In this paper, we discuss an algorithm for distributed formation of a lattice structures using a team of mobile robots. Lattice structures can be used for solving task allocation problems, as well as for utilizing cooperative swarm like motion for the agents. We are specifically dealing with the problem of constructing a lattice decentralized with the agents having only a limited sensing radius and a possibly imperfect communication channel that make ¿agree and go¿ methods unsuitable for solving the problem. The proposed algorithm is based on reducing the 2D problem to an 1D problem, i.e. moving on a curve that connects all the lattice points without intersecting itself. The algorithm is decentralized and is exact in the sense that all agents will converge to the lattice structure.

In this paper we present a polynomial navigation function (NF) for a sphere world that can be constructed almost locally, with partial knowledge of the environment. The presented navigation function is C2and as a result the computational complexity is very low, while the construction uses local knowledge and information. Moreover, an almost locally computable diffeomorphism between convex obstacles and spheres is presented, allowing the NF scheme to be used in a workspace populated by convex obstacles. Our approach is not strictly local in the epsiv sense, i.e., the field around a point is not influenced only by an e region around the point, but rather it is local in the sense that the NF around each obstacle is influenced only by the obstacle and the adjacent obstacles. In particular, we require, in the vicinity of an obstacle, the distance between the obstacle and the adjacent obstacles. Simulations are presented to verify this approach.

In this paper we study the problem of controlling a micro robot which moves either on a line or on circle of predetermined radius. Locomotion constraints of this type are usual in micro robots, and therefore, it is important to have efficient and easy to implement ways of coping with these constraints. To solve the problem we present a multilevel motion controller that can be easily implemented on a robot with scarce computational resources as it does not rely on complex logical operations. It reduces the kinematics of the micro robot to the kinematics of a unicycle, screening in effect the micro behavior from the high level planner. Simulated results are provided to verify the proposed methodology.

In this paper we present a new navigation function for a sphere world that can be computed locally with limited knowledge of the environment. By requiring smooth and not analytic NF, the effect of each obstacle is exactly nullified outside a sensing zone around the obstacle (the only required parameter is the width of the sensing zone). This allows the computation of the navigation function using information from a single obstacle each time. We present simulations to verify the validity of this approach.

In the area of micro-robotics, control problems have to cope with a number of issues not found on macro-scale robotics. Micro robots moving in the micro-world have limited capabilities and frequently must cooperate in large numbers. In this paper we focus at an object carrying task performed by a number of micro-robots. We study a number of combinations, of agent-object contact types and agent motion principles in order to find algorithms of decomposing a given object trajectory to agent trajectories.

We have developed a laser scanner based simultaneous localization and map building method, specifically addressing the divergence problem of the classical extended Kalman filters (EKF) based simultaneous localization and map building (SLAM) algorithms. Our method utilizes two EKFs. The first is used to estimate the orientations of the robot and the obstacles, and the second estimates the positions of the robot and of the obstacles. Experimental results are also presented to verify our arguments.