Search

An intelligent trajectory planning and obstacle avoidance method based on the improved twin delayed deep deterministic policy gradient algorithm (TD3) was proposed to solve the trajectory planning problem for a 4-DOF manipulator mounted on a satellite.The training strategy had 2 periods.In the pre-training stage, the target position was always guided combining with the output of the strategy network to optimize the trajectory.After the pre-training, the algorithm can autonomously output the velocity trajectory while the initial position and the target were specified randomly in the joint space of the manipulator.This target-guided mechanism decreased the unnecessary explorations and improved the learning efficiency in high dimensional action space.In the second training stage, a collision-free safety reference trajectory was firstly obtained by demonstration, and then this trajectory was constantly learned during the training process until the final output trajectory has the ability to avoid obstacles.

In order to study the influence of the whole dock block on dock floor and foundation, the force condition of dock floor and foundation is calculated and compared under working conditions of independent block. From different thicknesses, the structure of whole block is analyzed and optimized, and the force condition of dock floor and foundation is calculated under working conditions of the whole block. The influence of pile-soil co-reaction on pile foundation is analyzed. The results show that the force condition of dock floor and foundation cannot meet the requirements when using independent block. The whole block can make the load more uniform, improve the force condition, and make force and cracks meet the requirements. When pile-soil co-reaction is considered, the pile force will be reduced. When the longitudinal line load is greater than that designed for the original dock, priority should be given to the whole block. The results can provide reference for similar projects in the future.

A wreck salvage scheme is designed for the integral salvage of “Yangtze River Estuary II” ancient ship, and the dynamic response of the critical state of salvage is investigated via numerical simulation. Comprehensive studies including the motion response characteristics of the multi-body coupling system and the tension of the cable under different sea conditions are conducted. The results show that the instability of the salvage system increases under the transverse sea condition, and the operation risk is obviously higher than other waves of the same wave level conditions. In addition, the tension responses of lifting cables and mooring cables are higher in the off-bottom stage than that of the submerged part of the wreck. The numerical results demonstrate the feasibility of the salvage scheme, providing reference for decision-making on sea conditions to avoid the risk of salvage operation.

As a widely-applied public-key cryptosystem in TLS, SSL and IPSec protocols, the security of RSA cryptosystem is of great importance. At FDTC 2014, Rauzy and Guilley proposed several improved countermeasure algorithms of RSA implementation based on Chinese remainder theorem, which were used to defeat fault-injection attacks. New fault-injection attacks on two of their countermeasure algorithms are proposed. During the RSA computation process, a permanent fault is injected and then a faulty RSA signature result is induced. The RSA private key can be obtained by using the faulty RSA signature and the correct result. Therefore, Rauzy and Guilley’s two countermeasure algorithms cannot resist our fault-injection attack.