module is connected with the environment acquisition module and is used for sending the external environment information to the central control unit;
the environment acquisition module comprises a plurality of sensing devices, the plurality of sensing devices at least comprise four cameras, the four cameras are all arranged on the front side of the head and are all used for acquiring the surrounding environment information of the high-intelligence deformation robot;
the head control module includes the ambient environment data in the external environment information and transmits to the central control unit.
Preferably, the highly intelligent shape-changing robot further comprises:
the radar device is arranged above the head, two camera devices are respectively arranged on two sides of the radar device, and the radar device drives the camera devices to rotate at a constant speed;
the radar device is used for detecting distance information around the high-intelligence deformation robot;
one camera device is used for detecting remote environment information of the high-intelligence deformation robot;
the other camera device is used for detecting the near environment information of the high-intelligence deformation robot;
the head control module includes the distance information, the far environment information, and the near environment information in the external environment information and transmits to the central control unit.
The beneficial effects of the above technical scheme are that: the technical scheme of the high-intelligent deformable robot is provided, the problem that the human robot performs self-adaptive adjustment and switching between a standing type posture and other postures according to tasks and scene change can be solved, and various tasks in a scene can be automatically completed according to external instructions.
Drawings
FIG. 1 is a vertical structure diagram of the high intelligent deformation robot provided by the invention;
FIG. 2 is a top-down configuration diagram of a highly intelligent deformable robot in accordance with a preferred embodiment of the present invention;
FIG. 3 is a schematic diagram of the system framework of the highly intelligent deformable robot in the preferred embodiment of the present invention;
FIG. 4 is a block diagram illustrating an embodiment of an execution module according to the present invention;
FIG. 5 is a schematic diagram of a navigation module according to a preferred embodiment of the present invention; FIG. 6 is a schematic diagram of an exemplary embodiment of an operation module.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
The invention is further described with reference to the following drawings and specific examples, which are not intended to be limiting.
In a preferred embodiment of the present invention, in order to solve the above problems in the prior art, a solution of a highly intelligent transformable robot is provided, which specifically includes a main body 1, a head 2 and a plurality of mechanical limbs, wherein the head 2 is internally provided with a sensing unit a, the main body 1 is internally provided with a central control unit B, and the central control unit B is respectively connected to each mechanical limb and the sensing unit a;
the head 2 is arranged above the main body 1;
the mechanical limbs comprise:
a first mechanical leg 3 rotatably connected to the left bottom of the main body 1 via a first connecting shaft 01;
a second mechanical leg 4 rotatably connected to the bottom of the right side of the main body 1 by a second connecting shaft 02;
the middle end of the first mechanical arm 7 is provided with a first supporting part 5, and the first mechanical arm 7 is rotatably connected with the top of the left side of the main body 1 through a third connecting shaft 03;
a second mechanical arm 8, wherein a second supporting part 6 is arranged at the middle end of the second mechanical arm 8, and the second mechanical arm 8 is rotatably connected with the top of the right side of the main body 1 through a fourth connecting shaft 04;
the ends of the first and second legs 3 and 4 may be crawler structures or other rigid structures capable of supporting the movement of the robot. The difference of the end structures of the mechanical diagrams only brings about the difference of the moving modes of the high-intelligence deformation robot, and the realization principle of the technical scheme of the invention can not be changed at all, so the invention is in the protection scope.
The central control unit B is internally preset with task information and execution actions respectively related to different task scenes, and comprises the following components:
the scene selection module B1 is used for selecting different task scenes according to an externally input instruction, and extracting corresponding task information and executing actions according to the selected character scenes;
the navigation module B2 is used for carrying out navigation control on the walking path of the high-intelligence deformable robot according to the external environment information transmitted by the sensing unit A;
the attitude change module B3 is respectively connected with the scene selection module B1 and the navigation module B2 and is used for controlling the highly intelligent deformable robot to change the attitude according to the external environment information and the task information in the navigation control process;
the operation module B4 is connected with the scene selection module B1 and is used for controlling the high intelligent deformation robot to execute the corresponding operation action according to the external environment information and the execution action when the high intelligent deformation robot moves to the execution position determined in the task information;
and the execution module B5 is respectively connected with the navigation module B2, the posture change module B3 and the operation module B4, and the execution module B5 is also connected with the driving motors of all the mechanical limbs and is used for controlling the driving motors of all the mechanical limbs according to the control commands output by all the modules, so that the high-intelligence deformable robot is controlled to perform path navigation, posture change and corresponding operation action.
Further, as shown in fig. 1-2, an environment acquisition module a1 is disposed in the sensing unit a in the head 2, the environment acquisition module a is used for acquiring the surrounding environment, and the central control unit B is used for controlling the highly intelligent deformable robot to perform posture change and self-adjustment of the walking path according to the signal (external environment information) transmitted by the environment acquisition module a.
Specifically, environment collection module A1 gathers the robot surrounding environment and sends to central control unit B through a head control module A2, then central control unit B turns to first connecting axle 01, second connecting axle 02, third connecting axle 03 and fourth connecting axle 04 according to the external environment information of gathering to realize carrying out different automatic deformations to high intelligent deformation robot under the different scenes, with the demand under the different scenes of adaptation.
Further, the environment acquisition module A1 comprises a plurality of sensing devices, specifically a plurality of cameras 22-25, and the four cameras 22-25 are respectively installed on the front side of the head of the highly intelligent deformable robot for detecting the surrounding environment information of the highly intelligent deformable robot. The positions of the four cameras 22-25 and the camera parameters (such as the view angles and the like) are all fixed, namely, the video data/distance data around the high-intelligence deformable robot are continuously detected in the process of traveling of the robot, and the surrounding environment information is obtained. The head control module includes the ambient environment information in the external environment information and transmits to the central control unit.
Of course, in other embodiments of the present invention, in order to more comprehensively detect the surrounding environment information of the highly intelligent deformable robot, the four or even multiple cameras may be respectively installed around the head of the highly intelligent deformable robot and the camera parameters are fixed, which is not described herein again.
Further, the plurality of sensing devices further include:
a radar device 26, wherein the radar device 26 is arranged above the head 2, two camera devices 27 and 28 are respectively arranged on two sides of the radar device 26, and the radar device 26 drives the camera devices 27 and 28 to rotate at a constant speed;
the radar device 26 is used for detecting distance information around the high-intelligent deformation robot;
one camera device is used for detecting the remote environment information of the high-intelligent deformation robot;
the other camera device is used for detecting the near environment information of the high-intelligent deformation robot;
the head control module includes the distance information, the far environment information, and the near environment information in the external environment information and transmits to the central control unit.
The remote environment information may be, for example, wide-angle video image data/ranging data right in front of the robot, i.e., the angle of view of one of the cameras is forward. The near environment information may be, for example, when the robot is operating a tool in a hand, i.e. with one of the cameras facing downwards, and may be used to obtain video image data/ranging data of the tool.
Specifically, the robot realizes the collection of the external environment information of the robot through a plurality of cameras of the head 2, and transmits the collected information to the central control module, and the central control module carries out the deformation of different states to the robot according to the received information and the preset walking path, thereby realizing the automatic deformation of the robot. And through the detection of the radar device 26, the environment around the robot can be collected at 360 degrees without dead angles, more accurate environment information is obtained, and the automatic deformation of the robot in different postures is further realized.
Further, the first mechanical arm 7 and the second mechanical arm 8 are in an eight-axis transmission structure.
A mechanical claw 9 is arranged on each of the first mechanical arm 7 and the second mechanical arm 8, and the mechanical claw 9 is respectively arranged at the front end of the first mechanical arm 7 and the front end of the second mechanical arm 8.
Specifically, the mechanical claw 9 is arranged on the mechanical arm, and the central control unit can control the mechanical claw 9 to work when the mechanical arm acts, so that the fine and complex work processing is realized.
Further, the first mechanical leg 3, the second mechanical leg 4, the first support part 5 and the second support part 6 are all connected with a plurality of driving motors, and the plurality of driving motors are used for driving the first mechanical leg 3, the second mechanical leg 4, the first support part 5 and the second support part 6 so as to move the automatic deformation robot.
Furthermore, the first mechanical arm 7 and the second mechanical arm 8 further comprise a plurality of joints, the joints and the mechanical claw 9 are respectively connected with a driving motor, and the driving motors are used for driving the joints and the mechanical claw 9 to rotate so as to adjust the action of the automatic deformation robot.
In a preferred embodiment of the present invention, as shown in fig. 4, the execution module B5 includes:
the torque calculation component B51 is used for monitoring the real-time torque of the driving motor corresponding to each joint in real time, comparing the real-time torque with the corresponding preset torque stored in advance, and correcting the real-time torque according to the preset torque;
and the motor control part B52 is connected with the torque calculation part B51 and is used for controlling the driving motor according to the corrected real-time torque so as to enable each joint and each mechanical claw to be positioned on the corresponding motion track.
Specifically, the execution module B5 detects real-time torques of the driving motors corresponding to the respective joints in real time during the control of the respective joints of the highly intelligent deformable robot. Meanwhile, preset torques related to various operations of each joint are preset in the execution module B5, and the preset torques refer to standard torques defining the driving motors of each joint when executing various operation actions. The real-time torque of the driving motor corresponding to each joint detected in real time is compared with the corresponding preset torque under the operation action by the execution module B5, the real-time torque is corrected according to the preset torque, real-time motion correction is carried out on the head and the mechanical limbs of the high-intelligence deformation robot, all parts such as each joint and a mechanical claw are guaranteed to operate on the correct motion track, and the situation that the incorrect motion track exceeds the motion range of the parts of the high-intelligence deformation robot to cause the damage of the parts can be avoided.
The basic mechanical constitution and the principle of mechanical movement of the highly intelligent deformation robot are introduced above, and the control principle of the highly intelligent deformation robot is described in detail below.
As shown in fig. 3, the control of the highly intelligent deformable robot is divided into a control process of the sensing unit a and a control process of the central control unit B:
the plurality of sensing devices of the environment collection module a1 in the sensing unit a collect external environment information respectively and transmit to the central control unit B via the head control module a 2. The external environment information may include wide-view far environment information, narrow-view near environment information, and surrounding distance information acquired by a camera. The header control module a2 includes the above information in the external environment information and packetizes and transmits to the central control unit B. The process is continuously carried out in the running process of the high-intelligence deformation robot, namely, the external environment information around the high-intelligence deformation robot is continuously detected for subsequent model building and navigation.
The central control unit B is mainly responsible for the following processes:
1) the scene selection module B1 is preset with a plurality of task information and execution actions associated with different task scenes, where the task information may include an execution object of a task, and the execution action may be what kind of operation is performed on the execution object. The task information and the execution action can be set by teaching the high-intelligence deformable robot in advance. The scene selection module B1 selects a different task scene according to the externally input instruction, thereby determining different task information and performing an action. For example, the scene selection module B1 stores task information and execution actions of a task scene "robot opens door" in a previously taught manner. The task information may include image features of the object data "door", and image features of various components on the "door" that need to be used, such as "door handle", "door frame", and the like. The executing action may be to control the robot to execute a door opening operation, and further may include to control the robot to execute a series of decomposed sub-actions, such as "turn the door handle", "pull the door handle inward/outward", "hold the door frame", "pull the door handle hard", and the like.
2) The navigation module B2 performs 3D aggregate analysis according to the external environment information transmitted from the sensing unit a of the head 2, thereby performing 3D modeling of an unfamiliar scene. Because the collection and transmission of external environment information are continuously carried out, a 3D high-precision map obtained by 3D modeling is continuously updated, and a high-intelligent deformation robot can sense the change of the surrounding environment.
3) And the posture change module B3 controls the robot to change the posture in the advancing process of the high-intelligent deformation robot according to the 3D high-precision map obtained by the 3D modeling and continuous updating so as to perform adaptive adjustment on the task scene. The process of pose change is detailed below.
4) When the highly intelligent deformable robot moves to the execution position (usually, the position of the execution object) designated by the task information, the operation module B4 controls the highly intelligent deformable robot to perform the corresponding operation on the execution object at the execution position according to the execution action corresponding to the task scene.
5) The processed outputs of the navigation module B2, the posture change module B3 and the operation module B4 are control commands, and the execution module B5 sends actual control signals to the driving motors on the joints of the trunk and the head of the high-intelligence deformable robot according to the control commands output by different modules, controls the joints to move, and can control the high-intelligence deformable robot to complete corresponding movement, posture change, operation actions and the like. In other words, the navigation module B2, the posture change module B3 and the operation module B4 are all configured to output related control commands, and the execution module B5 is configured to perform bottom layer operations according to the control commands, that is, directly control the related driving motors to execute the operations.
Further, in a preferred embodiment of the present invention, as shown in fig. 5, the navigation module B2 includes:
the model building component B21 is used for building an external environment model where the highly intelligent deformation robot is currently located according to the external environment information;
an object capturing unit B22 for continuously capturing an execution object corresponding to a task scene based on external environment information and task information;
and the path planning component B23 is respectively connected with the model building component B21 and the object capturing component B22 and is used for constructing a walking path from the current position of the highly intelligent deformation robot to the position of the execution object in real time according to the external environment model and the execution object and outputting a corresponding control command in real time according to the walking path.
The navigation module B2 further includes:
the obstacle avoidance component B24 is respectively connected with the model building component B21 and the path planning component B23 and is used for detecting in real time according to the external environment model and the walking path to obtain obstacle information;
and the path planning component adjusts the walking path of the high-intelligent deformable robot in real time according to the obstacle information.
Specifically, in this embodiment, the navigation module B2 mainly functions to:
1) as described above, a 3D high-precision map is built according to the external environment information transmitted by the sensing unit A, and an external environment model where the high-intelligent deformation robot is located currently is formed.
2) According to the task information corresponding to the selected task scene and the external environment information (video image data) transmitted by the sensing unit a, the object capturing component B22 can determine the position of the current execution object in the external environment model, and the path planning component B23 can plan the walking path between the position of the high intelligent deformation robot and the position of the execution object. And the object capturing unit B22 continuously updates the relative position of the execution object in the external environment model according to the change of the external environment model, the path planning unit B23 can continuously update the walking path. The walking path refers to the whole moving path of the high-intelligence deformation robot.
3) When the highly intelligent robot approaches the position where the execution object is located, the object capturing section B22 continues to capture the execution details of the execution object, and the path planning section B23 can plan the movement path between the part of the highly intelligent robot that operates the execution object and the corresponding detailed part on the execution object. Similarly, the object capture component B22 continuously updates the position of the detailed portion of the execution object according to the change of the external environment model, and the path planning component B23 can continuously update the movement path. The movement path herein refers to an individual movement path of a part of the highly intelligent robot which operates the execution object, and is not an overall movement path of the highly intelligent robot.
4) The obstacle avoidance component B24 can detect and obtain the obstacle information which is possibly encountered by the high-intelligent deformable robot in the moving process according to the external environment model and the current walking path, and the obstacle information is fed back to the path planning component B23 to adjust the walking path, so that the obstacle avoidance function of the high-intelligent deformable robot is realized.
The function of the navigation unit B2 and the overall operation principle of the highly intelligent deformable robot are also described below by taking the task scenario of "robot door opening" as an example:
when the high-intelligence deformation robot receives an instruction input from the outside and indicates the high-intelligence deformation robot to open the door, the high-intelligence deformation robot firstly carries out 3D clustering analysis through external environment information to obtain a 3D external environment model, and processes the external environment model to obtain the position of the door of an execution object, and the image characteristics of the object data can be obtained from preset task information.
And then the path planning component B23 begins to plan the walking path of the highly intelligent deformable robot moving to the position of the execution object 'door', and outputs a control instruction to control the highly intelligent deformable robot to move, thereby realizing the function of obstacle avoidance in the moving process.
When the highly intelligent deformation robot is far away from the door of the execution object, the acquired image data related to the execution object is fuzzy and rough, and the positioning is generally coarse positioning. As the highly intelligent deformable robot is closer to the execution object "door", the image data associated with the execution object obtained by the highly intelligent deformable robot becomes clearer, and thus the accuracy of positioning is gradually improved.
When the highly intelligent robot moves to a position sufficiently close to the execution object "door", the highly intelligent robot stops moving as a whole, and controls the first robot arm 7 and/or the second robot arm 8 to move toward the door knob "and the door frame" which are the detailed parts of the execution object "door", at which time the object to be captured by the object capturing part B22 is changed from the whole execution object "door" to the door knob "and the door frame" which are the detailed parts, until the first robot arm 7 and/or the second robot arm 8 come into contact with the door knob and/or the door frame. The operation block B4 then begins to control the highly intelligent deformable robot to perform the associated door opening operation.
In a preferred embodiment of the present invention, the gesture change triggering conditions of the highly intelligent deformable robot can be various, and specifically include:
1) when the task information includes the execution target and the operation posture of the highly intelligent robot when the execution target is operated, the posture change module B4 controls the highly intelligent robot to change the posture according to the operation posture. Such pose changes are implemented according to the task scenario. For example, if the highly intelligent transformable robot must be in a standing position (as shown in fig. 1) when performing the "robot door opening" action, if the highly intelligent transformable robot is still in another posture such as a prone posture (as shown in fig. 2) when it is located at a position where an execution object is located and starts to perform the relevant door opening operation, the posture must be first changed to a standing position before performing the subsequent operation.
Or the high-intelligent deformable robot can be taught in a mode of teaching in advance to realize a unique ladder climbing task. In the task of climbing a ladder, the high intelligent deformable robot needs to imitate the action of a human climbing ladder, and adopts mechanical claws to hook the steps of the ladder and climb upwards with the bow, which is a special climbing ladder type gesture (not shown in the figure). When the highly intelligent transformable robot moves to the position where the ladder is located, it is controlled to transform into a ladder-like posture, and then the ladder-climbing operation is performed.
In summary, the triggering condition can be summarized as adaptively triggering posture deformation according to a task scene, so that the high-intelligence deformable robot can smoothly complete an execution task in the task scene.
2) And the posture change module B4 controls the high-intelligence deformable robot to change the posture according to the obstacle information so that the high-intelligence deformable robot smoothly passes through the obstacle. Such pose changes are made temporally in accordance with obstacles that appear in the task scene. Although the navigation module B2 has some obstacle avoidance function as described above, it is not excluded that some large obstacles are present in the task scenario and cannot be avoided simply by "detour". In this case, the posture change module B4 can determine whether or not the highly intelligent deformable robot needs to change the posture based on the obstacle information (the position, size, etc. of the obstacle), and control the highly intelligent deformable robot to change the posture to pass through the obstacle.
For example, there is an obstacle of a large size that cannot be bypassed in the walking path of the highly intelligent deformable robot, which is in a standing position (as shown in fig. 1). The posture change module B4 judges that the robot needs to be deformed at this time, and then it can control the high-intelligent deformable robot to change to a prone type (as shown in fig. 2) with a lower center of gravity and less possibility of falling down and pass through the obstacle. After passing through the obstacle, the posture change module B4 can selectively control the highly intelligent transformable robot to change back to the standing type, or does not need any control until the highly intelligent transformable robot moves to the position of the execution object.
In a preferred embodiment of the invention, the tail ends of the mechanical limbs of the high-intelligence deformable robot are respectively provided with a state feedback sensor, and when the high-intelligence deformable robot executes operation actions, the state feedback sensors feed back the current execution state to the central control unit;
as shown in fig. 6, the operation module B4 specifically includes:
an operation feedback section B41 for continuously acquiring the execution state;
an operation adjusting part B42 connected to the operation feedback part B41 for:
adjusting a control command related to the operation action when the execution state indicates that the operation action cannot be completed temporarily; and
and outputting a control instruction for abandoning the execution of the operation action when the execution state indicates that the operation action cannot be realized.
Specifically, in this embodiment, the state feedback sensor may be a force feedback sensor. Still taking the task scenario of "robot open door" as an example, when the highly intelligent robot is performing the "open door" action, the standard action is to use the manipulator to grasp the door handle and push the door, and in the initial state, the operation module B4 will provide an initial force to the manipulator (which can be obtained through the preset task information). The force feedback sensor at the end of the robot now transmits feedback to operator block B4 to provide to operator block B4 to determine the corresponding actuation state (whether the door is being pushed open).
If the current execution state indicates that the door is not being pushed open and the pushing force provided by manipulator module B4 is within a reasonable range (again, available through the pre-set task information), manipulator module B4 will increase the force provided to the manipulator such that the manipulator applies a greater force to push the door.
If the current execution state indicates that the door is not opened and the pushing force provided by the operation module B4 exceeds the above reasonable range, the operation module B4 determines that the operation (the robot opens the door) cannot be executed smoothly, and at this time, the operation module B4 sends out a control command for abandoning the execution to control the high intelligent deformation robot to abandon the operation, and the mechanical limbs of the high intelligent deformation robot return to the initial state.
The state feedback sensor and the corresponding state feedback and execution action adjusting mechanism are arranged, and the purpose is as follows: 1) the problem that the high-intelligent deformation robot cannot complete tasks is avoided; 2) the damage to parts caused by continuous trying of the high-intelligence deformation robot to complete the task is avoided.
In summary, the technical solution of the present invention provides a highly intelligent deformable robot, which can adaptively change the posture of the robot according to a task scene corresponding to an externally input command, and automatically navigate to complete the operation actions specified in the task scene, thereby solving the problem that most robots in the prior art are hard to execute tasks and cannot adapt to different scenes.
While the invention has been described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention.
Claims (10)
1. A high-intelligence deformable robot is characterized by comprising a main body, a head and a plurality of mechanical limbs, wherein a sensing unit is arranged in the head, a central control unit is arranged in the main body, and the central control unit is respectively connected with the mechanical limbs and the sensing unit;
the head is arranged above the main body;
the mechanical limbs include:
the first mechanical leg is connected with the left bottom of the main body in a steering way through a first connecting shaft;
the second mechanical leg is connected with the bottom of the right side of the main body in a steering way through a second connecting shaft;
the middle end of the first mechanical arm is provided with a first supporting part, and the first mechanical arm is connected with the top of the left side of the main body in a steering manner through a third connecting shaft;
the middle end of the second mechanical arm is provided with a second supporting part, and the second mechanical arm is connected with the top of the right side of the main body in a steering manner through a fourth connecting shaft;
the central control unit is internally preset with task information and execution actions respectively related to different task scenes, and comprises:
the scene selection module is used for selecting different task scenes according to an externally input instruction and extracting corresponding task information and the execution action according to the selected character scene;
the navigation module is used for carrying out navigation control on the walking path of the high-intelligent deformation robot according to the external environment information transmitted by the sensing unit;
the attitude change module is respectively connected with the scene selection module and the navigation module and is used for controlling the highly intelligent deformable robot to change the attitude according to the external environment information and the task information in the process of navigation control;
the operation module is connected with the scene selection module and used for controlling the highly intelligent deformation robot to execute corresponding operation actions according to the external environment information and the execution actions when the highly intelligent deformation robot moves to the execution position determined in the task information;
and the execution module is respectively connected with the navigation module, the attitude change module and the operation module, and is also connected with the driving motors of the mechanical limbs and is used for controlling the driving motors of the mechanical limbs according to the control instructions output by the modules so as to control the high-intelligent deformation robot to perform path navigation, attitude change and execute corresponding operation actions.
2. The highly intelligent transformable robot of claim 1, wherein a gripper is mounted on each of the first robot arm and the second robot arm, and the grippers are respectively disposed at the front end of the first robot arm and the front end of the second robot arm.
3. The highly intelligent robot for deformation according to claim 2, wherein the first and second robot arms further comprise a plurality of joints, each of the joints and the gripper is connected to a driving motor, and the driving motors are used for driving the joints and the gripper to rotate so as to control the highly intelligent robot for posture change and operation.
4. The highly intelligent anamorphic robot of claim 3 wherein the execution module comprises:
the torque calculation component is used for monitoring the real-time torque of the driving motor corresponding to each joint in real time, comparing the real-time torque with a corresponding preset torque stored in advance, and correcting the real-time torque according to the preset torque;
and the motor control component is connected with the torque calculation component and used for controlling the driving motor according to the corrected real-time torque so as to enable each joint and each mechanical claw to be positioned on the corresponding motion track.
5. The highly intelligent transformable robot of claim 1, wherein the navigation module comprises:
the model building component is used for building an external environment model where the highly intelligent deformation robot is currently located according to the external environment information;
the object capturing component is used for continuously capturing an execution object corresponding to the task scene according to the external environment information and the task information;
and the path planning component is respectively connected with the model building component and the object capturing component and used for constructing a walking path from the current position of the high-intelligence deformation robot to the position of the execution object in real time according to the external environment model and the execution object and outputting a corresponding control instruction in real time according to the walking path.
6. The highly intelligent transformable robot according to claim 5, wherein the task information includes the execution object and an operation posture of the highly intelligent transformable robot when the execution object is operated;
the attitude change module controls the highly intelligent transformable robot to change the attitude according to the operation attitude.
7. The highly intelligent transformable robot of claim 5, further comprising in the navigation module:
the obstacle avoidance component is respectively connected with the model building component and the path planning component and is used for detecting in real time according to the external environment model and the walking path to obtain obstacle information;
the path planning component adjusts the walking path of the high-intelligent deformation robot in real time according to the obstacle information;
and the attitude change module controls the highly intelligent deformable robot to change the attitude according to the obstacle information so that the highly intelligent deformable robot smoothly passes through the obstacle.
8. The highly intelligent transformable robot of claim 1, wherein a state feedback sensor is provided at each end of the mechanical limbs of the highly intelligent transformable robot, and when the highly intelligent robot is performing an operation action, the state feedback sensor feeds back the current execution state to the central control unit;
the operation module specifically includes:
an operation feedback section for continuously acquiring the execution state;
an operation adjusting component connected with the operation feedback component and used for:
adjusting a control command related to an operation action when the execution state indicates that the operation action cannot be completed temporarily; and
and outputting a control instruction for abandoning the execution of the operation action when the execution state indicates that the operation action cannot be realized.
9. The highly intelligent transformable robot of claim 1, wherein the sensing unit comprises an environment acquisition module and a head control module, the environment acquisition module is used for acquiring the external environment information, and the head control module is connected with the environment acquisition module and is used for sending the external environment information to the central control unit;
the environment acquisition module comprises a plurality of sensing devices, the plurality of sensing devices at least comprise four cameras, the four cameras are all arranged on the front side of the head and are all used for acquiring the surrounding environment information of the high-intelligence deformation robot;
the head control module includes the ambient environment data in the external environment information and transmits to the central control unit.
10. The highly intelligent transformable robot of claim 9, wherein a plurality of said sensing devices further comprise:
the radar device is arranged above the head, two camera devices are respectively arranged on two sides of the radar device, and the radar device drives the camera devices to rotate at a constant speed;
the radar device is used for detecting distance information around the high-intelligence deformation robot;
one camera device is used for detecting remote environment information of the high-intelligence deformation robot;
the other camera device is used for detecting the near environment information of the high-intelligence deformation robot;
the head control module includes the distance information, the far environment information, and the near environment information in the external environment information and transmits to the central control unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010197497.6A CN111300451B (en) | 2020-03-19 | 2020-03-19 | High-intelligence shape shifting robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010197497.6A CN111300451B (en) | 2020-03-19 | 2020-03-19 | High-intelligence shape shifting robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111300451A true CN111300451A (en) | 2020-06-19 |
| CN111300451B CN111300451B (en) | 2021-06-29 |
Family
ID=71155384
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010197497.6A Active CN111300451B (en) | 2020-03-19 | 2020-03-19 | High-intelligence shape shifting robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111300451B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113110176A (en) * | 2021-04-15 | 2021-07-13 | 北京云迹科技有限公司 | Robot-based running state control method and related equipment |
| WO2022140173A1 (en) * | 2020-12-22 | 2022-06-30 | Boston Dynamics, Inc. | Door opening behavior and robot presenting the behaviour |
| WO2024021806A1 (en) * | 2022-07-25 | 2024-02-01 | 腾讯科技（深圳）有限公司 | Method and apparatus for swing-up movement of robot, robot, storage medium, and product |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103287523A (en) * | 2013-05-06 | 2013-09-11 | 中国科学技术大学 | Composite transformation mobile robot combining elastic foot and wheel type motion mechanism |
| US20170173792A1 (en) * | 2015-12-17 | 2017-06-22 | Panasonic Intellectual Property Management Co., Ltd. | Work device |
| CN107813309A (en) * | 2017-11-16 | 2018-03-20 | 徐立志 | A kind of control method of fighter toy, device and fighter toy |
| CN108098731A (en) * | 2017-08-30 | 2018-06-01 | 安徽工程大学 | Intelligent mobile equipment and driving method with executing agency |
| CN108283814A (en) * | 2018-02-26 | 2018-07-17 | 森汉智能科技（深圳）有限公司 | Programmable fully-automatic conversion anthropomorphic robot |
| CN108638019A (en) * | 2018-05-08 | 2018-10-12 | 浙江大学 | The deformable bionical wheel robot leg of one kind and its control method |
-
2020
- 2020-03-19 CN CN202010197497.6A patent/CN111300451B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103287523A (en) * | 2013-05-06 | 2013-09-11 | 中国科学技术大学 | Composite transformation mobile robot combining elastic foot and wheel type motion mechanism |
| US20170173792A1 (en) * | 2015-12-17 | 2017-06-22 | Panasonic Intellectual Property Management Co., Ltd. | Work device |
| CN108098731A (en) * | 2017-08-30 | 2018-06-01 | 安徽工程大学 | Intelligent mobile equipment and driving method with executing agency |
| CN107813309A (en) * | 2017-11-16 | 2018-03-20 | 徐立志 | A kind of control method of fighter toy, device and fighter toy |
| CN108283814A (en) * | 2018-02-26 | 2018-07-17 | 森汉智能科技（深圳）有限公司 | Programmable fully-automatic conversion anthropomorphic robot |
| CN108638019A (en) * | 2018-05-08 | 2018-10-12 | 浙江大学 | The deformable bionical wheel robot leg of one kind and its control method |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022140173A1 (en) * | 2020-12-22 | 2022-06-30 | Boston Dynamics, Inc. | Door opening behavior and robot presenting the behaviour |
| CN113110176A (en) * | 2021-04-15 | 2021-07-13 | 北京云迹科技有限公司 | Robot-based running state control method and related equipment |
| WO2024021806A1 (en) * | 2022-07-25 | 2024-02-01 | 腾讯科技（深圳）有限公司 | Method and apparatus for swing-up movement of robot, robot, storage medium, and product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111300451B (en) | 2021-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111300451B (en) | High-intelligence shape shifting robot | |
| CN113696186B (en) | Mechanical arm autonomous moving and grabbing method based on visual-touch fusion under complex illumination condition | |
| US9862090B2 (en) | Surrogate: a body-dexterous mobile manipulation robot with a tracked base | |
| JP3994950B2 (en) | Environment recognition apparatus and method, path planning apparatus and method, and robot apparatus | |
| JP3094091B2 (en) | Space robot controller | |
| CN111055281A (en) | ROS-based autonomous mobile grabbing system and method | |
| KR20200140834A (en) | Wearable device-based mobile robot control system and control method | |
| CN111230873B (en) | Teaching learning-based collaborative handling control system and method | |
| JP7044047B2 (en) | robot | |
| JP7117237B2 (en) | ROBOT CONTROL DEVICE, ROBOT SYSTEM AND ROBOT CONTROL METHOD | |
| US20220080599A1 (en) | Robot controlling system | |
| CN114505840A (en) | Intelligent service robot of autonomous operation box type elevator | |
| KR102131097B1 (en) | Robot control system and robot control method using the same | |
| Prats et al. | Vision force control in task-oriented grasping and manipulation | |
| US11656923B2 (en) | Systems and methods for inter-process communication within a robot | |
| Anderson et al. | Coordinated control and range imaging for mobile manipulation | |
| CN111496790B (en) | Arbitration planning system and method | |
| JP3901006B2 (en) | Visual recognition device | |
| US20240149458A1 (en) | Robot remote operation control device, robot remote operation control system, robot remote operation control method, and program | |
| US20220080603A1 (en) | Image analysis system | |
| CN115958575B (en) | Mobile robot capable of being operated flexibly by similar people | |
| US11818328B2 (en) | Systems and methods for automatically calibrating multiscopic image capture systems | |
| WO2023207304A1 (en) | Control method for multi-modal mobile robot, related device, medium, and program product | |
| JP5539000B2 (en) | Control device | |
| CN117136120A (en) | Robot remote operation control device, robot remote operation control system, robot remote operation control method, and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |