Search

To solve the problems of poor exploration ability and convergence speed of traditional deep reinforcement learning in the navigation task of the patrol robot under indoor specified routes, an improved deep reinforcement learning algorithm based on Pan/Tilt/Zoom(PTZ) image information was proposed in this paper. The obtained symmetric image information and target position information are taken as the input of the network, the speed of the robot is taken as the output of the next action, and the circular route with boundary is taken as the test. The improved reward and punishment function is designed to improve the convergence speed of the algorithm and optimize the path so that the robot can plan a safer path while avoiding obstacles first. Compared with Deep Q Network(DQN) algorithm, the convergence speed after improvement is shortened by about 40%, and the loss function is more stable. [ABSTRACT FROM AUTHOR]

IR-drop is a fundamental constraint by almost all integrated circuits (ICs) physical designs, and many iterations of timing engineer change order (ECO), IR-drop ECO, or other ECO are needed before design signoff. However, IR-drop analysis usually takes a long time and wastes so many resources. In this work, we develop a fast dynamic IR-drop predictor based on a machine learning technique, XGBoost, and the prediction method can be applied to vector-based and vectorless IR-drop analysis simultaneously. Correlation coefficient is often used to characterize the symmetry of prediction data and golden data, and our experiments show that the prediction correlation coefficient is more than 0.96 and the average error is no more than 1.3 mV for two industry designs, which are of 2.4 million and 3.7 million instances, respectively, and that the analysis is speeded up over 4.3 times compared with the IR-drop analysis by commercial tool, Redhawk. [ABSTRACT FROM AUTHOR]

The reliability of integrated circuits under advanced process nodes is facing more severe challenges. Single-event transients (SET) are an important cause of soft errors in space applications. The SET caused by heavy ions in the 28 nm bulk silicon inverter chains was studied. A test chip with good symmetry layout design was fabricated based on the 28 nm process, and the chip was struck by using 5 kinds of heavy ions with different linear energy transfer (LET) values on heavy-ion accelerator. The research results show that in advanced technology, smaller sensitive volume makes SET cross-section measured at 28 nm smaller than 65 nm by an order of magnitude, the lower critical charge required to generate SET will increase the reliability threat of low-energy ions to the circuit, and high-energy ions are more likely to cause single-event multiple transient (SEMT), which cannot be ignored in practical circuits. The transients pulse width data can be used as a reference for SET modeling in complex circuits. [ABSTRACT FROM AUTHOR]