Evolutionary multitasking (EMT) is an emerging research direction in the field of evolutionary computation. EMT solves multiple optimization tasks simultaneously using evolutionary algorithms with the aim to improve the solution for each task via intertask knowledge transfer. The effectiveness of intertask knowledge transfer is the key to the success of EMT. The multifactorial evolutionary algorithm (MFEA) represents one of the most widely used implementation paradigms of EMT. However, it tends to suffer from noneffective or even negative knowledge transfer. To address this issue and improve the performance of MFEA, we incorporate a prior-knowledge-based multiobjectivization via decomposition (MVD) into MFEA to construct strongly related meme helper-tasks. In the proposed method, MVD creates a related multiobjective optimization problem for each component task based on the corresponding problem structure or decision variable grouping to enhance positive intertask knowledge transfer. MVD can reduce the number of local optima and increase population diversity. Comparative experiments on the widely used test problems demonstrate that the constructed meme helper-tasks can utilize the prior knowledge of the target problems to improve the performance of MFEA.

Recently, the multifactorial evolutionary algorithm (MFEA) has achieved remarkable success in multi-task optimization (MTO) and received extensive attention from academia and industry. The key idea of MFEA is to use the inter-task knowledge transfer to produce the mutual promotion effect of all tasks. However, MFEA still has some limitations in accelerating convergence and enhancing global search ability, especially when the optima of different optimization tasks are far away. To relieve this issue, this paper integrates a new cross-task knowledge transfer, which is based on a search direction instead of an individual. The proposed knowledge transfer strategy generates offspring by the sum of an elite individual of one task and a difference vector from another task. As a basic vector, the elite individual is used to speed up the population convergence. Adding the elite individual with a difference vector from another task can enhance the search diversity. The experimental studies have shown the effectiveness and efficiency of the proposed cross-task knowledge transfer strategy, compared with the classical MFEA on a set of benchmark problems with different degrees of similarities.

Recently, multi-tasking optimization (MTO) has become a rising research topic in the field of evolutionary computation that has attracted increasing attention of academia. Comparing with single-objective optimization (SOO) and multi-objective optimization (MOO), MTO can solve different optimization tasks simultaneously by utilizing inter-task similarities and complementarities. Based on crossover operator, the classical multifactorial evolutionary algorithm (MFEA) transfers inter-task knowledge. To broaden the search region and accelerate the convergence, this paper integrates differential evolution (DE) and opposition-based learning (OBL) into MFEA and hence proposes MFEA/DE-OBL. The motivation of integrating DE and OBL is that they have different search neighborhoods and strong complementarity with simulated binary crossover (SBX) used in MFEA. Furthermore, integrating DE and OBL can help MFEA jump out of local optima. The effectiveness and efficiency of integrating DE and OBL into MFEA are experimentally studied on a set of benchmark problems with different degrees of similarities. Experimental results demonstrate that the proposed MFEA/DE-OBL dramatically improves the performance compared with the MFEA.

Intending to mimic the operating mechanism of biological neural systems, a self organizing map-based approach to task assignment of a swarm of robots in 3-D dynamic environments is proposed in this paper. This approach integrates the advantages and characteristics of biological neural systems. It is capable of dynamically planning the paths of a swarm of robots in 3-D environments under uncertain situations, such as when some robots are presented in or broken down or when more than one robot is needed for some special task locations. A Bezier path optimizing algorithm and a parameter adjusting algorithm are integrated in this paper. It is capable of reducing the complexity of the robot navigation control and limiting the number of convergence iterations. The simulation results with different environments demonstrate the effectiveness of the proposed approach.

In this paper, a SOM (self organizing map)-based approach to task assignment of multi-robots in 3-D dynamic environments is proposed. This approach intends to mimic the operating mechanism of biological neural systems, and integrates the advantages and characteristics of biological neural systems. It is capable of dynamically planning the paths of multi-robots in 3-D environments under uncertain situations, such as when some robots are added in or broken down or when more than one robot is needed for some special task locations. The effectiveness and efficiency of the proposed approach are demonstrated by simulation studies.

To realize real-time goal-oriented navigation for a mobile robot in unpredictable environments, a fuzzy reactive system is proposed in this paper. Besides the establishment of the fuzzy logic system, this paper focuses on the the physical meaning of the parameters in the fuzzy system, and proposes a systematic method to automatically suppress redundant fuzzy rules from the rule base. Under the control of the proposed system with automatic redundant fuzzy rule removal, the mobile robot can preferably avoid obstacles autonomously, and generate reasonable trajectories toward the target in various situations. The effectiveness and efficiency of the proposed approach are demonstrated by simulation and experimental studies.

In this paper, a neurofuzzy-based approach is proposed, which coordinates the sensor information and robot motion together. A fuzzy logic system is designed with two basic behaviors, target seeking and obstacle avoidance. A learning algorithm based on neural network techniques is developed to tune the parameters of membership functions, which smooths the trajectory generated by the fuzzy logic system. Another learning algorithm is developed to suppress redundant rules in the designed rule base. A state memory strategy is proposed for resolving the "dead cycle" problem. Under the control of the proposed model, a mobile robot can adequately sense the environment around, autonomously avoid static and moving obstacles, and generate reasonable trajectories toward the target in various situations without suffering from the "dead cycle" problems. The effectiveness and efficiency of the proposed approach are demonstrated by simulation studies.

In this paper, a neural network approach to task assignment, based on a self-organizing map (SOM), is proposed for a multirobot system in dynamic environments subject to uncertainties. It is capable of dynamically controlling a group of mobile robots to achieve multiple tasks at different locations, so that the desired number of robots will arrive at every target location from arbitrary initial locations. In the proposed approach, the robot motion planning is integrated with the task assignment, thus the robots start to move once the overall task is given. The robot navigation can be dynamically adjusted to guarantee that each target location has the desired number of robots, even under uncertainties such as when some robots break down. The proposed approach is capable of dealing with changing environments. The effectiveness and efficiency of the proposed approach are demonstrated by simulation studies.

In this paper, a novel biologically inspired tracking controller is proposed for real-time navigation of nonholonomic mobile robots, which is inspired by the agonist/antagonist effects in muscular sensory motor reaction of a gated dipole neural model. Through the incorporation of the biological computation element, the proposed controller is capable of generating smooth, bounded acceleration command signals for the mobile robot to track reference paths. It resolves the velocity jump problem in the conventional backstepping controllers that result from the initial tracking errors or the discontinuities in discrete paths. In addition, the proposed controller removes the unpractical assumption of "perfect velocity tracking" in some existing approaches. The effectiveness and efficiency of the proposed approach are demonstrated by simulation and comparison studies.

In this paper, a novel fuzzy logic control system is developed for reactive navigation of a behavior-based mobile robot in dynamic environments. A combination of multiple sensors is equipped to sense the obstacles near the robot, the target location and the current robot speed. A fuzzy logic system with 48 fuzzy rules is designed, which consists of three behaviors: target seeking, obstacle avoidance and barrier following. The "symmetric indecision" problem is resolved by several mandatory-turn rules, while the "dead cycle" problem is resolved by a state memory strategy. Under the control of the proposed fuzzy logic model, the mobile robot can preferably "see" the environment around, and avoid static and moving obstacles automatically. The robot can generate reasonable trajectories toward the target in various situations without suffering from the "symmetric indecision" and the "dead cycle" problems. The effectiveness and efficiency of the proposed approach are demonstrated by simulation studies.

In this paper, a novel neural network approach to self-organizing behavior of a multi-robot system is proposed, which is capable of controlling a group of mobile robots to achieve multiple tasks at several different locations, such that the desired number of robots will arrive at every target location from any arbitrary initial robot locations. The proposed model is based on a self-organizing map (SOM) neural network. Unlike some conventional approaches to multi-robot path planning for multiple tasks where the task assignment and path planning are handled separately, this model combines the robot task requirement and motion planning together, such that the robots can start to move once the total tasks are set. The robot navigation can be dynamically adjusted to guarantee each target location will have the desired number of robots, even under unexpected uncertainties, such as one robot breaks down. In addition, unlike the conventional models that are suitable for static environment only, the proposed approach is also capable of dealing with changing environment. The effectiveness of the proposed approach is demonstrated by simulation studies.