Most work in navigation approaches for mobile robots does not take into account existing solutions to similar problems when learning a policy to solve a new problem, and consequently solves the current navigation problem from scratch. In this article we investigate a knowledge transfer technique that enables the use of a previously know policy from one or more related source tasks in a new task...

In this paper we address the robot-human interactions in a multi-robot and people group framework. The objective is to develop and evaluate techniques for missions in which several robots cooperate among them and interact with a group of people in order to adapt their behaviors to the ones of the people. The focus is oriented to detect people behaviors in order to act consequently for coordinat...

This paper presents a communication framework for integrating sensors in a robotic laser welding system. The framework was originally developed for the application of sensorguided robotic laser welding, but the principles are generic, making it useful in other application areas as well. To use the sensor measurements during the robot motion, a synchronisation mechanism is presented for an image...

Trajectory planning is the basis of robot control. A robot with seven degrees of freedom is the object of study. The shortest time is taken as the trajectory optimization target. The joint trajectory planning is carried out by using B-spline curve. Under the constraint of kinematics parameters, the time optimization of the motion trajectory is realized by using the improved genetic algorithm. T...

In this paper, path planning of wheeled mobile robots is investigated in presence of environmental obstacles based on potential field method. To do this, nonlinear dynamic equations of the mobile robot are derived with the respect of its nonholonomic constraints. To avoid the obstacles during the robot’s motion, repulsive potential functions are used. By implementation of potential field method...

Partially observable Markov decision processes (POMDPs) have been successfully applied to various robot motion planning tasks under uncertainty. However, most existing POMDP algorithms assume a discrete state space, while the natural state space of a robot is often continuous. This paper presents Monte Carlo Value Iteration (MCVI) for continuous-state POMDPs. MCVI samples both a robot’s state s...

This paper presents a methodology for motion planning in outdoor environments that takes into account specific characteristics of the terrain. Instead of decomposing the robot configuration space into “free” and “occupied”, we consider the existence of several regions with different navigation costs. Costs are determined experimentally by navigating the robot through the regions and measuring t...

We are given a connected. undirected graph G on n vertices. There is a mobile robot on one of the vertices; this vertex is labeled s. Each of several other vertices contains a single movable obsracle. The robot and the obstacles may only reside at vertices, although they may be moved across edges. A vertex may never contain more than one object (robot/obstacle). In one step, we may move either ...

This paper presents a technique for motion planning which is capable of planning trajectories for a large number of nonholonomic robots. The robots plan within a two dimensional environment that consists of stationary/moving obstacles, and fixed boundaries. Each robot uses randomized motion planner techniques based on Probabilistic Road Maps (PRM’s) to construct it’s own trajectory that is free...

This paper proposes a solution to the motion planning and control problem of a point-mass robot which is required to move safely to a designated target in a priori known workspace cluttered with fixed elliptical obstacles of arbitrary position and sizes. A tailored and unique algorithm for target convergence and obstacle avoidance is proposed that will work for any number of fixed obstacles. Th...