Obstacle-free Path Research Articles

A NEW PARAMETERIZED POTENTIAL FAMILY FOR PATH PLANNING ALGORITHMS

In this work, it is proposed a new family of potentials for path planning algorithms, one kind to the goal and other to the obstacles. With these new potentials it is possible to parameterize the potential scale length and strength easily, providing better control over the moving object path characteristics. In this way, the path problem can be treated analytically. For example, the minimum distance between the moving object and the obstacles can be calculated as a function of the potential parameters. Simulations are made to test its ability to guide a vehicle through an obstacle-free path towards the goal. The success rate of the moving object on reaching the goal is compared with the potential parameters and with obstacle configuration and distribution parameters.

Navigation Techniques for Mobile Robots in Greenhouses

This article discusses navigation methods for mobile agricultural robots in greenhouses. Today, many dangers of repetitive and hazardous agricultural tasks for humans could be avoided by using robots. The problem of autonomous navigation in greenhouses has been solved using both deliberative and pseudo-reactive techniques. The first one utilizes a map-based algorithm to create a safe, obstacle-free path to circulate throughout the greenhouse. The second technique applies a sensor-feedback algorithm to move through the greenhouse corridors. Furthermore, along the trajectory a sensorial map is built. Both approaches have been implemented and tested in a real environment, with promising results.

A Complete and Scalable Strategy for Coordinating Multiple Robots Within Roadmaps

This paper addresses the challenging problem of finding collision-free trajectories for many robots moving toward individual goals within a common environment. Most popular algorithms for multirobot planning manage the complexity of the problem by planning trajectories for robots individually; such decoupled methods are not guaranteed to find a solution if one exists. In contrast, this paper describes a multiphase approach to the planning problem that uses a graph and spanning tree representation to create and maintain obstacle-free paths through the environment for each robot to reach its goal. The resulting algorithm guarantees a solution for a well-defined number of robots in a common environment. The computational cost is shown to be scalable with complexity linear in the number of the robots, and demonstrated by solving the planning problem for 100 robots, simulated in an underground mine environment, in less than 1.5 s with a 1.5 GHz processor. The practicality of the algorithm is demonstrated in a real-world application requiring coordinated motion planning of multiple physical robots.

Global Map Building and Navigation of Mobile Robot Based on Ultrasonic Sensor Data Fusion

In mobile robotics, ultrasonic sensors became standard devices for collision avoiding. Moreover, their applicability for map building and navigation has exploited in recent years. In this paper, as the preliminary step for developing a multi-purpose autonomous carrier mobile robot to transport trolleys or heavy goods and serve as robotic nursing assistant in hospital wards. The aim of this paper is to present the use of multi-sensor data fusion such as ultrasonic sensor, IR sensor for mobile robot to navigate, and presents an experimental mobile robot designed to operate autonomously within both indoor and outdoor environments. The global map building based on multi-sensor data fusion is applied for recognition an obstacle free path from a starting position to a known goal region, and simultaneously build a map of straight line segment geometric primitives based on the application of the Hough transform from the actual and noisy sonar data. We will give an explanation for the robot system architecture designed and implemented in this study and a short review of existing techniques, Hough transform, since there exist several recent thorough books and review paper on this paper. Experimental results with a real Pioneer DX2 mobile robot will demonstrate the effectiveness of the discussed methods.

Real-time motion planning of an autonomous mobile manipulator using a fuzzy adaptive Kalman filter

This paper presents the real-time motion planning i.e., map building and path planning of an autonomous mobile manipulator capable of scanning natural terrain using a detector e.g., a landmine detector. Map building generates a terrain map using the measurements of laser and ultrasonic rangefinders, and path planning uses the map to define an obstacle-free path for the detector. Map building involves sensor fusion to tackle the uncertainties associated with range measurement. Fusion takes place in a hierarchical filtering process that updates the map in real time and also optimizes the scanning process based on the terrain type. The filtering process includes a proposed fuzzy adaptive Kalman filter in which the gain of the filter is adapted using a fuzzy model that characterizes the terrain. The efficiency of the proposed map building and path planning methods has been verified by experiments on a prototype mine detector robot.

COMPLETE AND SCALABLE MULTI-ROBOT PLANNING IN TUNNEL ENVIRONMENTS

This paper addresses the challenging problem of finding collision-free trajectories for many robots moving to individual goals within a common environment. Most popular algorithms for multi-robot planning manage the complexity of the problem by planning trajectories for robots sequentially; such decoupled methods may fail to find a solution even if one exists. In contrast, this paper describes a multi-phase approach to the planning problem that guarantees a solution by creating and maintaining obstacle-free paths through the environment as required for each robot to reach its goal. Using a topological graph and spanning tree representation of a tunnel or corridor environment, the multi-phase planner is capable of planning trajectories for up to r = L – 1 robots, where the spanning tree includes L leaves. Monte Carlo simulations in a large environment with varying number of robots demonstrate that the algorithm can solve planning problems requiring complex coordination of many robots that cannot be solved with a decoupled approach, and is scalable with complexity linear in the number of robots.

Obstacle avoidance algorithm for visual navigation using ultrasonic sensors and a CCD camera

An obstacle-avoidance algorithm is presented for autonomous mobile robots equipped with a CCD camera and ultrasonic sensors. This approach uses segmentation techniques to segregate the floor from other fixtures, and measurement techniques to measure the distance between the mobile robot and any obstacles. It uses a simple computation for the selection of a threshold value. This approach also uses a cost function, which is combined with image information, distance information, and a weight factor, to find an obstacle-free path. This algorithm, which uses a CCD camera and ultrasonic sensors, can be used for cases including shadow regions, and obstacles in visual navigation and in various lighting conditions.

Sensor Fusion Based Intelligent Motion Control for Nonholonomic Wheeled Mobile Robots

ABSTRACT This paper presents a sensor fusion based intelligent motion control scheme for nonholonomic wheeled mobile robots under unstructured environments. The proposed scheme is composed of path planning and tracking control modules, considering kinematic constraints in steering control of nonholonomic vehicles. First, the path planning module generates an obstacle-free short path as a sequence of control vectors of orientation using a genetic algorithm. Then, the tracking control module produces the references for steering control using a sensor fusion network. Simulations of path planning and preliminary experiments with internal and external sensors are presented to show the effectiveness of the proposed control scheme

Sensor-Based Path Planning and Tracking Control Scheme for Nonholonornic Wheeled Mobile Robots

This paper presents a control scheme for intelligent motion control of nonholonomic wheeled mobile robots under unstructured environments. First, using a simple genetic algorithm, the path planning module calculates an obstacle-free path as a sequence of control vectors of orientation, considering kinematic constraints in steering control. Then, the tracking control module calculates the references for motion control of the mobile robot using a sensor fusion neural network. Preliminary experiments for teaching the neural network with internal and external sensors are presented to show the effectiveness of the proposed control scheme.

Learning sensor-based navigation of a real mobile robot in unknown worlds

In this paper, we address the problem of navigating an autonomous mobile robot in an unknown indoor environment. The parti-game multiresolution learning approach is applied for simultaneous and cooperative construction of a world model, and learning to navigate through an obstacle-free path from a starting position to a known goal region. The paper introduces a new approach, based on the application of the fuzzy ART neural architecture, for on-line map building from actual sensor data. This method is then integrated, as a complement, on the parti-game world model, allowing the system to make a more efficient use of collected sensor information. Then, a predictive on-line trajectory filtering method, is introduced in the learning approach. Instead of having a mechanical device moving to search the world, the idea is to have the system analyzing trajectories in a predictive mode, by taking advantage of the improved world model. The real robot will only move to try trajectories that have been predicted to be successful, allowing lower exploration costs. This results in an overall improved new method for goal-oriented navigation. It is assumed that the robot knows its own current world location-a simple dead-reckoning method is used for localization in our experiments. It is also assumed that the robot is able to perform sensor-based obstacle detection (not avoidance) and straight-line motions. Results of experiments with a real Nomad 200 mobile robot are presented, demonstrating the effectiveness of the discussed methods.

Reports and surveys

ROBOTICS AND AUTOMATION WORLDWIDE1. AustraliaRobot Etherbot. At Monash University researchers report the development of a portable mobile robot system called ‘Etherbot’. It carries no computer aboard but instead, the calculations required to determine the robot's location and the shortest obstacle-free path to a desired destination are carried on a nearby workstation. This is a Silicon Graphics workstation with which the robot communicates via a 2Mb radio Ethernet link. This reduces the payload and increases the time that the robot can travel before its batteries need recharging.

AN ON-LINE ALGORITHM FOR NAVIGATING IN AN UNKNOWN ENVIRONMENT

Suppose that a robot is required to traverse a two-dimensional scene with impenetrable rectangular obstacles. The robot has no information about the obstacles in advance and the size, location, and orientation of each obstacle in the scene are arbitrary, yet the robot can see and move in any direction. In this paper we construct an on-line algorithm for the robot to determine an obstacle-free path to its destination dynamically. The primary concern for such on-line algorithm is the competitiveness coefficient which essentially compares the actual distance traversed to the length of the shortest path. We show that if the aspect ratio of every rectangular obstacle in the scene is bounded by a constant r, then our algorithm achieves the optimal competitiveness coefficient which is r/2+1.

A New Integrated Path Planning and Generation Real Time System For Mobile Robots

In this paper we present an integrated path generation and path planning system for mobile robots and intelligent autonomous vehicles. The system integrates a new extension of a planning algorithm to determine an optimal obstacle free path, with a new efficient path generation method based on β-splines to compute the postures defining the path to follow from the results of the path planning algorithm. The result is a continuous stream of postures with continuity in position, heading and curvature, maximum curvature lower than a certain value provided by vehicle´s kinematic and dynamic analysis, and smooth quasilinear curvature transitions. In the paper we also present the implementation of the system in a real time vehicle´s controller, and the application to RAM-I a new autonomous mobile robot designed and built for navigation in indoor and outdoor industrial environments.

Dynamic motion planning of autonomous vehicles

A method for planning the motions of autonomous vehicles moving on general terrains is presented that obtains the geometric path and vehicle speeds that minimize motion time considering vehicle dynamics, terrain topography, obstacles, and surface mobility. The terrain is represented by a smooth cubic B patch, and the geometric path consists of a B spline curve mapped to the surface. The time-optimal motions are computed by first obtaining the best obstacle-free path from all paths represented by a uniform grid. This path is further optimized using a local optimization procedure, using the optimal motion time along the path as the cost function and the control points of a B spline as the optimizing parameters. Examples are presented that demonstrate the method for a simple dynamic model of a vehicle moving on mountainous terrain.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>