Robot Path Planning using Particle Swarm Optimization of Ferguson Splines

Path Planning for Formations of Mobile Robots using PSO Technique

“…Parameters of the PSO method were adjusted in agreement with (Saska et al, 2006), where the algorithm was used in similar application. As the test scenario were chosen situations with several local extremes corresponding to feasible as well as unfeasible paths for the leader.…”

“…The method was developed by Barfoot and Clark (Barfoot et al, 2002;Barfoot & Clark, 2004) and later improved for following of trajectories with arbitrary shape within our team (Saska et al, 2006;Hess et al, 2007). In this chapter there will be published only the parts of formation control necessary for understanding of restrictions applied in the path planning while a detailed description of control inputs for each vehicle can be found in (Saska et al, 2006;Hess et al, 2007). Important fact of the formation driving of car-like robots that needs to be considered is caused by impossibility to change heading of the robot on spot.…”

“…The whole string of the splines is then in 2D case uniquely determined by n 8 variables ( n denotes the amount of splines in the string). The initial and desired state (position and orientation) of the formation is specified by 8 equations, while continuity of first and second derivative in the whole path, which is important for the formation driving as is shown in (Saska et al, 2006), Therefore, only ) 1 ( 2 − n degree of freedom define the whole path, which conforms to positions of the points in the spline connections. The whole path representation used in our method is shown in Fig.…”

“…In the literature there is no adequate method providing flexible control inputs for the followers as well as designing an optimal path for the leader of formation responding to the environment which is necessary for fully autonomous systems. This chapter proposes a path planning approach developed for leader-following formations of car-like robots which is an extension of work (published by the authors' team in (Saska et al, 2006)) designed for single robot. In this extended method a reference path calculated by the leader should be feasible for all following robots without changing a relative distance in the formation.…”

Motion- and Communication-Planning of Unmanned Aerial Vehicles in Delay Tolerant Network using Mixed-Integer Linear Programming

“…Also, many optimization methods are not easily modified to allow for coordination between multiple vehicles. Examples of popular methods used for path-or motion planning include rapidly exploring random trees, LaValle and Kuffner (2001); Kuwata et al (2009), particle swarm optimization Kennedy and Eberhart (1995); Ho et al (2013); Saska et al (2006), A andD Hart et al (1968); Stentz (1994); Likachev et al (2005) or variants of these. The performance of these methods relies heavily on the choice of a good heuristic potential.…”