Path planning of cooperating industrial robots using evolutionary algorithms

Abstract

Under the concept of "Industry 4.0", production processes will be pushed to be increasingly interconnected, information based on a real time basis and, necessarily, much more efficient. In this context, capacity optimization goes beyond the traditional aim of capacity maximization, contributing also for organization's profitability and value. Indeed, lean management and continuous improvement approaches suggest capacity optimization instead of maximization. The study of capacity optimization and costing models is an important research topic that deserves contributions from both the practical and theoretical perspectives. This paper presents and discusses a mathematical model for capacity management based on different costing models (ABC and TDABC). A generic model has been developed and it was used to analyze idle capacity and to design strategies towards the maximization of organization's value. The trade-off capacity maximization vs operational efficiency is highlighted and it is shown that capacity optimization might hide operational inefficiency.

Reinforcement Learning-Based Safe Path Planning for a 3R Planar Robot

“…Sensors, target, and obstacle was illustrated orange, green, and red filled circles, respectively. d, γ, di, and γi were calculated by using Equations (1)(2)(3)(4).…”

“…In other study, path planning process has been realized faster by using bidirectional associate learning [3]. Path planning process for an industrial robot has been implemented by using genetic algorithm [4]. An improved A* algorithm has been compared to original A* algorithm and the developed algorithm has generated path which is short and high success rate [5].…”

Adaptive Simplex Architecture for Safe, Real-Time Robot Path Planning

“…In the case of robot arms (i.e., serial manipulators), the current approaches to obstacle avoidance use various combinatorial search strategies to find suitable robot poses along a trajectory, e.g., evolutionary algorithms [ 15 , 16 ], different versions of the Rapidly Exploring Random Tree method [ 17 , 18 , 19 , 20 ], etc. The common aspects in these approaches are that they take into consideration the potential collisions of all the joints of the robot with the obstacle(s), and, in so doing, they require repeated computations of inverse kinematics for a high number of robot poses resulting from the different combinatorial search strategies being used.…”

Path planning optimization of six-degree-of-freedom robotic manipulators using evolutionary algorithms

“…Cooperating robotic manipulators are often used in industrial applications. 10,21 In both cases, the method is validated using ABB IRB 120 robotic manipulator. In observed cases, robotic manipulators are transporting a prismatic shaped object with weight of 2 kg along the calculated path.…”

“…Authors conclude that the approach of using a multiple population GA is valid and produces results quickly. Larsen et al 10 show the application of evolutionary algorithms and rapidly exploring random trees (RRT) with various parameters on a robot system with KUKA KR210 and KUKA R3100 robots on a common axis to calculate collision-free paths. The results show superior results when using evolutionary algorithms in comparison with sampling methods, as well as concluding that the results gained using GA are superior to ones gained with RRT.…”