Optimal Formation of Multirobot Systems Based on a Recurrent Neural Network

Abstract

The optimal formation problem of multirobot systems is solved by a recurrent neural network in this paper. The desired formation is described by the shape theory. This theory can generate a set of feasible formations that share the same relative relation among robots. An optimal formation means that finding one formation from the feasible formation set, which has the minimum distance to the initial formation of the multirobot system. Then, the formation problem is transformed into an optimization problem. In addition, the orientation, scale, and admissible range of the formation can also be considered as the constraints in the optimization problem. Furthermore, if all robots are identical, their positions in the system are exchangeable. Then, each robot does not necessarily move to one specific position in the formation. In this case, the optimal formation problem becomes a combinational optimization problem, whose optimal solution is very hard to obtain. Inspired by the penalty method, this combinational optimization problem can be approximately transformed into a convex optimization problem. Due to the involvement of the Euclidean norm in the distance, the objective function of these optimization problems are nonsmooth. To solve these nonsmooth optimization problems efficiently, a recurrent neural network approach is employed, owing to its parallel computation ability. Finally, some simulations and experiments are given to validate the effectiveness and efficiency of the proposed optimal formation approach.

Adaptive fault‐tolerant time‐varying formation tracking for multiagent systems with multiple leaders

“…By choosing h i (t) = 0, it may be used to deal with the containment control. As for other works, 4,6,7,17,38 the actuator faults are not considered, it is a difficulty to tackle the influences of unknown faults to the time-varying formation.…”

“…In recent years, the formation control of multiagent systems is an actively studied topic, where the objective is to drive multiple agents to achieve predefined constraints on their states. The broad applications of formation control have been shown in unmanned aerial vehicles (UAVs), attitude synchronization control of satellites, and teaming of multirobotics . Formation control is a special form of cooperative control of multiagent systems.…”

“…The broad applications of formation control have been shown in unmanned aerial vehicles (UAVs), 4,5 attitude synchronization control of satellites, 6 and teaming of multirobotics. 7,8 Formation control is a special form of cooperative control of multiagent systems. In recent decades, some centralized or decentralized protocols have been introduced to make the multiagent systems converge to the predefined formation.…”

Sliding Surface in Consensus Problem of Multi-Agent Rigid Manipulators with Neural Network Controller

“…Many authors have studied some new models e.g., [20][21][22][23][27][28][29]39,40] and many control approaches are proposed. Their models can be linear systems or nonlinear systems but almost all of them omit friction and disturbance or if it exists, then removing it is not focused.…”

Scalable formation control in stealth with limited sensing range

“…The roles of leaders or followers are adjustable to achieve a better performance in . Alternatively, the most suitable positions in the objective formation are derived for the robots in . However, globally available information is accessible in , communication is required in , and the overall topology is needed in .…”