Attractive Potential Function Research Articles

Learning strategies for underwater robot autonomous manipulation control

Autonomous manipulation operations represent the high intelligent coordination from robotic vision and control, it is also a symbol of the advances of robotic intelligence. The limitations of visual sensing and the increasingly complex experimental conditions make autonomous manipulation operations more difficult, particularly for deep reinforcement learning methods, which can enhance robotic control intelligence but require a lot of training process. Due to the high-dimensional continuous state space and continuous action space characteristics of underwater operations, this paper adopts a policy-based reinforcement learning method as the foundational approach. To address the issues of instability and low convergence efficiency in traditional policy-based reinforcement learning algorithms during the learning process, this paper proposes a novel policy learning method. This method adopts the Proximal Policy Optimization algorithm (PPOClip) and optimizes it through an actor-critic network. The aim is to improve the stability and effectiveness of convergence in the learning process. In the underwater training environment, a new reward shaping scheme has been designed to address the issue of reward sparsity during the training process. The manually crafted dense reward function is utilized as attractive and repulsive potential functions for goal manipulation and obstacle avoidance. On the highly complex underwater manipulation and training environment, transferred learning algorithm has been established to reduce the training times and compensate the differences between the simulation and experiment. Simulations and tank experiments have verified the performance of the proposed strategy learning method.

PDE-based fault-tolerant control of swarm deployment while preserving connectedness

The present study investigates PDE-based fault-tolerant control for a swarm system with a dynamic graph, wherein all agents maintain the communication connectivity and avoid collisions while being deployed along desired planar curves in the presence of actuator faults. Firstly, a switched parabolic system is established based on the switching of attractive potential functions between neighboring agents, occurring at the time instant when communication edges are generated between them. Secondly, a Lyapunov-based boundary controller is proposed to ensure that the switched PDE system achieves the desired planar deployment originating from equilibrium curves of this system. Finally, the finite-time stability of the closed-loop system is rigorously demonstrated to guarantee that all pairs of initially connected agents remain within each other’s sensing range for future finite time. Simulation results validate the effectiveness of the proposed research.

COLREGS-based collision avoidance algorithm for unmanned surface vehicles using modified artificial potential fields

In this paper, to improve the safety of navigation in dynamic environments, a new collision avoidance method is presented for Unmanned Surface Vehicles (USVs). It is mainly focused on dynamic obstacles and safety requirements. Convention on the International Regulations for Preventing Collisions at Sea (COLREGS) is introduced and the original artificial potential field (APF) algorithm is modified to ensure safe collision avoidance of USVs. The new attractive and repulsive potential field functions are designed and a new process of dynamic collision avoidance is constructed to solve the issue. At last, theoretical simulations and field tests are launched to validate our method. The simulation results show that the proposed method can perform safe navigation well. Through our USV platform, the effectiveness of the improved APF method for collision avoidance is also verified. Meanwhile, it is fast, effective, and deterministic.

Dynamic Pathfinding for Non-Player Character Follower on Game

Artificial Intellegences in video game are important things that can challenge game player. One of them is creating character or NPC Follower (Non-player character Follower) inside the video game, such as real human/animal attitude. Artificial Intelligences have some techniques in which pathfinding is one of Artificial Intellegence techniques that is more popular in research than other techniques. The ability to do dynamic pathfinding is Dynamic Particle Chain (DPC) algorithm. This algorithm has the ability of flocking behavior called boid to explore the environment. But, the algoritm method moves from one boid’s point to another according to the nearest radius, then it will be able to increase computation time or needed time toward the target. To finish higher computation problem in dynamic pathfinding, the researcher suggests an algorithm that is able to handle dynamic pathfinding process through attractive potential field function of Artificial Potential Field to start pathfinding toward the target and flocking behavior technique to avoid the obstacle. Based on the test result by simulation of moving environment and complex, the computation time of algorithm is faster than comparison algorithms, DPC and Astar. It concludes that the suggested method can be used to decrease computation level in dynamic pathfinding.

UAV Formation Obstacle Avoidance Control Algorithm Based on Improved Artificial Potential Field and Consensus

Aiming at the problem of UAV formation's obstacle avoidance and the consensus of position and velocity in a 3D obstacle environment, a novel distributed obstacle avoidance control algorithm for cooperative formation based on the improved artificial potential field (IAPF) and consensus theory is proposed in this paper. First, the particle model of the UAV and the dynamic model of the second-order system are established, and the topological structure of the communication network of the system is described with the knowledge of graph theory. Second, the attractive potential field function containing the coordination gains factor, the repulsive potential field function containing the influence factor of the repulsive force and the planning angle, and the potential field function between the UAVs containing the communication weight are defined. Then, the variables of position and velocity in the consensus protocol are improved by the reference vector of the formation center and the expected velocity, respectively, and a new formation obstacle avoidance control protocol is designed by combining the IAPF and the theory of consensus. Finally, the Lyapunov function is used to prove the stable convergence of the algorithm. The simulation results show that this method can not only prevent the UAV from colliding with each other while avoiding static and dynamic obstacles but also enable the UAV to quickly restore the expected formation and achieve the consensus of the relative distance, relative height, and velocity.

Collision Avoidance of 3D Rectangular Planes by Multiple Cooperating Autonomous Agents

We develop a set of novel autonomous controllers for multiple point-mass robots or agents in the presence of wall-like rectangular planes in three-dimensional space. To the authors’ knowledge, this is the first time that such a set of controllers for the avoidance of rectangular planes has been derived from a single attractive and repulsive potential function that satisfies the conditions of the Direct Method of Lyapunov. The potential or Lyapunov function also proves the stability of the system of the first-order ordinary differential equations governing the motion of the multiple agents as they traverse the three-dimensional space from an initial position to a target that is the equilibrium point of the system. The avoidance of the walls is via an approach called the Minimum Distance Technique that enables a point-mass agent to avoid the wall from the shortest distance away at every unit time. Computer simulations of the proposed Lyapunov-based controllers for the multiple point-mass agents navigating in a common workspace are presented to illustrate the effectiveness of the controllers. Simulations include towers and walls of tunnels as obstacles. In the simulations, the point-mass agents also show typical swarming behaviors such as split-and-rejoin maneuvers when confronted with multiple tower-like structures. The successful illustration of the effectiveness of the controllers opens a fertile area of research in the development and implementation of such controllers for Unmanned Aerial Vehicles such as quadrotors.

Suboptimal obstacles avoidance control of spacecraft rendezvous

Spacecraft on-orbital services and docking require their autonomous rendezvous control system to have obstacle avoidance capability. Motivated by this, a suboptimal velocity artificial potential function-based control scheme is presented. An ellipsoid model is applied to describe the outer envelopes of the service spacecraft and the obstacles via an eigenvalue algorithm. This has better description precision than the traditional methods. The potential sigmoid function is used to generate repulsive force to avoid obstacles collision. A velocity artificial potential function-based controller is finally developed to ensure that the relative speed of the service spacecraft is reduced to zero before reaching the outer envelops of obstacles. The shaping parameters of the attractive potential function are adaptively optimized. Numerical simulations are performed to demonstrate that the approach can achieve a safe and autonomous rendezvous with fuel cost saved.

Artificial Potential Function Safety and Obstacle Avoidance Guidance for Autonomous Rendezvous and Docking with Noncooperative Target

The problem of artificial potential function (APF) safety and obstacle avoidance guidance for autonomous rendezvous and docking of chaser spacecraft with noncooperative spacecraft is studied. The relative motion equation of the chaser and the target is established based on the line-of-sight coordinate system, the reference state is designed, and the corresponding state error is deduced. The attitude motion equation of the noncooperative target spacecraft in space is established. The safety and obstacle avoidance guidance problem of autonomous rendezvous and docking with noncooperative target is transformed into a path planning problem in a dynamic environment. The attractive potential function is designed according to the state error. In order to ensure that the chaser can safely approach the noncooperative target spacecraft, a safe corridor with ellipse cissoid is designed in the final approaching stage of autonomous rendezvous and docking. The obstacle is assumed to be a sphere with a certain radius to avoid its influence in the approach, and the obstacle potential function is designed based on the Gaussian function method. The total potential function of the system is designed according to the attractive potential function, the safe potential function, and the obstacle potential function. The total potential function of the system is modified to ensure that the reference state is the minimum of the total potential function of the system. The stability of the system is proven according to the Lyapunov stability principle, and the conditions for satisfying the monotonic decrease in the total potential function of the system are deduced. Finally, the effectiveness of the proposed method is verified by three sets of numerical simulations.

Robust sliding-mode formation control and collision avoidance via repulsive vector fields for a group of Quad-Rotors

ABSTRACTThis paper is focused on solving the collision avoidance problem for a group of Quad-Rotors which are affected by external disturbances when they are moving in a horizontal plane by means of Repulsive Vector Fields (RVFs). The RVFs are included in an attractive potential function control strategy, that allows the Quad-Rotors to reach the desired position in a geometric pattern, together with a Continuous Sliding-Mode Control (C-SMC) strategy based on Sliding-Mode Observers (SMOs) that are used to estimate, in a finite-time, the linear and angular velocities, respectively. For this purpose, a parameter, which depends on the distance among the Quad-Rotors and their velocities, is designed in order to scale the RVFs properly. In this sense, the repulsion force will be proportional to the velocity and acceleration of the Quad-Rotor when it detects any obstacle. A RVF not properly scaled may result in a collision or a Quad-Rotor movement far away from its desired position. The combination between the C-SMC strategy, the SMOs, the attractive potential functions and the RVFs robustly solves the formation control and avoidance collision problem under the presence of disturbances. Numerical simulations illustrate the performance of the RVFs when the Quad-Rotors are in risk of collision.

Discrete Artificial Potential Field Approach to Mobile Robot Path Planning

Abstract The paper introduces a path planning method for an autonomous mobile robot, called the Discrete Artificial Potential Field algorithm (DAPF). The method is different from the currently applied similar path planning approaches, such as the classical APF method, using attractive and repulsive potential field functions or the wave front algorithm. The novelty and originality of the method lies in the construction of the discrete potential field, the method of taking dynamic obstacles into account and achievement of effective solutions in terms of the path length and run time of the algorithm. The DAPF algorithm is capable of finding a collision-free path for a mobile robot in static and dynamic environments. The Path Optimization Algorithm (POA) is also proposed in the paper. Its aim is to modify the collision-free path in order to obtain a smoother and shorter path. The DAPF algorithm runs in near-real time, therefore the method can be used in practical applications. The algorithm is evaluated by simulations in the MATLAB environment and by real experiments with the use of four-wheel differentially driven mobile robots. The results were compared with a heuristic approach based on Ant Colony Optimization and demonstrate the feasibility and effectiveness of the presented approach.

Dual-well potential field function for articulated manipulator trajectory planning

A new attractive potential field function is proposed in this paper for manipulator trajectory planning. Existing attractive potential field constructs a global minimum through which maneuvering objects move down the gradient of the potential field toward this global minimum. The proposed method constructs a potential field with two minima. The purpose of these two minima is to create a dual attraction between links rather than affecting each link by the preceding one through kinematic constraints.

Aircraft Swarm Intelligence: An Approach to Coordinated Swarming with Artificial Potential Functions & Gradient Descent

This study presents an organized method of swarm coordination with the use of artificial potential functions (APFs) utilizing a first-order optimization gradient descent algorithm. With the emergence of an increasing need for Unmanned Aerial Vehicles (UAVs) system control, swarm coordination presents an approach to eliminate collisions and effectively achieve mission goal parameters. The gradient descent algorithm begins with an initial configuration and implements a step, or iteration, in a direction that is opposite to the gradient. The APFs contain both repulsive and attractive potential functions that contribute to the gradient ultimately determining the states of the agent with respect to the distance from other agents and obstacles. Obstacles or other agents projected to be too close within the path of an individual agent affect the agent’s path and dynamics. Experimental simulations consisted of three, five, and ten agents with two obstacles arranged at different initial positions. Agents’ dynamics were constrained to match the Boeing AH-6 Unmanned Little Bird (ULB). Simulations had shown each agent to effectively travel to a prescribed target location while avoiding obstacles and other agents simultaneously.

Decentralized Discrete-Time Formation Control for Multirobot Systems

Inspired from the collective behavior of biological entities for the group motion coordination, this paper analyzes the formation control of mobile robots in discrete time where each robot can sense only the position of certain team members and the group behavior is achieved through the local interactions of robots. The main contribution is an original formal proof about the global convergence to the formation pattern represented by an arbitrary Formation Graph using attractive potential functions. The analysis is addressed for the case of omnidirectional robots with numerical simulations.

Lane Changing and Merging Maneuvers of Carlike Robots

This research paper designs a unique motion planner of multiple platoons of nonholonomic car-like robots as a feasible solution to the lane changing/merging maneuvers. The decentralized planner with a leaderless approach and a path-guidance principle derived from the Lyapunov-based control scheme generates collision free avoidance and safe merging maneuvers from multiple lanes to a single lane by deploying a split/merge strategy. The fixed obstacles are the markings and boundaries of the road lanes, while the moving obstacles are the robots themselves. Real and virtual road lane markings and the boundaries of road lanes are incorporated into a workspace to achieve the desired formation and configuration of the robots. Convergence of the robots to goal configurations and the repulsion of the robots from specified obstacles are achieved by suitable attractive and repulsive potential field functions, respectively. The results can be viewed as a significant contribution to the avoidance algorithm of the intelligent vehicle systems (IVS). Computer simulations highlight the effectiveness of the split/merge strategy and the acceleration-based controllers

Mobile Robot Dynamic Path Planning Based on Artificial Potential Field Approach

Artificial potential field based mobile robot path planning approaches have been widely used. However, most methods are applied in the static environment where the target and the obstacles are stationary. In this paper, a potential field approach used in dynamic situation is proposed. Its major characteristics include a new attractive potential function as well as a repulsive potential function. The former takes the relative position and velocity between the robot and the target into consideration; the latter takes into account the relative position and velocity between the robot and the obstacles. The proposed approach guarantees the robot can track the moving target while escape from moving obstacles. Simulation experiments are carried out and the results demonstrate the effectiveness of the new potential field method.

Non-Collision Conditions in Multi-Agent Virtual Leader-Based Formation Control

Formation control is one of the most important issues of group coordination for multi-agent robots systems. Some schemes are based on the leader-followers approach where some robots are considered as group leaders which influence the group behaviour. In this work, we address a formation strategy using a virtual leader which has communication with the rest of the follower robots, considered as omnidirectional robots. The virtual leader approach presents advantages such as analysis simplification and fewer sensing requirements in the control law implementation. The formation control is based on attractive potential functions only. The control law guarantees the convergence to the desired formation but, in principle, does not avoid inter-agent collisions. A set of necessary and sufficient non-collision conditions based on the explicit solution of the closed-loop system is derived. The conditions allow concluding from the initial conditions whether or not the agents will collide. The results are extended to the case of unicycle-type robots.

Smooth Jerk-Bounded Optimal Path Planning of Tricycle Wheeled Mobile Manipulators in the Presence of Environmental Obstacles

In this work, a computational algorithm is developed for the smooth-jerk optimal path planning of tricycle wheeled mobile manipulators in an obstructed environment. Due to a centred orientable wheel, the tricycle mobile manipulator exhibits more steerability and manoeuvrability over traditional mobile manipulators, especially in the presence of environmental obstacles. This paper presents a general formulation based on the combination of the potential field method and optimal control theory in order to plan the smooth point-to-point path of the tricycle mobile manipulators. The nonholonomic constraints of the tricycle mobile base are taken into account in the dynamic formulation of the system and then the optimality conditions are derived considering jerk restrictions and obstacle avoidance. Furthermore, by means of the potential field method, a new formulation of a repulsive potential function is proposed for collision avoidance between any obstacle and each part of the mobile manipulator. In addition, to ensure the accurate placement of the end effector on the target point an attractive potential function is applied to the optimal control formulation. Next, a mixed analytical-numerical algorithm is proposed to generate the point-to-point optimal path. Finally, the proposed method is verified by a number of simulations on a two-link tricycle manipulator.

Small spacecraft formation using potential functions

A group of small spacecraft able to change its orbital formation through using the potential function is discussed. Spacecraft shapes, sizes, and maneuvering capabilities in general are not identical. All objects are assumed to maneuver under discrete thruster effects. A hyperbolic form of attractive potential function is then used to reduce the control intervention by using the natural orbital motion for approaching goal configuration. A superquadric repulsive potential with 3D rigid object representation is then used to have more accurate mutual sensing between objects. As spacecraft start away from their goals, the original parabolic attractive potential becomes inefficient as the continuous control force increases with distance linearly. The hyperbolic attractive potential offers good representation of the control force independent of the distance to goal, ensuring global stability as well.

A new potential field method for mobile robot path planning in the dynamic environments

AbstractA new potential field method for mobile robot path planning is proposed in this paper. At present, most potential field methods are designed to be applied in the stationary environment, and several improved potential functions have brought in the velocity factors in the dynamic circumstances. Based on the consideration that the moving trend of the robot in the dynamic environments is also necessary to produce more reasonable path, this paper defines new attractive potential function with respect to the relative position, velocity, and acceleration between the robot and the goal, as well as the repulsive potential function with respect to the relative positions, velocities, and accelerations between the robot and the obstacles. The virtual forces are calculated to make the robot plan its motion, not only with right positions, but also with suitable velocities. Furthermore, the robot will keep a similar moving trend with the goal and contrary trends with the obstacles. Finally, some methodic simulations are carried out to validate and demonstrate the effectiveness of the new potential field method. Copyright © 2009 John Wiley and Sons Asia Pte Ltd and Chinese Automatic Control Society

Adaptive vs. conventional potential field approaches for solving navigation problems of a real car-like wheeled robot

Adaptive Potential Field Methods (APFMs) have been proposed in this paper and their performances have been compared among them and with that of Conventional Potential Field Method (CPFM) to solve navigation problems of the mobile robot. The performance of a potential field method (PFM) depends on its chosen attractive and repulsive potential functions and the constant terms associated with them. Robots that navigate using the CPFM may not find time-optimal path and may suffer from the deadlock situations. APFM could solve the said problems by changing the constant terms associated with the potential functions to cope with the varying situations of the environment. The performances of the proposed adaptive and CPFMs have been tested through computer simulations and on a real car-like wheeled robot. The proposed PFM is found to perform better than the conventional one.