Sharif Digital Repository

In this paper, a new approach based on Artificial Neural Networks to solve the robot motion planning problem is presented. For this purpose, a Hopfield Neural Network is used in a certain constraint satisfaction problem of the robot motion planning in conjunction with fuzzy modeling of the real robot's environment so that the energy of a state can be interpreted as the extent to which a hypothesis fit the underlying neural formulation model. Thus, low energy values indicate a good level of constraint satisfaction of the problem. Finally, since the obtained answer by the Hopfield Neural Network is not optimal, some algorithms are designed to optimize and generate the final answer  

Robot navigation is a challenging problem in robotics, which involves determining of robot positioning relative to objects in the environment, and also the mobility of robot through obstacles without colliding into them. The former is known as localization, while the latter is called motion planning. This paper introduces a roadmap method for solving motion planning problem in a dynamic environment based on Generalized Voronoi Diagram (GVD). The efficiency of the proceeding work is verified by examining it in a sample home environment. © 2008 Springer-Verlag  

Given a translating and rotating rod robot in a plane in the presence of polygonal obstacles with the initial and final placements of the rod known, the d1-optimal motion planning problem is defined as finding a collision-free motion of the rod such that the orbit length of a fixed but arbitrary point F on the rod is minimized. In this paper we study a special case of this problem in which the rod can translate freely, but can only rotate by some pre-specified given angles around F. We first characterize the d1-optimal motion of the robot under the given conditions and then present a (1 + ε)-approximation algorithm for finding the optimal path. The running time of the algorithm is bounded by... 

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... 

A manipulator mounted on a moving vehicle is called a mobile manipulator. A mobile manipulator with an appropriate suspension system can pass over uneven surfaces, thus having an infinite workspace. If the manipulator could operate while the vehicle is traveling, the efficiency concerning with the time and energy used for stopping and starting will be increased. This paper presents the kinematic and dynamic modeling of a one degree of freedom manipulator attached to a vehicle with a two degrees of freedom suspension system. The vehicle is considered to move with a constant linear speed over an uneven surface while the end effector tracks a desired trajectory in a fixed reference frame. In... 

Motion planning is a key factor in enhancing the autonomy level of unmanned flying vehicles. A new dynamic hybrid algorithm is developed to solve the motion planning problem in real-time using a heuristic optimization approach. The proposed algorithm effectively combines desired features such as rapid convergence to an optimal path with reduced computational effort. In addition to the terrain obstacles, the proposed algorithm is able to avoid random threats that may arise sporadically in the terrain. Using the maneuver automaton concept, nonlinear dynamic model and performance constraints are also considered in the process of motion planning to further ensure feasible trajectories.... 

Motion planning in an autonomous agent is responsible for providing smooth, safe and efficient navigation. Many solutions for dealing this problem have been offered, one of which is, Artificial Potential Fields (APF). APF is a simple and computationally low cost method which keeps the robot away from the obstacles in environment. However, this approach suffers from trapping in local minima of potential function and then fails to produce motion plans. Furthermore, Oscillation in presence of obstacles or in narrow passages is another disadvantage of the method which makes it unqualified for many planning problems. In this paper we aim to resolve these deficiencies by a novel approach which... 

A major issue required to enhance the autonomy level of unmanned vehicles is real-time motion planning. In this context, optimal trajectories need to be generated online considering the vehicle's dynamic potentials and constraints. However, autonomous air vehicles often need to plan and execute their missions with varying objectives that may even be dictated in flight. Therefore, the current study introduces and focuses on the new concept of variable-objective motion planning. In this regard, a new dynamic multi-objective heuristic optimization algorithm is developed for path and motion planning of autonomous air vehicles in presence of deterministic terrain obstacles as well as random... 

In a multi-robot system, a number of autonomous robots would sense, communicate, and decide to move within a given domain to achieve a common goal. In the pursuit-evasion problem, a polygonal region is given and a robot called a pursuer tries to find some mobile targets called evaders. The goal of this problem is to design a motion strategy for the pursuer such that it can detect all the evaders. In this paper, we consider a new variant of the pursuit-evasion problem in which the robots (pursuers) each moves back and forth along an orthogonal line segment inside a simple orthogonal polygon P. We assume that P includes unpredictable, moving evaders that have bounded speed. We propose the... 

The failure of mechanical components is a common phenomenon in satellites. This failure can happen in the satellite attitude control system, which causes that the control system of the satellite becomes underactuated. There have been many attempts to control the orientation of underactuated satellites. However, in most studies, the inertia matrix of the satellite is assumed to be diagonal with respect to the body coordinate system, and no limitations on the amount of torque applied by the reaction wheels have been considered. In this paper, at first, it is attempted to control the satellite using the motion planning method. The satellite control inputs are assumed to be cubic spline with... 

In this paper, we investigate an efficient deadlock-free shortest path routing algorithm for WK-recursive mesh networks which has been shown that possess several advantages like suitable to be manufactured by VLSI technology and easy to be expanded. It will be shown that the proposed algorithm requires O(√n) routing steps (where N is the network size) to route the entire network by exploiting either the self-routing or second order routing scheme. © Springer-Verlag Berlin Heidelberg 2008  

This paper presents a new approach for trajectory planning of manipulator robots based on Virtual Potential Field (VPF) in presence of static obstacles. In this method, a series of via points between starting point and goal point is obtained by traverse end-effector of manipulator in affected by different VPF while avoiding obstacles in the Cartesian space. An optimum trajectory is generated by using pattern search algorithm which determines strength of potential fields to minimize the value of desired objective function. Cubic splines are used to generate a smooth trajectory through path points in joint space that are obtained by inverse kinematics solution of corresponding points in the... 

A new methodology has been proposed to enhance inverse dynamics applications in the process of trajectory planning and optimization in terrain following flights (TFFs). The new approach uses a least square scheme to solve a general two-dimensional (2-D) TFF in a vertical plane. In the mathematical process, Chebyshev polynomials are used to model the geographical data of the terrain in a given route in a manner suitable for the aircraft at hand. The aircraft then follows the modeled terrain with sufficient clearance. In this approach the terrain following (TF) problem is effectively converted to an optimal tracking problem. Results show that this method provides a flexible approach to solve... 

This paper proposed a new curvature based path-description method for path-generation of planar mechanism, in which the position vector of a point on coupler, which follows most closely a predefined path, is directly calculated as a function of coupler motion properties. In addition this curvature based method makes it possible to define an objective function independent of rotation and translation transformations. Therefore, in this method, initial position, orientation, and coupler point vector parameters are not the optimization variable. These five parameters could be calculated as a function of other design parameters and they are found when these optimal values are obtained. Reducing... 

Motion planning and trajectory control are two basic challenges of unmanned vehicles. In motion planning problem, feasible trajectories are developed while nonlinear dynamic model and performance constraints of the vehicle under utility are considered. In this study, motion planning is performed via an enhanced particle swarm optimization algorithm. The resulting offline generated trajectories are tracked using a nonlinear trajectory control system methodology. The Lyapunov-based constrained backstepping approach and command filters are utilized in designing the trajectory control system. Command filters smoothen the input signals and provide their derivatives. Evaluation of the proposed... 

A hyper-redundant manipulator is made by mounting the serial and/or parallel mechanisms on top of each other as modules. In discrete actuation, the actuation amounts are a limited number of certain values. It is not feasible to solve the kinematic analysis problems of discretely actuated hyper-redundant manipulators (DAHMs) by using the common methods, which are used for continuous actuated manipulators. In this paper, a new method is proposed to solve the trajectory tracking problem in a static prescribed obstacle field. To date, this problem has not been considered in the literature. The removing first collision (RFC) method, which is originally proposed for solving the inverse kinematic... 

A hyper-redundant manipulator is made by mounting the serial and/or parallel mechanisms on top of each other as modules. In discrete actuation, the actuation amounts are a limited number of certain values. It is not feasible to solve the kinematic analysis problems of discretely actuated hyper-redundant manipulators (DAHMs) by using the common methods, which are used for continuous actuated manipulators. In this paper, a new method is proposed to solve the trajectory tracking problem in a static prescribed obstacle field. To date, this problem has not been considered in the literature. The removing first collision (RFC) method, which is originally proposed for solving the inverse kinematic...