Jile Jiao

Embedded Vision-Based Autonomous Move-to-Grasp Approach for a Mobile Manipulator

This paper proposes a vision-based autonomous move-to-grasp approach for a compact mobile manipulator under some low and small environments. The visual information of specified object with a radial symbol and an overhead colour block is extracted from two CMOS cameras in an embedded way. Furthermore, the mobile platform and the postures of the manipulator are adjusted continuously by vision-based control, which drives the mobile manipulator approaching the object. When the mobile manipulator is sufficiently close to the object, only the manipulator moves to grasp the object based on the incremental movement with its head end centre of the end-effector conforming to a Bezier curve. The effectiveness of the proposed approach is verified by experiments.

Bezier curve based path planning for a mobile manipulator in unknown environments

This paper presents a collision-free path planning approach based on Bezier curve for a mobile manipulator with the endpoints restricted by the manipulator. Based on these candidate endpoints and the initial posture of mobile manipulator, a series of feasible Bezier paths are obtained with the constraints from velocity, acceleration and environment. And then the optimal collision-free path is determined according to the related information of the path as well as obstacles. The mobile manipulator has the ability to adapt to the environment and the optimal path will be updated once the new detected obstacles block this path. The path planning approach is verified by simulations.

A general robot environment understanding approach inspired by biological visual cortex

A general vision approach for environment understanding of mobile robot is proposed, which is inspired by biological visual cortex. Gray level image from robot camera is firstly processed in the selective attention layer, and then in S and C layers for meaningful structure elements. With the help of the Sc layer designed for endpoints detection, the line segments map is generated to serve as the form of environment understanding results. Experiments on mobile robot are implemented by the task of avoiding obstacles with different sizes and shapes, pits, sharp cliffs, et al. The experimental results demonstrate the adaptability and versatility of the proposed approach.

A Novel Geometric Transportation Approach for Multiple Mobile Manipulators in Unknown Environments

In this paper, a geometric transportation approach is proposed for multiple mobile manipulators transporting a large object in unknown environments. The candidate interval of system width is first determined based on constraints from the object, mobile manipulators as well as the obstacles. Then, a passageway-based decision is made to facilitate the selection of the optimized system width and moving direction. On this basis, each mobile manipulator adjusts its position and posture with a form of system consistency to maintain a flexible marching while avoiding the obstacles. The main advantage of the proposed approach is that it leads to smooth changes in system configuration. The effectiveness of the proposed approach is verified by simulation experiments.

Transportation by Multiple Mobile Manipulators in Unknown Environments With Obstacles

A novel approach to transport a large object by multiple mobile manipulators in unknown environments with obstacles is proposed in this paper. The main moving direction of the system as well as its width and the leading mobile manipulator are first assigned manually or obtained automatically according to the geometric layout of mobile manipulators. Then, three transportation modes, i.e., default mode, shrink mode, and incline mode, are defined based on constraints from the object and mobile manipulators. In default mode, mobile manipulators are distributed around the object to be transported with the initial geometric layout. Mobile manipulators in shrink mode are required to lie inside the boundaries of the objects outlined rectangle, whereas multiple mobile manipulators in incline mode endeavor to hold the object with an inclined angle. On this basis, a decision based on the multiscale passageway is proposed to facilitate the selection of best transportation mode and moving direction. The effectiveness of the approach is verified by simulations and experiments.

A general image skew detection approach with a bio-inspired mechanism

This paper proposes a simple but effective bio-inspired approach for skew detection of different kinds of images including nature images, documents, paintings etc., which requires no parameter tuning. Without relying on local visual cues, the proposed approach exploits the global statistics of an image. Orientation perceptron is designed in the inspiration of biological simple cells for local orientation detection. Statistics of their outputs are processed and then transferred by orientation transform into a curve whose maximum value is used to determine the skew angle. The effectiveness of the proposed approach is verified by experiments.

Autonomous grasp of the embedded mobile manipulator with an eye-in-hand camera

This paper proposes an autonomous grasp method for the embedded mobile manipulator with an eye-in-hand CMOS camera. A three-stage scheme including object searching, approaching and grasping operation is adopted. With the help of visual information, the Bezier curve based approaching as well as vision-based approaching adjustment is applied, where an optimal Bezier path is obtained based on the evaluation of its length and curvature with constraints from the velocity, tangential acceleration and the minimum turning radius. When the mobile manipulator thinks that the object is within its grasping range, it executes the grasping operation according to image information and inverse kinematics. During the move-to-grasp process, the posture of the manipulator is adjusted in real time to endeavor to make the object be targeted. The validity of the proposed method is verified by experiments.

Robot pose estimation and navigation based on the understanding of laser landmarks in unknown environments

A pose estimation approach for the navigation of mobile robot in unknown environments is proposed. Compared with the existing mainstream SLAM, the proposed approach has a better generality without the help of odometers or motion models and it is completely based on external environment perceived by a laser sensor. In each of the laser frames, landmark points are first determined and they are then coded into a series of description matrixes. On this basis, by considering the landmarks matching in two neighboring laser frames, the pose change of the robot may be calculated, and the understanding of laser-based landmarks by geometric coding is achieved. The proposed approach is proved to be effective by the experiments of a tracked robot.

A monitoring network based on embedded vision nodes suitable for robotic systems

A visual monitoring network suitable for robotic systems is presented in this paper. The monitoring network is composed of embedded vision nodes. By interacting with an upper computer as well as the robotic system, the monitoring network provides an important supplement, which may accelerate the task execution. Each embedded vision node captures and processes images independently, and it is easy to install with compact size. The vision node contains a S3C2440 processor as the main processing module, a CMOS camera as the image capturing module and a zigbee module for wireless communication. The detection based on frame difference or color feature is used to determine the mass center of moving object. On this basis, the object information from one vision node may also be sent to another one for stereo vision localization with stereo vision model and least square method. Application examples are demonstrated to testify the monitoring network.

Control of Fe-precipitates in Fe-doped InP

An attempt has been made, on the basis of the three-levels model and considerations relative to the existence of interstitial atoms, to correlate the resistivity of InP crystal with the Fe weight fraction and the background concentration of the polycrystalline InP used as the starting material for growing semi-insulating crystals with low Fe concentration. The calculated and experimental results are in good agreement. The correlation between Fe weight fraction and solidified InP that is free of Fe-precipitates was obtained experimentally.<<ETX>>