Obstacle Avoidance Of Redundant Manipulators Research Articles

Reinforcement Learning-Based Reactive Obstacle Avoidance Method for Redundant Manipulators.

Redundant manipulators are widely used in fields such as human-robot collaboration due to their good flexibility. To ensure efficiency and safety, the manipulator is required to avoid obstacles while tracking a desired trajectory in many tasks. Conventional methods for obstacle avoidance of redundant manipulators may encounter joint singularity or exceed joint position limits while tracking the desired trajectory. By integrating deep reinforcement learning into the gradient projection method, a reactive obstacle avoidance method for redundant manipulators is proposed. We establish a general DRL framework for obstacle avoidance, and then a reinforcement learning agent is applied to learn motion in the null space of the redundant manipulator Jacobian matrix. The reward function of reinforcement learning is redesigned to handle multiple constraints automatically. Specifically, the manipulability index is introduced into the reward function, and thus the manipulator can maintain high manipulability to avoid joint singularity while executing tasks. To show the effectiveness of the proposed method, the simulation of 4 degrees of planar manipulator freedom is given. Compared with the gradient projection method, the proposed method outperforms in a success rate of obstacles avoidance, average manipulability, and time efficiency.

Obstacle Avoidance and Tracking Control of Redundant Robotic Manipulator: An RNN-Based Metaheuristic Approach

In this article, we present a metaheuristic-based control framework, called beetle antennae olfactory recurrent neural network, for simultaneous tracking control and obstacle avoidance of a redundant manipulator. The ability to avoid obstacles while tracking a predefined reference path is critical for any industrial manipulator. The formulated control framework unifies the tracking control and obstacle avoidance into a single constrained optimization problem by introducing a penalty term into the objective function, which actively rewards the optimizer for avoiding the obstacles. One of the significant features of the proposed framework is the way that the penalty term is formulated following a straightforward principle: maximize the minimum distance between a manipulator and an obstacle. The distance calculations are based on Gilbert–Johnson–Keerthi algorithm, which calculates the distance between a manipulator and an obstacle by directly using their three-dimensional geometries, which also implies that our algorithm works for a manipulator and an arbitrarily shaped obstacle. Theoretical treatment proves the stability and convergence, and simulations results using an LBR IIWA seven-DOF manipulator are presented to analyze the performance of the proposed framework.

Acceleration-Level Obstacle Avoidance of Redundant Manipulators

Avoiding obstacle during path planning is a crucial issue in redundant manipulators. In this study, the obstacle avoidance of redundant manipulators, which is investigated at acceleration level, is presented. Specifically, a new acceleration-level inequality is designed and formulated, which is proven to be capable of avoiding obstacle. By combining the end-effector planning requirement (formulated as equality constraint) and incorporating the physical limits (formulated as bound constraints), the acceleration-level obstacle avoidance (ALOA) scheme for redundant manipulators is proposed. Such scheme is transformed into a quadratic program and is computed by a numerical algorithm. Simulation results under the PA10 manipulator with different obstacles further validate the effective performance of the proposed ALOA scheme.

Trajectory tracking with obstacle avoidance of redundant manipulator based on fuzzy inference systems

In presence of the uncertainties in robot dynamics, model-based control law can easily fail. In our paper, this important question is tackled by using fuzzy adaptive control to drive with obstacle avoidance an industrial redundant manipulator under the hypothesis of uncertain dynamics. This hypothesis makes our controller an original one, since the problem of the tracking trajectory in the presence of obstacles and assuming that the robot dynamics are unknown has not been discussed before in the literature. Besides, the proposed obstacle avoidance is achieved by generating a self-motion. Furthermore, the usual procedure related to the obstacle avoidance based on Euclidean distance in 3D space is made easier since this one includes only the parameters of 2D space. This self-motion is directly incorporated into the adaptive fuzzy control scheme via the filtered tracking errors. The proposed method is tested by simulations in the case of redundant robot (PUMA 560) operating in 3D space in presence of obstacles. Despite that the robot dynamics are assumed to be uncertain, the proposed control performance is satisfactory. Indeed, the trajectory tracking control, incorporating self-motion obstacle avoidance, operates effectively with weak tracking control errors and bounded actuator torques evolving in admissible range.

Obstacle avoidance of redundant manipulators using neural networks based reinforcement learning

This paper proposes a new approach for solving the problem of obstacle avoidance during manipulation tasks performed by redundant manipulators. The developed solution is based on a double neural network that uses Q-learning reinforcement technique. Q-learning has been applied in robotics for attaining obstacle free navigation or computing path planning problems. Most studies solve inverse kinematics and obstacle avoidance problems using variations of the classical Jacobian matrix approach, or by minimizing redundancy resolution of manipulators operating in known environments. Researchers who tried to use neural networks for solving inverse kinematics often dealt with only one obstacle present in the working field. This paper focuses on calculating inverse kinematics and obstacle avoidance for complex unknown environments, with multiple obstacles in the working field. Q-learning is used together with neural networks in order to plan and execute arm movements at each time instant. The algorithm developed for general redundant kinematic link chains has been tested on the particular case of PowerCube manipulator. Before implementing the solution on the real robot, the simulation was integrated in an immersive virtual environment for better movement analysis and safer testing. The study results show that the proposed approach has a good average speed and a satisfying target reaching success rate.