Sharif Digital Repository

Design and construction of multi-agent systems is a challenging but an intriguing problem. It is because of the intrinsic distribution of the intelligent components. In such environments the interaction and communication between the constituent parts extends the complexity since appropriate coordination methods need to be designated and employed. In this paper a successful experiment in designing and implementing such an environment is presented1. The test bed for this research is the rescue simulation environment. The architecture of the implemented heterogeneous agents takes advantage of various algorithms. These algorithms make the agents act intelligently by themselves albeit they happen... 

In this paper, two new approaches, using the combination of Hopfield Neural Network and Genetic Algorithm for solving the Robot Motion Planning Problem both in Crisp and Fuzzified environments are presented. Based on the hypothesis of Genetic Algorithms, the Genomes and Chromosomes of the algorithm are modified so that they can he used to solve the Motion Planning Problem. Because of some problem restrictions and limits hinder us to use the generic Genetic Algorithm; some modifications are applied to the main algorithm to able us to solve the problem. Although the proposed algorithms are both rely on Genetic Algorithm, the heart of both is based on Hopfield Neural Network Robot Path Planner... 

In this paper, two online path planning methods are presented for SURENA III humanoid robot by using model predictive control scheme. The methods are general control schemes which can generate the online motions for walking of a humanoid robot. For lowering computational costs a three dimensional linear inverted pendulum model is used instead of the full dynamical model of the robot. The generated trajectories are then used for computing the zero-moment point (ZMP) of the robot and the joint torques. The resulted joint torques of the two methods are compared to torques obtained from Genetic Algorithm (GA) path planning method presented for SURENA III humanoid robot in previous studies. The... 

In this paper, the problem of obtaining the optimal trajectory of a Dual-Arm Cam-Lock (DACL) robot is addressed. The DACL robot is a reconfigurable manipulator consisting of two cooperative arms, which may act separately. These may also be cam-locked in each other in some links and thus lose some degrees of freedom while gaining higher structural stiffness. This will also decrease their workspace volume. It is aimed to obtain the optimal configuration of the robot and the optimal joint trajectories to minimize the consumed energy for following a specific task space path. The Pontryagin's Minimum Principle is utilized with a shooting method to resolve kinematic redundancy. Numerical examples... 

In this paper, the path planning problem of special hyper-redundant manipulator with lockable joints is solved using particle swarm optimization. There is a locking mechanism in each link of this tendon-actuated manipulator. At any time, all links of the manipulator must be locked except one. Then by pulling the cables, the configuration of the corresponding link will change and the manipulator will tilt to its new position. Therefore, by unlocking the links in sequence and pulling the cables, any desirable configuration of manipulator can be reached. In path planning problem, the desired path of the end-effector is given and the optimum sequence of switching (discrete) and the optimum... 

In this paper, the path planning problem of special hyper-redundant manipulator with lockable joints is solved using particle swarm optimization. There is a locking mechanism in each link of this tendon-actuated manipulator. At any time, all links of the manipulator must be locked except one. Then by pulling the cables, the configuration of the corresponding link will change and the manipulator will tilt to its new position. Therefore, by unlocking the links in sequence and pulling the cables, any desirable configuration of manipulator can be reached. In path planning problem, the desired path of the end-effector is given and the optimum sequence of switching (discrete) and the optimum... 

This paper presents an offline path planning method in 3D space for a surveillance aerial vehicle. In this method, the aerial vehicle is supposed to visit particular points on the path, and the collision between the vehicle and the fixed obstacles in the environment must be avoided. In order to accomplish the mission, first, the path is generated using B-splines. Then, the feasibility of tracking the designed path for the vehicle is considered by analyzing the vehicle's dynamic constraints, such as limitations on deflections of control surfaces. The analysis is supported by a simulation. Potential extension of the proposed analysis to multiple aerial vehicles has been also discussed at the... 

This paper presents evolutionary methods for optimization in dynamic mobile robot path planning. In dynamic mobile path planning, the goal is to find an optimal feasible path from starting point to target point with various obstacles, as well as smoothness and safety in the proposed path. Pattern search (PS) algorithm, Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) are used to find an optimal path for mobile robots to reach to target point with obstacle avoidance. For showing the success of the proposed method, first they are applied to two different paths with a dynamic environment in obstacles. The first results show that the PSO algorithms are converged and minimizethe... 

Using mobile robots in disaster areas can reduce risks and the search time in urban search and rescue operations. Optimal path-planning for mobile robotics can play a key role in the reduction of the search time for rescuing victims. In order to minimize the search time, the shortest path to the target should be determined. In this paper, a new integrated Reinforcement Learning—based method is proposed to search and find a hidden target in an unknown environment in the minimum time. The proposed algorithm is developed in two main phases. Depending on whether or not the mobile robot receives the signal from the hidden target, phases I or II of the proposed algorithm can be carried out. Then,... 

In this paper, a new method for path planning is proposed using a genetic algorithm (GA). Our method has two key advantages over existing GA methods. The first is a novel environment representation which allows a more efficient method for obstacles dilation in comparison to current cell based approaches that have a tradeoff between speed and accuracy. The second is the strategy we use to generate the initial population in order to speed up the convergence rate which is completely novel. Simulation results show that our method can find a near optimal path faster than computational geometry approaches and with more accuracy in smaller number of generations than GA methods. © 2009 IEEE  

This paper seeks to provide a probabilistic control framework, named Probabilistic Multiple-Horizon Multiple-Model Predictive Control, for the soft and precise landing on an asteroid. The modified version of the Predictive Path Planning method is also introduced to generate a safe and smooth reference trajectory for landing. The Probabilistic Multiple-Horizon Multiple-Model Predictive Control is carried out in two phases; the offline phase to calculate the difference between models, and the online phase to use a probabilistic approach to track the reference trajectory. The difference of the dynamical models is utilized in the online control method to compensate the accuracy of the... 

Using mobile robots in disaster areas can reduce risks and the search time in urban search and rescue operations. Optimal path-planning for mobile robotics can play a key role in the reduction of the search time for rescuing victims. In order to minimize the search time, the shortest path to the target should be determined. In this paper, a new integrated Reinforcement Learning—based method is proposed to search and find a hidden target in an unknown environment in the minimum time. The proposed algorithm is developed in two main phases. Depending on whether or not the mobile robot receives the signal from the hidden target, phases I or II of the proposed algorithm can be carried out. Then,... 

In this paper, a hierarchical method for trajectory design for cooperative combat missions (CCM) is presented. In a military environment, in addition to physical constraints (aircraft dynamics and mountains) there are threats made by Radars or Artillery. So an important constraint, "Avoid Threats", is added to physical constraints. Major steps in trajectory design are: "Target Assignment", "Path Planning", "Path Smoothing and Trajectory Design". The most important points and a brief algorithm for each step is presented in this paper. Finally the method is applied to special case and the results presented. ©2008 IEEE  

This paper initially deals with the design of a new customized reconfigurable mobile parallel mechanism. This mechanism is called "Taar Reconfigurable ParaMobile (TRPM)", consisting of three mobile robots as the main actuators. Then, the kinematics and path planning for this mechanism are represented. The newly proposed mechanism is expected to circumvent some shortcomings of inspection operation in unknown environments with unexpected changes in their workspace, e.g., in a water pipe with non-uniform section area. In this paper, "Artificial Potential Field (APF)" has been assumed to be the path planning algorithm and its resulting attractive and repulsive forces are only applied to the...