Double-section soft robot system based on tension sensor and control method

Abstract

The invention provides a double-section soft robot system based on a tension sensor and a control method, and relates to the field of soft robots. According to the flexible robot system, firstly, the design of a double-section flexible structure is adopted, so that the flexible robot system has various deformation modes such as local bending, overall swinging and complex form reconstruction, and therefore the adaptability of the flexible robot system to different environments and tasks is improved; the force and load change of a traction rope of the soft robot system can be monitored in real time, the soft robot system can effectively compensate external disturbance by dynamically adjusting a control strategy, the soft robot system can sense environment change in real time in combination with a visual sensing module, and therefore the response speed and accuracy of a closed-loop control system are improved, and finally, the control system can be applied to the field of intelligent control. And the control module adopts a hierarchical control framework and software and hardware collaborative hierarchical design, so that the comprehensive performance and the intelligent level of the soft robot are improved, and reasonable allocation of computing resources is realized.

Description

Technical Field

[0001] This invention relates to the field of soft robots, and more particularly to a two-segment soft robot system and control method based on a tension sensor. Background Technology

[0002] While traditional rigid robots excel in precision and load-bearing capacity, they suffer from limitations in adaptability, safety, and biocompatibility in complex environments. Soft robots, with their flexible materials and biomimetic structures, overcome these limitations, exhibiting superior mobility when exploring unknown environments or performing complex tasks. In recent years, soft robots have found widespread application in fields such as medical surgery, industrial manufacturing, and deep-sea exploration, with their unique compliance and environmental adaptability opening up new avenues for robotics development. However, the precise control and stability of soft robots still face numerous challenges, especially in complex environments requiring precise manipulation.

[0003] Soft robots, constructed from flexible materials, exhibit nonlinear large deformation characteristics, strongly coupled dynamic behavior, and complex deformable control properties. In the application of two-segment soft robots, existing control strategies (such as open-loop control based on pre-defined models or low-frequency feedback relying on external vision systems) face significant limitations: open-loop control based on pre-defined models struggles to accurately predict and compensate for the inherent nonlinear deformation of soft materials and disturbances caused by environmental interactions; low-frequency feedback relying on external vision systems suffers from perception delays, field-of-view occlusion, or poor adaptability to complex environments. These limitations pose a severe challenge to the precise control and dynamic adaptability of robots when performing complex tasks requiring high-precision operation or rapid adaptation to dynamic environments.

[0004] Existing rope-driven soft body control methods primarily achieve motion by adjusting rope length or controlling rope driving force. Rope length control relies on adjusting the length of the drive rope and using kinematic models to derive the mapping relationship between rope length changes and shape deformation, thereby achieving attitude control. However, due to the nonlinear deformation characteristics of soft materials, a single rope length control method is insufficient to accurately describe the motion behavior of real systems, and friction, material elastic deformation, and rope slack effects can affect the repeatability and stability of the system.

[0005] Single-segment soft robots are limited by a single continuous structure, resulting in a severe lack of motion degrees of freedom and an inability to achieve multi-target cooperative operations (such as simultaneous navigation and fine manipulation). The strong coupling characteristics of nonlinear deformation make high-precision trajectory tracking difficult, and environmental disturbances can easily lead to global loss of control. The lack of functional integration space restricts their application in complex scenarios. Summary of the Invention

[0006] To address the problems in the prior art, this invention provides a two-segment soft robot system and control method based on a tension sensor. Firstly, by employing a two-segment soft structure design, the soft robot system possesses diverse deformation modes such as local bending, overall oscillation, and complex shape reconstruction, thereby enhancing its adaptability to different environments and tasks and optimizing the overall performance and stability of the system. Secondly, a high-precision tension feedback module is introduced to monitor the force and load changes of the traction rope of the soft robot system in real time. By dynamically adjusting the control strategy, the soft robot system can effectively compensate for external disturbances. Combined with a visual perception module, the soft robot system can perceive environmental changes in real time and adaptively adjust the control strategy, thereby improving the response speed and accuracy of the closed-loop control system and enhancing the stability and adaptability of the soft robot system in complex environments. Finally, the control module adopts a hierarchical control architecture with a hardware and software co-design, improving the comprehensive performance and intelligence level of the soft robot and achieving rational allocation of computing resources. To achieve the above objectives, the technical solution is as follows: On one hand, the present invention provides a two-segment soft robot system based on a tension sensor, the system comprising: A dual-segment soft actuator module is used to simulate the movement of a living organism and change the movement mode of a dual-segment soft robot by deformation. The dual-segment soft actuator module includes an upper soft segment and a lower soft segment, which are connected in series. The visual perception module is used to capture the position information of the two-segment soft actuator module in real time; The tension feedback module is used to monitor the change in the tension of the drive module during the movement of the dual-segment soft actuator module; This drive module is used to provide power to the two-stage soft actuator module; The control module is used to perform closed-loop control based on the data from the visual perception module and the tension feedback module, and to adjust the output of the drive module.

[0007] Optionally, the upper soft segment and the lower soft segment are fixedly connected by an intermediate coupler, and traction ropes are respectively installed on the upper soft segment and the lower soft segment. A sleeve is nested inside the upper soft segment, and the traction rope of the lower soft segment is connected to the tension feedback module through the sleeve.

[0008] Optionally, the driver module includes: The drive platform is used to ensure the fixation and positioning of the two-stage soft actuator module during movement; The internal software drive structure is used to adjust the working state of the two-segment software actuator module and change its motion mode.

[0009] Optionally, the drive platform includes: a front pulley, a drive motor, and a fixed platform; The front pulley is fixed on the fixed platform, the drive motor is slidably mounted on the fixed platform, and the dual-stage soft actuator module is fixed below the fixed platform; the traction rope of the dual-stage soft actuator module passes through the front pulley and is connected to the drive motor, and the drive motor is connected to the tension feedback module.

[0010] Optionally, the drive motor includes: The upper soft segment drive motor is used to drive the movement of the upper soft segment; The lower soft segment drive motor is used to drive the movement of the lower soft segment; The upper soft segment drive motor and the lower soft segment drive motor are alternately slidably mounted on the fixed platform.

[0011] Optionally, the control module includes: The upper-level decision-making unit is used to generate a soft deformation control strategy based on the data from the visual perception module and the tension feedback module. The underlying execution unit is used to execute the software deformation control strategy.

[0012] Optionally, based on the data from the visual perception module and the tension feedback module, closed-loop control is performed to adjust the output of the drive module, including: Based on the data from the visual perception module and the force feedback module, motion parameters are obtained through a reinforcement learning algorithm; Based on these motion parameters, a soft body deformation control strategy is generated through comprehensive processing. Based on the software deformation control strategy, the drive module is controlled to obtain the motion pattern of the dual-segment software actuator module and the updated data of the tension feedback module. Based on the motion patterns of the visual perception module and the dual-segment soft actuator module, the updated data of the visual perception module is obtained. Repeat all the above steps to obtain the output of the drive module of the final form of the two-segment soft robot.

[0013] Optionally, the manufacturing process of the two-stage software actuator module includes: Based on the design requirements of the dual-segment soft actuator module, a split resin mold is obtained, the inner cavity shape of which is consistent with the upper soft segment and the lower soft segment. The sleeve is placed inside the split resin mold, and the heated silicone is poured into the split resin mold. After curing at room temperature, a two-section soft integrated model is obtained. The two-segment integrated soft model was demolded using a resin mold to obtain the two-segment soft actuator module.

[0014] On the other hand, the present invention provides a control method for a two-segment soft robot based on a tension sensor. This method is implemented by a two-segment soft robot system based on a tension sensor, and includes: S1. Based on the motion pattern instructions of the two-segment soft robot, the two-segment soft actuator module is controlled by the drive module to obtain the motion pattern of the first stage. S2. Based on the motion pattern of the first stage, the end position information of the dual-stage soft actuator module and the tension of the drive motor are obtained through the visual perception module and the tension feedback module. S3. Based on the end position information of the dual-segment soft actuator module and the tension of the drive motor, a reinforcement learning algorithm is used to obtain a soft deformation control strategy. S4. Based on the software deformation control strategy, control the drive module to obtain the updated motion pattern of the first stage; S5. Repeat S2~S4 to obtain the final motion pattern of the two-segment soft robot.

[0015] Compared with the prior art, the technical solution of the present invention has at least the following beneficial effects: The above-mentioned solution has three main aspects. First, by adopting a dual-segment soft structure design, the soft robot system can possess diverse deformation modes such as local bending, overall swinging, and complex shape reconstruction, thereby improving its adaptability to different environments and tasks and optimizing the overall performance and stability of the system. Second, by introducing a high-precision tension feedback module, the system can monitor the force and load changes of the traction rope in real time. Through dynamic adjustment of the control strategy, the soft robot system can effectively compensate for external disturbances. Combined with a visual perception module, the system can perceive environmental changes in real time and adaptively adjust the control strategy, thereby improving the response speed and accuracy of the closed-loop control system and enhancing the stability and adaptability of the soft robot system in complex environments. Third, the control module adopts a hierarchical control architecture with a hardware and software co-design, improving the comprehensive performance and intelligence level of the soft robot and achieving a reasonable allocation of computing resources. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a system block diagram of an embodiment of the two-segment soft robot system based on a tension sensor of the present invention; Figure 2This is a flowchart illustrating the adjustment of the output of the drive module in an embodiment of the two-segment soft robot system based on a tension sensor according to the present invention; Figure 3 This is a flowchart illustrating the manufacturing process of the dual-segment soft actuator module in an embodiment of the dual-segment soft robot system based on a tension sensor according to the present invention. Figure 4 This is a perspective view of the structure of an embodiment of the two-segment soft robot system based on a tension sensor according to the present invention; Figure 5 This is a front view of an embodiment of the two-segment soft robot system based on a tension sensor according to the present invention; Figure 6 This is a top view of an embodiment of the two-segment soft robot system based on a tension sensor according to the present invention; Figure 7 This is a schematic diagram of the internal structure of the dual-segment soft actuator module in an embodiment of the dual-segment soft robot system based on a tension sensor of the present invention; Figure 8 This is a schematic diagram of the control of the soft robot system in an embodiment of the two-segment soft robot system based on a tension sensor according to the present invention; Figure 9 This is a flowchart of an embodiment of the two-segment soft robot control method based on a tension sensor according to the present invention.

[0018] The following are the labels in the diagram: 1. Drive motor; 2. Tension sensor; 3. Fixed platform; 4. Traction rope; 5. Slide rail; 6. Front pulley; 7. Upper soft section; 8. Middle coupler; 9. Lower soft section; 10. Bowden tube; 11. Fixing plate. Detailed Implementation

[0019] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0020] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0021] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0022] like Figure 1 The system block diagram of the two-segment soft robot system based on the tension sensor of the present invention shown is as follows: Figure 4The diagram shows a structural perspective view of an embodiment of the two-segment soft robot system based on a tension sensor according to the present invention. The present invention provides a two-segment soft robot system based on a tension sensor, which can implement a two-segment soft robot control method based on a tension sensor. The system includes: a two-segment soft actuator module, a vision perception module, a tension feedback module, a drive module, and a control module. A dual-segment soft actuator module is used to simulate the movement of a living organism and change the movement mode of the dual-segment soft robot by deformation. The dual-segment soft actuator module includes an upper soft segment 7 and a lower soft segment 9, which are connected in series. Specifically, such as Figure 3 The flowchart shown is a fabrication process diagram of the dual-segment soft actuator module in an embodiment of the dual-segment soft robot system based on a tension sensor according to the present invention. The fabrication process of the dual-segment soft actuator module includes: Based on the design requirements of the dual-segment soft actuator module, a split resin mold is obtained, the inner cavity shape of which is consistent with the upper soft segment 7 and the lower soft segment 9. The sleeve is placed inside the split resin mold, and the heated silicone is poured into the split resin mold. After curing at room temperature, a two-section soft integrated model is obtained. The two-segment integrated soft model was demolded using a resin mold to obtain the two-segment soft actuator module.

[0023] Furthermore, a split resin mold is first designed, with an inner cavity shape consistent with the shape of the dual-segment soft actuator module. A Bowden tube 10 with a diameter of 1-2 mm is pre-embedded as a channel for the traction rope. Medical-grade paraffin wax (melting point 50-60℃) is melted and injected into the hollow part of the mold to form a wax core. Before wax injection, the mold needs to be preheated to 40℃ to prevent filling defects. Curing is carried out at room temperature for 24 hours or at 60℃ for 2-4 hours. After demolding, the molded tentacles are immersed in a 70-80℃ hot water bath for 10-15 minutes to completely melt and flow out the wax core. Finally, the traction rope 4 is inserted through the pre-embedded Bowden tube 10 to complete the assembly.

[0024] Specifically, such as Figure 5 The front view of the embodiment of the two-segment soft robot system based on the tension sensor of the present invention is shown. The upper soft segment 7 and the lower soft segment 9 are fixedly connected by an intermediate coupler 8. Traction ropes 4 are installed at the center of the four sides of the upper soft segment 7 and at the four corners of the lower soft segment 9, respectively. The upper soft segment 7 is nested in a tube, and the traction ropes 4 of the lower soft segment 9 are connected to the tension feedback module through the tube.

[0025] Furthermore, such as Figure 7The diagram shows the internal structure of the dual-segment soft actuator module in an embodiment of the dual-segment soft robot system based on a tension sensor of the present invention. The upper soft segment 7 adopts a hollow silicone structure, with a traction rope channel at the center of each of the four upper soft segment walls. The hollow part contains a Bowden tube 10, which is fixed to the upper soft segment 7 by a fixing plate 11. The intermediate coupler 8 connects the upper soft segment 7 and the lower soft segment 9 in an embedded connection manner. The lower soft segment 9 adopts a solid silicone structure and has traction rope channels at the center of the four sides of the upper soft segment 7. The traction rope 4 of the lower soft segment 9 will pass through the Bowden tube 10 of the upper soft segment 7. Traction ropes 4 are fixed at the center of the four sides of the upper soft segment 7 and the four corners of the lower soft segment 9, with a total of eight traction ropes 4 (0.9mm white nylon thread, tensile strength limit 40.9kg) for independently controlling the deformation of the upper soft segment 7 and the lower soft segment 9.

[0026] The visual perception module is used to capture the position information of the two-segment soft actuator module in real time; The tension feedback module is used to monitor the change in the tension of the drive module during the movement of the dual-segment soft actuator module; Specifically, the tension feedback module uses tension sensor 2, which collects tension data and sends it to the control module via RS485 protocol.

[0027] This drive module is used to provide power to the two-stage soft actuator module; Specifically, the driver module includes: The drive platform is used to ensure the fixation and positioning of the two-stage soft actuator module during movement; The internal software drive structure is used to adjust the working state of the two-segment software actuator module and change its motion mode.

[0028] Specifically, such as Figure 6 The top view of the embodiment of the two-segment soft robot system based on the tension sensor of the present invention shown includes: a front pulley 6, a drive motor 1, and a fixed platform 3; The front pulley 6 is fixed on the fixed platform 3, the drive motor 6 is slidably mounted on the fixed platform 3, and the dual-stage soft actuator module is fixed below the fixed platform 3; the traction rope 4 of the dual-stage soft actuator module passes through the front pulley 6 and is connected to the drive motor 1, and the drive motor 1 is connected to the tension feedback module.

[0029] Furthermore, the drive motor 1 is connected to the fixed platform 3 via the slide rail 5.

[0030] Specifically, the drive motor 1 includes: The upper soft segment drive motor is used to drive the upper soft segment 7 to move; The lower software segment drive motor is used to drive the movement of the lower software segment 9; The upper soft segment drive motor and the lower soft segment drive motor are alternately slidably mounted on the fixed platform 3.

[0031] Furthermore, eight drive motors 1 are centrally symmetrically distributed on the fixed platform 3 in a 360-degree arrangement, with the upper soft segment drive motor and the lower soft segment drive motor alternating between the two, totaling four upper soft segment drive motors and four lower soft segment drive motors.

[0032] The upper soft section drive motor directly drives the traction rope 4 to control the upper soft section 7, while the lower soft section drive motor accurately controls the traction rope 4 through the Bowden tube 10 to control the lower soft section 9. The drive system of the lower soft section operates in a cooperative manner with the traction rope 4 and the Bowden tube 10: the lower end of the traction rope 4 of the upper soft section 7 is fixed to the inside of the upper soft section 7, and the traction rope 4 is wound on the winch of the upper soft section drive motor. When the upper soft section drive motor is retracting, it achieves bidirectional bending of the upper soft section 7 through unilateral tension. The Bowden tube 10 serves the lower soft section 9. One end of the inner core of the Bowden tube 10 is fixed to the fixed platform 3, and the other end extends through the hollow part of the upper soft section 7 to the lower soft section drive motor, so that the tension of the lower soft section drive motor can be efficiently transmitted to the lower soft section 9, realizing the independent bending of the lower soft section 9. The traction rope 4 of the upper soft section 7 slides freely in the upper section channel, and the traction rope 4 of the lower soft section 9 passes through the Bowden tube 10 through the upper soft section 4 to ensure that the upper and lower traction systems do not interfere with each other.

[0033] The control module is used to perform closed-loop control based on the data from the visual perception module and the tension feedback module, and to adjust the output of the drive module.

[0034] Specifically, the control module includes: The upper-level decision-making unit is used to generate a soft deformation control strategy based on the data from the visual perception module and the tension feedback module. The underlying execution unit is used to execute the software deformation control strategy.

[0035] Specifically, such as Figure 2 The flowchart shown in the embodiment of the two-segment soft robot system based on the tension sensor of the present invention, illustrating the adjustment of the output of the drive module, and as shown in the figure... Figure 8 The diagram shown is a control schematic of a two-segment soft robot system based on a tension sensor, according to an embodiment of the present invention. The system performs closed-loop control based on data from the visual perception module and the tension feedback module, adjusting the output of the drive module, including: Based on the data from the visual perception module and the force feedback module, motion parameters are obtained through a reinforcement learning algorithm; Based on these motion parameters, a soft body deformation control strategy is generated through comprehensive processing. Based on the software deformation control strategy, the drive module is controlled to obtain the motion pattern of the dual-segment software actuator module and the updated data of the tension feedback module. Based on the motion patterns of the visual perception module and the dual-segment soft actuator module, the updated data of the visual perception module is obtained. Repeat all the above steps to obtain the output of the drive module of the final form of the two-segment soft robot.

[0036] Furthermore, the upper-level decision-making unit, based on the Jetson Orin NX platform, integrates a reinforcement learning controller to process the end-effector position coordinates (x, y, z) collected by the visual perception module and generate a software deformation control strategy. The lower-level execution unit uses a Raspberry Pi Pico to parse control commands in real time, generate drive motor pulse signals, and precisely adjust the length of the traction rope 4. It adopts a closed-loop feedback mechanism, monitors tension data in real time through the tension sensor 2, and dynamically adjusts control parameters in combination with the end-effector position feedback from the visual perception module, forming a closed-loop link of "perception-decision-execution-feedback" to ensure the stability and adaptability of deformation control.

[0037] like Figure 9 The flowchart shown is an embodiment of the two-segment soft robot control method based on a tension sensor according to the present invention. The present invention provides a two-segment soft robot control method based on a tension sensor, which is implemented by a two-segment soft robot system based on a tension sensor. The method includes: S1. Based on the motion pattern instructions of the two-segment soft robot, the two-segment soft actuator module is controlled by the drive module to obtain the motion pattern of the first stage. S2. Based on the motion pattern of the first stage, the end position information of the dual-stage soft actuator module and the tension of the drive motor are obtained through the visual perception module and the tension feedback module. S3. Based on the end position information of the dual-segment soft actuator module and the tension of the drive motor, a reinforcement learning algorithm is used to obtain a soft deformation control strategy. S4. Based on the software deformation control strategy, control the drive module to obtain the updated motion pattern of the first stage; S5. Repeat S2~S4 to obtain the final motion pattern of the two-segment soft robot.

[0038] This invention provides a two-segment soft robot system and control method based on a tension sensor. Firstly, by employing a two-segment soft structure design, the soft robot system possesses diverse deformation modes such as local bending, overall oscillation, and complex shape reconstruction, thereby enhancing its adaptability to different environments and tasks and optimizing the overall performance and stability of the system. Secondly, a high-precision tension feedback module is introduced to monitor the force and load changes of the traction rope of the soft robot system in real time. Through dynamic adjustment of the control strategy, the soft robot system can effectively compensate for external disturbances. Combined with a visual perception module, the soft robot system can perceive environmental changes in real time and adaptively adjust the control strategy, thereby improving the response speed and accuracy of the closed-loop control system and enhancing the stability and adaptability of the soft robot system in complex environments. Finally, the control module adopts a hierarchical control architecture with a hardware and software co-design, improving the comprehensive performance and intelligence level of the soft robot and achieving reasonable allocation of computing resources.

[0039] It is understood that the present invention has been described through the above embodiments and should not be construed as limiting the implementation and scope of the present invention. Those skilled in the art will recognize that various changes or equivalent substitutions can be made to these features and embodiments without departing from the spirit and scope of the present invention. Furthermore, under the teachings of the present invention, these features and embodiments can be modified to adapt to specific situations and materials without departing from the spirit and scope of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed herein, and all embodiments falling within the scope of the claims of this application are within the protection scope of the present invention.

Claims

1. A two-segment soft robot system based on a tension sensor, characterized in that, The system includes: A dual-segment soft actuator module is used to simulate the movement of a living organism and change the movement mode of a dual-segment soft robot by deformation. The dual-segment soft actuator module includes an upper soft segment and a lower soft segment, which are connected in series. The visual perception module is used to capture the position information of the dual-segment soft actuator module in real time; The tension feedback module is used to monitor the change in the tension of the drive module during the movement of the dual-segment soft actuator module; The drive module is used to provide power to the dual-segment soft actuator module; The control module is used to perform closed-loop control based on the data from the visual perception module and the tension feedback module, and to adjust the output of the drive module.

2. The two-segment soft robot system based on a tension sensor according to claim 1, characterized in that, The upper soft section and the lower soft section are fixedly connected by an intermediate coupler. Traction ropes are installed on the upper soft section and the lower soft section respectively. A tube is nested inside the upper soft section, and the traction rope of the lower soft section is connected to the tension feedback module through the tube.

3. The two-segment soft robot system based on a tension sensor according to claim 1, characterized in that, The driving module includes: A drive platform is used to ensure the fixation and positioning of the dual-segment soft actuator module during movement; The internal software drive structure is used to adjust the working state of the dual-segment software actuator module and change the motion mode of the dual-segment software actuator module.

4. The two-segment soft robot system based on a tension sensor according to claim 3, characterized in that, The drive platform includes: a front pulley, a drive motor, and a fixed platform; The front pulley is fixed on the fixed platform, the drive motor is slidably mounted on the fixed platform, and the dual-stage soft actuator module is fixed below the fixed platform; the traction rope of the dual-stage soft actuator module passes through the front pulley and is connected to the drive motor, and the drive motor is connected to the tension feedback module.

5. The two-segment soft robot system based on a tension sensor according to claim 4, characterized in that, The drive motor includes: The upper soft segment drive motor is used to drive the upper soft segment to move; A lower soft segment drive motor is used to drive the movement of the lower soft segment; The upper soft segment drive motor and the lower soft segment drive motor are alternately slidably mounted on the fixed platform.

6. The two-segment soft robot system based on a tension sensor according to claim 1, characterized in that, The control module includes: The upper-level decision-making unit is used to generate a soft deformation control strategy based on the data from the visual perception module and the tension feedback module. The underlying execution unit is used to execute the software deformation control strategy.

7. The two-segment soft robot system based on a tension sensor according to claim 1, characterized in that, The step of performing closed-loop control based on data from the visual perception module and the tension feedback module, and adjusting the output of the drive module, includes: Based on the data from the visual perception module and the tension feedback module, motion parameters are obtained through a reinforcement learning algorithm; Based on the motion parameters, a soft body deformation control strategy is generated through comprehensive processing. According to the soft deformation control strategy, the drive module is controlled to obtain the motion pattern of the dual-segment soft actuator module and the updated data of the tension feedback module. Based on the motion patterns of the visual perception module and the dual-segment soft actuator module, the updated data of the visual perception module is obtained; Repeat all the above steps to obtain the output of the drive module of the final form of the two-segment soft robot.

8. The two-segment soft robot system based on a tension sensor according to claim 1, characterized in that, The manufacturing process of the dual-segment software actuator module includes: Based on the design requirements of the dual-segment soft actuator module, a split resin mold is obtained, wherein the inner cavity shape of the split resin mold is consistent with the upper soft segment and the lower soft segment. The sleeve is placed inside the split resin mold, and the heated silicone is poured into the split resin mold. After curing at room temperature, a two-section soft integrated model is obtained. The dual-segment integrated soft model is demolded using a resin mold to obtain the dual-segment soft actuator module.

9. A control method for a two-segment soft robot based on a tension sensor, wherein the control method is implemented by the two-segment soft robot system based on a tension sensor according to any one of claims 1-8, characterized in that, The method includes: S1. Based on the motion pattern instructions of the two-segment soft robot, the two-segment soft actuator module is controlled by the drive module to obtain the motion pattern of the first stage. S2. Based on the motion pattern of the first stage, the end position information of the dual-segment soft actuator module and the tension of the drive motor are obtained through the visual perception module and the tension feedback module. S3. Based on the end position information of the dual-segment soft actuator module and the tension of the drive motor, a reinforcement learning algorithm is used to obtain a soft deformation control strategy. S4. According to the software deformation control strategy, control the drive module to obtain the updated motion pattern of the first stage; S5. Repeat S2 to S4 to obtain the final motion form of the two-segment soft robot.

Images