Discontinuous Track Recognition System Based on PolyLaneNet for Darwin-op2 Robot.

This paper proposes and demonstrates a single-line discontinuous track recognition system by associating the track recognition problem of a humanoid robot with the lane detection problem. The proposal enables the robot to achieve stable running on the single-line discontinuous track. The system consists of two parts: the robot end and the graphics computing end. The robot end is responsible for collecting track information and the graphics computing end is responsible for high-performance computing. These two parts use the TCP for communication. The graphics computing side uses PolyLaneNet lane detection algorithm to train the track image captured from the first perspective of the darwin-op2 robot as the data set. In the inference, the robot end sends the collected tracking images to the graphics calculation end and uses the graphics processor to accelerate the calculation. After obtaining the motion vector, it is transmitted back to the robot end. The robot end parses the motion vector to obtain the motion information of the robot so that the robot can achieve stable running on the single-line discontinuous track. The proposed system realizes the direct recognition of the first perspective image of the robot and avoids the problems of poor stability, inability of identifying curves and discontinuous lines, and other problems in the traditional line detection method. At the same time, this system adopts the method of cooperative work between the PC side and the robot by deploying the algorithm with high computational requirements on the PC side. The data transmission is carried out by stable TCP communication, which makes it possible for the robot equipped with weak computational controllers to use deep-learning-related algorithms. It also provides ideas and solutions for deploying deep-learning-related algorithms on similar low computational robots.

Association between potentially functional polymorphisms of chemokine family members and the survival of esophageal cancer patients in a Chinese population.

Background: The chemokine family plays an important role in the growth, invasion, and metastasis of tumors. However, most studies have only focused on a few genes or a few gene loci, and thus could not reveal the associations between functional polymorphisms of chemokine family members and tumor progression. This study aimed to determine the associations between single nucleotide polymorphisms (SNPs) of chemokine family members and the prognosis of esophageal cancer (EC). Methods: The Cox risk proportional model and log-rank test were used to analyze the associations of 16 potentially functional SNPs in 13 genes from the chemokine family with the survival of 729 Chinese patients with EC. Results: Prognostic analysis on the 16 SNPs showed that different genotypes of 5 SNPs were associated with patients' survival and the risk of death. Multivariate Cox regression analysis showed that the risk of death was higher in CCL26rs2302009 genotype A/C carriers than in A/A carriers and it was also higher in CX3CL1rs2239352 genotype T/T carriers than in C/C carriers. Stepwise Cox regression analysis showed that CCL26rs2302009 genotype A/C was an independent prognostic factor of EC, and its association with increased risk of death was stronger in patients who were ≤60 years old, female, with tumors located in the middle part of esophagus, with undifferentiated or poorly differentiated tumors, with early-stage pathologic type disease, with the longest diameter of tumor ≤5cm than in their counterparts. Conclusion: These findings suggest that CCL26rs2302009 may be a candidate biomarker for EC and its effect on death risk are associated with the histological grade, pathologic type, and the longest diameter of tumor.