2023 Robotic perception-motion synergy for novel wrapping tasks §
阅读 §
资料的搜集 §
- 关键词
- 操作对象（分类不绝对）
- 一般意义：
Deforamble linear object，Deformable one-dimensional object
- 未指定应用场景的科研：
string，rope，flexible coil
- 工业应用：
cable，wire，harness
- 医疗应用：
catheter，suturing
- 操作方法：
winding，insertion，knotting，routing，rearranging
论文的总结 §
| Category | Method |
|---|
| Application | |
| Problem abstraction | |
| DLO model (physical model/topology model/model-free)? | |
| DLO detecting method (CV/Tact/Mixture) | |
| If use CV, what method? | |
| Motion planning method | |
| Shape Control | |
写作 §
摘要的修改 §
| 修改前 | 修改后 |
| 先行定义常用术语 | This paper introduces a novel and general method to solve the problem of using a general-purpose robot manipulator with a parallel gripper to wrap a deformable linear object (DLO) around a rigid object. | This paper introduces a novel and general method to address the problem of using a general-purpose robot manipulator with a parallel gripper to wrap a deformable linear object (DLO), called a rope, around a rigid object, called a rod, autonomously. |
| 将要强调的重点（方法的优势1）放在前面 | This method uses real-time perception to determine the wrapping state and uses feedback control to adjust a canonical motion to achieve high-quality results. Our method does not require prior knowledge of the physical and geometrical properties of the DLO. | Our method does not require prior knowledge of the physical and geometrical properties of the objects but enables the robot to use real-time RGB-D perception to determine the wrapping state and feedback control to achieve high-quality results. |
| 方法的优势2 | | As such, it provides the robot manipulator the general capabilities to handle wrapping tasks of different rods or ropes. |
| We test our method on 6 conditions with 3 types of rope and 2 types of rod. The result shows that the wrapping quality improved and converged within 5 wraps for all test conditions. | We tested our method on 6 combinations of 3 different ropes and 2 rods. The result shows that the wrapping quality improved and converged within 5 wraps for all test cases. |
引言 §
总结论文贡献部分 §
- 提炼的总结，简单解释，语法统一
> 1) Grasping point selection: Using RGB images to search for a grasping point along the DLO.
> 2) Motion adjustment for wrapping: Generating robot end-effector’s motion trajectory based on tunable parameters, after it grasps the DLO.
> 3) Motion outcome estimation and feedback control: Using RGB images to estimate the outcome of the motion and adjust the parameters of the motion trajectory generator