Direct step‐by‐step method for industrial robot path planning

Abstract

PurposeThe purpose of this paper is to solve the path‐planning problem of industrial robots in complex environments.Design/methodology/approachA direct method (in each step, the path is been recorded) is presented in which the search of the path is made in the state space of the robotic system, and it makes use of the information generated about the characteristics of the process, introducing graph techniques for branching. The method poses an optimization problem that aims at minimizing the distance travelled by the significant points of the robot.FindingsA new approach to solve the path‐planning problem has been introduced in which the behaviour of three operational parameters (computational time, distance travelled and number of configurations generated) have been analyzed so that the user can choose the most efficient algorithm depending on which parameter he is most interested in.Research limitations/implicationsA new technique has been introduced which yields good results as the examples show.Practical implicationsThe algorithm is able to obtain the solution to the path‐planning problem for any industrial robot working in a complex environment.Originality/valueGives a new tool for solving the path‐planning problem.

Comparing the efficiency of five algorithms applied to path planning for industrial robots

“…Distances are constraints in the optimization problem so the algorithms calculate collision-free adjacent configurations (see Section 7). Further details on robot modelling and collision avoidance can be found in Valero et al, 1997 andRubio et al, 2009. …”

“…Configuration space is obtained by generating adjacent configurations (see Rubio et al, 2009). Given a feasible configuration C k , it is said that a new configuration C p is adjacent to it if it is also feasible (i.e.…”

“…In the first part, the configuration space is generated from the initial configuration by calculating adjacent configurations. The robot end-effector must visit all the nodes that are part of the discretized workspace (see Rubio et al, 2009) until the final configuration is reached. Having calculated the configuration space, a weighted graph is created.…”

“…Some examples are Kavraki and Latombe, 1998, Isto, 1996, LaValle, 1996and 2000, Gupta, 1998. a historical approach to genetic algorithms is presented by Fares, 2007. Rubio et al, 2009 presented an approach in which the search of the path is made in the state space of the robotic system (direct approach), and it makes use of the information generated about the characteristics of the process and the techniques for introducing a branching graph.…”

“…The five algorithms have been applied to the same PUMA 560 robot, which has been modelled in wired format, see Rubio et al, 2009. To obtain collision-free configurations, obstacles have been modelled using patterned obstacles: spheres, cylinders and planes (see also Rubio et al, 2009).…”