In this paper we present a robust hybrid motion/force controller for rigid robot manipulators. The main contribution of this paper is that the proposed hybrid control system is able to accomplish motion objectives in free directions and force objectives in constrained directions under parametric uncertainty both in robot dynamics and stiffness constraint constant. Also, the given scheme is prov...

In this paper, a new formulation along with numerical solution for the problem of finding a point-to-point trajectory with maximum load carrying capacities for flexible manipulators is proposed. For rigid manipulators, the major limiting factor in determining the Dynamic Load Carrying Capacity (DLCC) is the joint actuator capacity. The flexibility exhibited by light weight robots or by robots o...

Joint flexibility is a very important factor to consider in the controller design for robot manipulators if high performance is expected. Most of the research works on control of flexible-joint robots in literature have ignored the actuator dynamics to avoid complexity in controller design. The problem of designing nonlinear controller for a class of single-link flexible-joint robot manipulator...

A method for using the Time Hopping technique as a tool for probability redistribution is proposed. Applied to reinforcement learning in a simulation, it is able to re-shape the state probability distribution of the underlying Markov decision process as desired. This is achieved by modifying the target selection strategy of Time Hopping appropriately. Experiments with a robot maze reinforcement...

Robot soccer is played in a dynamic environment. All robots in a team should select their task dynamically and adaptively in a cooperative manner. This paper proposes a framework for task and role selection strategy for distributed multi-robot coordination and its application to robot soccer. To deal with such a dynamic environment, context-based cooperation method is provided. The robot team h...

We give an overview of evolutionary robotics research at Sussex over the last 5 years. We explain and justify our distinctive approaches to (artiicial) evolution, and to the nature of robot control systems that are evolved. Results are presented from research with evolved controllers for autonomous mobile robots; simulated robots, coevolved animats, real robots with software controllers, and a ...

In multi-robot settings, activity recognition allows a robot to respond intelligently to the other robots in its environment. Conditional random fields are temporal models that are well suited for activity recognition because they can robustly incorporate rich, non-independent features computed from sensory data. In this work, we explore feature selection in conditional random fields for activi...

The challenge of persistent navigation and mapping is to develop an autonomous robot system that can simultaneously localize, map and navigate over the lifetime of the robot with little or no human intervention. Most solutions to the simultaneous localization and mapping (SLAM) problem aim to produce highly accurate maps of areas that are assumed to be static. In contrast, solutions for persist...

in this project guidance and control of underwater robot, including three engines and propeller attached to it, by fuzzy control has been investigated. fuzzy control is done based on human experience and requiered laws. the robot can also be controlled and guided by the user. this robot may be used in sea or swimming pool environment for finding goal point and locate in desired direction. in ad...

Selection of neural network learning rates to obtain satisfactory performance from neural network controllers is a challenging problem. To assist in the selection of learning rates, this paper investigates robotic system sensitivity to neural network (NN) learning rate. The work reported here consists of experimental and simulation results. A neural network controller module, developed for the ...