The manipulation of deformable objects, especially deformable linear objects (DLOs), represents an open challenge in robotics. The keys to solving the problem are accurately recognizing the topological model describing the entwined state of DLO(s) and a manipulation strategy based on it. The situation becomes more challenging in practical applications since the DLO(s) may be placed under complex and unencountered environments, making distinguishing between the targets and the background difficult. In addition, with the information obtained from a sensor system with a limited field of sense, a robot has to treat the encountered DLO(s) as multiple ones of an unknown quantity. This paper proposes a solution based on deep learning techniques for these complicated scenarios. The approach can derive a topological model describing the entangled structure of single or multiple DLOs. Based on the model, we proposed a strategy for untangling the DLO(s), considering both the possible self-tangling in one DLO and the tangling between multiple DLOs. The strategy ensures that the entangled DLO(s) can be arranged to be the neatest state given a limited field of view. The feasibility and effectiveness of the proposed solution were verified by untangling experiments utilizing a dual-arm robot system. Even if the exact quantity of the DLO(s) is unknown, the robots can still untangle the DLO(s). Moreover, the proposed approach performed robustness to unfamiliar background textures, which is preferable in practical applications. Dataset used in this paper can be found at https://github.com/lancexz/dlos-dataset. Note to Practitioners —This article proposes an automatic solution for untangling an unknown quantity of DLO(s) using robots. Issues concerned with complex backgrounds, an unknown quantity of DLOs, and limits of field of view, which are easily encountered in practical applications, are solved. Experiments demonstrated the feasibility and robustness of the approach in different scenarios. Potential applications for the proposed method include pipeline bin-picking tasks, rope-like object manipulation in household robots, and cable assembly in industrial areas. Moreover, the topological state recognition process can also be utilized in knot-tying studies and producing datasets. As the current system can not deal with scenes where DLO segments or crossings severely overlap, practitioners should integrate real-time tracking, deformation control method, and unqualified cases detection to avoid the appearance of such cases during manipulation. Future works should also consider the rebound caused by the elastic potential of DLOs.

Embryo vitrification is a fundamental technology utilized in assisted reproduction and fertility preservation. Vitrification involves sequential loading and unloading of cryoprotectants (CPAs) with strict time control, and transferring the embryo in a minimum CPA droplet to the vitrification straw. However, manual operation still cannot effectively avoid embryo loss, and the existing automatic vitrification systems have insufficient system reliability, and operate differently from clinical vitrification protocol. Through collaboration with in vitro fertilization (IVF) clinics, we are in the process realizing a robotic system that can automatically conduct the embryo vitrification process, including the pretreatment with CPAs, transfer of embryo to the vitrification straw, and cryopreservation with liquid nitrogen ( $\rm LN_{2}$ ). An open microfluidic chip (OMC) was designed to accommodate the embryo during the automatic CPAs pretreatment process. The design of two chambers connected by a capillary gap facilitated solution exchange around the embryo, and simultaneously reduced the risk of embryo loss in the flow field. In accordance to the well-accepted procedure and medical devices in manual operation, we designed the entire vitrification protocol, as well as the robotic prototype. In a practical experiment using mouse embryos, our robotic system showed a 100 $\%$ success rate in transferring and vitrifying the embryos, achieved comparable embryo survival rates (90.9 $\%$ versus 94.4 $\%$ ) and development rates (90.0 $\%$ versus 94.1 $\%$ ), when compared with the manual group conducted by the senior embryologist. With this study, we aim to facilitate the standardization of clinical vitrification from manual operation to a more efficient and reliable automated process.

Manipulation of deformable objects is an essential task in surgery, the textile industry, and household tasks, such as washing, hanging, and folding clothes. However, current studies on fabric manipulation, have rarely considered the scenes in which rigid objects have to be wrapped by fabrics. This type of operation is widely adopted in the logistic packaging and packaging of surgical instrument baskets. In this study, we propose a method to perform this operation, which can be used in fabric folding or wrapping a box with fabric. Owing to the complex dynamics and configuration spaces of fabric, our method is based on deep imitation learning to estimate pick-place points and the phase of the manipulation process. The dataset was completely generated from an open-source physical simulator. To make the data as realistic as that in actual scenarios, we adopted domain randomization and rendered the texture of fabric and box from the real world to simulation data. This not only helps in transferring the learned policies to a physical robot, but also allows the robot to wrap a box with complex patterns. The experiments demonstrate the efficiency of the developed method for accomplishing complex manipulation tasks. The results also showed that it could be generalized to fabrics with different colors and boxes with different sizes, textures, or geometric shapes.

Oocyte vitrification technology is widely used for assisted reproduction and fertility preservation, which requires precise washing sequences and timings of cryoprotectant agents (CPAs) treatment to relieve the osmotic shock to cells. The gold standard Cryotop method is extensively used in oocyte vitrification and is currently the most commonly used method in reproductive centers. However, the Cryotop method requires precise and complex manual manipulation by an embryologist, whose proficiency directly determines the effect of vitrification. Therefore, in this study, an automatic microfluidic system consisting of a novel open microfluidic chip and a set of automatic devices was established as a standardized operating protocol to facilitate the conventional manual Cryotop method and minimize the osmotic shock applied to the oocyte. The proposed open microfluidic system could smoothly change the CPA concentration around the oocyte during vitrification pretreatment, and transferred the treated oocyte to the Cryotop with a tiny droplet. The system better conformed to the operating habits of embryologists, whereas the integration of commercialized Cryotop facilitates the subsequent freezing and thawing processes. With standardized operating procedures, our system provides consistent treatment effects for each operation, leading to comparable survival rate, mitochondrial membrane potential (MMP) and reactive oxygen species (ROS) level of oocytes to the manual Cryotop operations. The vitrification platform is the first reported microfluidic system integrating the function of cells transfer from the processing chip, which avoids the risk of cell loss or damage in a manual operation and ensures the sufficient cooling rate during liquid nitrogen (${\mathrm{LN}}_2$) freezing. Our study demonstrates significant potential of the automatic microfluidic approach to serve as a facile and universal solution for the vitrification of various precious cells.

Embryo vitrification is an essential technique for in vitro fertilization (IVF), which avoids the formation of ice crystals during cryopreservation by dehydrating cells in cryoprotectant agents (CPAs) and ultrarapidly freezing them in liquid nitrogen ( $\rm LN_{2}$ ). In manual vitrification, the embryo will be repeatedly aspirated and released in different CPAs and finally transferred onto the vitrification straw under the microscope, which is time-consuming and requires intensive training of skilled operators. Robotic cell manipulation has been considered the solution to enhance the processing efficiency while reducing the failure rate for the manual vitrification protocols; however, the time-critical treatment with CPAs and transfer of the embryo to the straw still remain challenging in ongoing studies. In this article, we report a microfluidics-enabled robotic system for the emerging automatic embryo vitrification. Based on the strategy of microfluidic manipulation in our early works, an open microfluidic chip was designed to confine the embryo within a specific region while manipulating the surrounding flow field for solution exchange through the capillary effect. The embryo chamber was zoned into safe and danger zones based on the numerically simulated local velocity toward the capillary gap, which represents the risk of embryo loss and damage. A vision-based switch controller was adopted to manipulate the embryo trajectory during the solution exchange process, which selected the optimized flow rate according to the zoning of real-time embryo. The challenge of embryo transfer was addressed by a two-stage capillary valve, which switches open and allows the embryo to pass through under a certain pressure. The vitrification experiments with porcine embryos validate the reliable positioning of the embryo in each step, the satisfactory success rate of the robotic system, and the high quality of the robotic-vitrified embryos after thawing. Integrated with new manipulation strategies, our intelligent mechatronics system provides a promising solution for IVF featuring an embryologist-centered configuration and standardized robotic operation.

In logistics warehouse sorting, rubbish classification, and household services, scenarios exist in which rigid and soft objects are randomly piled together. In such situations, two major challenges arise in robotic picking tasks: the first is to distinguish rigid objects from soft objects, and the second is to grasp one object of each type at a time. In this study, we propose a novel robotic picking methodology for the grasping of objects mixed with towels. The proposed approach is based on a novel object detection method that can identify a rigid object placed in different directions using a rotational bounding box. Rigid objects can be separated from the mixed scene without object segmentation. Moreover, the grasping pose of a rigid object can be generated directly along its principal axis, without using a CAD model or specific pose detection method. The gripper opening width is determined according to the object size. Therefore, our method can detect whether other objects, particularly soft ones, exist around a rigid object. If no suitable grasping pose is available for the rigid objects, the grasping pose on a wrinkle of the towel is selected. The experiments demonstrate that our method can accomplish the picking task in scenes with mixed rigid and soft objects, thereby indicating its significance in robotic object detection and sorting.