doi: 10.1109/JAS.2021.1004132

>Taking into account the effects of DoS attacks and external disturbance, a state observer is designed to remove the assumption that the states of the agent are measurable. 

>A distribute adaptive memory event-triggered mechanism is designed, which does not need global information when updating, thus reducing the communication burden. 

>This method can effectively reduce the difficulty caused by unmeasurable state and improve observer performance. In addition, the consensus performance of the system can also be improved.

doi: 10.1109/JAS.2021.100395

>Framework: We combine intention prediction and trajectory prediction for the specified intersection scenarios.

>Distribution Parameter Constraints: We propose an intersection prior trajectories model (IPTM) to create statistics of the historical trajectories, which approximates the distribution of the ground truth.

>Evaluation Metrics: We analyse the credibility of the estimated trajectory by applying the modified Hausdorff distance criteria to the predicted trajectory and the prior trajectory distribution, which does not require the ground truth.

doi: 10.1109/JAS.2021.1004135

>Proposing a finite-time and a fixed-time backstepping control scheme with which the vehicle can track the given heading with all the signals uniformly bounded and the tracking errors converge to a neighborhood of zeros within the settling time.

>Incorporating the compensator-based command filter technique into the proposed control scheme, by which the issue of “explosion of complexity” is eliminated, the filtering error can be compensated within finite/fixed time.

>Adaptive technique is introduced in the context of controller design, and the problem of unknown model parameters is solved.

doi: 10.1109/JAS.2021.1004138

>This paper proposes a control strategy called enclosing control.

>A continuous-time protocol and a sampled-data based protocol are designed for enclosing control problems.

>A special enclosing control with no leader located on the convex hull boundary under the protocols is studied.

doi: 10.1109/JAS.2021.1004141

>The sub-goals are detected automatically via computer vision.

>The agent receives an inner reward after completing the sub-goal.

>The combined input of the sub-goal and the image achieves a better result.

doi: 10.1109/JAS.2021.1004201

>Mitigating the problem of exponentially-explosive sampling times in random walk.

>Making the convolution operation on graphs more efficient and flexible like CNN.

>Experimentally validating the efficiency and effectiveness.

doi: 10.1109/JAS.2021.1004147

>A model of multi-echelon logistic networks exhibiting complex topology is constructed.

>Goods reflow is subject to positive delay.

>Uncertain demand is placed at any network node.

doi: 10.1109/JAS.2020.1003441

>Under directed switching topology, the leader-following formation control problem for discrete-time linear multi-agent systems is first considered in this work.

>A novel reduced-order observer is designed for each following agent based on the relative output information, which can estimate the state effectively.

>Based on the Lyapunov method and the modified discrete-time Algebraic Riccati Equation, a multi-step control algorithm is established for achieving the expected leader-following formation.

doi: 10.1109/JAS.2021.1004000

>The practical trade-off design between energy consumptions and consensus performances is realized with a limited total budget.

>The impacts of both switching topologies and intermittent communications are considered in consensus design and analysis.

>The leaderless and leader-following consensus are achieved in a unified framework.