Robotic arm sorting aims to determine the optimal grasping poses and categories of objects to be sorted based on perception information and then place objects into corresponding positions. Most methods combine an object detection algorithm and a grasp detection algorithm sequentially. Such a two-stage strategy results in unsatisfactory grasp accuracy and speed. This paper proposes MSFF-SNet, which directly work with grasp poses as learning targets, while simultaneously recognizing the objects to be sorted. Specifically, multi-scale features from different layers of a ResNet50 are first extracted and intra-scale features are fused using a self-attention mechanism, emphasizing the global contextual information. The features of multiple scales are then fused through a cross-scale feature fusion module. Finally, a multi-task detection head is used to directly make pixel-level predictions of grasping poses and object categories. MSFF-SNet achieved a grasp accuracy of 99.62% on the Cornell Grasping Dataset and a mean Average Precision with Grasp of 79.52% on the Visual Manipulation Relationship Dataset, achieving the state-of-the-art performance. Besides, it achieved the highest inference speed on the Visual Manipulation Relationship Dataset. The code is available at https://github.com/wzhy2000/MSFF-SNet.

This paper proposes a hardware architecture for Context-based Adaptive Binary Arithmetic Code (CABAC) decoding in H.264/AVC. The proposed architecture takes both bin decoding efficiency and control efficiency into account. This architecture improves time and storage efficiency by taking full use of the new found characters of syntax elements (SEs). In this architecture, two controllers are designed to decode SEs. One is the main controller, and the other is the sub controller, which controls the decoding of residual block SEs. The parallel working mode of the two controller improves the time-consuming performance of the system. Experimental result shows that our design is quite rich for main profile CIF video stream at 30fps.

An efficient algorithm based on graph-theoretic approach and genetic algorithm for finding optimal deadlock-free schedules in the automated manufacturing systems with limited central buffers is presented. The scheduling problem introduced In this work involves sequencing the operations on resources to avoid the deadlock situation and to minimize the makespan. With the help of digraph models of automated manufacturing systems, deadlock avoidance policy is proposed to supervise the release and acquisition of resources. In order to satisfy the deadlock free constraint of chromosomes, the deadlock avoidance policy is embedded into the decoding procedure of genetic algorithm and after adaptation of gene sequences, the feasibility of solutions can always be guaranteed for the peculiarity of the scheduling problem. With this deadlock free scheduling method, the optimal deadlock free schedules can be got under the restriction of different buffer capacities. The efficiency of deadlock free scheduling algorithm is proved by simulation results.

A class of flexible manufacturing systems is modeled by timed Petri nets, and a new deadlock free scheduling method based on genetic algorithm and timed Petri net model is proposed. Under the framework of timed Petri nets model, the scheduling problem can be formulated as finding a feasible transition firing sequence to avoid the deadlock situation and to minimize the makespan. In the genetic algorithm, Petri net transition sequence is coded and a deadlock detection method based on siphon technology is addressed to reschedule the sequence of transitions, and thus the quality of solutions can be improved. In the fitness computation procedure, a penalty item for the infeasible solution is involved to prevent the search process from converging to the infeasible solutions. The method proposed In this work can get a feasible scheduling strategy as well as enable the system to achieve good performance, and this is shown by simulation results.