Enhanced approach for energy-efficient trajectory generation of industrial robots

The demands for machining by industrial robots have been increasing owing to their low installation cost and high flexibility. A novel trajectory generation algorithm for high-speed and high-accuracy machining by industrial robots is proposed in this paper. Linear interpolation in the workspace and smooth trajectory generation at the corners are important in industrial machining robots. Because industrial robots are composed of rotational joints, the joint space has a nonlinear relationship with the workspace. Therefore, linear interpolation in the joint space, which has been widely used in conventional machine tools, does not guarantee linear interpolation in the actual machining workspace. This results in the degradation of the machining surface. The proposed trajectory generation algorithm based on the decoupled approach can achieve linear interpolation in the workspace by separating the position commands into Cartesian coordinates and the orientation commands into spherical coordinates. In addition, a novel corner smoothing method that generates a smooth and continuous trajectory from discrete commands is proposed in this paper. The proposed kinematic local corner smoothing generates a smooth trajectory by using a 3-segmented constant jerk profile at the corners in the joint space. The sharp corners can thereby be replaced by smooth curves. The resulting cornering error is controlled by varying the cornering duration. The simulation results demonstrate the effectiveness of the proposed kinematic smoothing algorithm in achieving linear tool motion in straight sections and in generating smooth trajectories at corner sections within the user-defined tolerance.

Download Full-text

Path Planning Collision Avoidance using Reinforcement Learning

10.48011/asba.v2i1.1597 ◽

2020 ◽

Author(s):

Josias G. Batista ◽

Felipe J. S. Vasconcelos ◽

Kaio M. Ramos ◽

Darielson A. Souza ◽

José L. N. Silva

Keyword(s):

Reinforcement Learning ◽

Path Planning ◽

Production Process ◽

Collision Avoidance ◽

Production Systems ◽

Learning Algorithm ◽

Computational Cost ◽

Trajectory Generation ◽

Industrial Robots ◽

Q Learning

Industrial robots have grown over the years making production systems more and more efficient, requiring the need for efficient trajectory generation algorithms that optimize and, if possible, generate collision-free trajectories without interrupting the production process. In this work is presented the use of Reinforcement Learning (RL), based on the Q-Learning algorithm, in the trajectory generation of a robotic manipulator and also a comparison of its use with and without constraints of the manipulator kinematics, in order to generate collisionfree trajectories. The results of the simulations are presented with respect to the efficiency of the algorithm and its use in trajectory generation, a comparison of the computational cost for the use of constraints is also presented.

Download Full-text