Kinematics-Based Navigation Functions

In this paper, we introduce a new family of navigation laws which are based on analytic navigation functions derived using the kinematics equations. These navigation laws combine local and global aspects, and can be used for both indoor and outdoor navigation. The robot's kinematics model is represented in polar coordinates. The analytic navigation functions suggested here are functions of the line-of-sight angle between the robot and the goal, and depend on one or more navigation parameters. The navigation parameters allow us to control the navigation law and, thus, the path of the robot. The choice of the navigation function and its parameters is important, and must satisfy some conditions. Different paths are obtained for different navigation functions and different parameters. This property is used to avoid collision with obstacles. Under this formulation, the number of navigation functions allowing the robot to reach a given goal is infinite. An extensive simulation study shows the effectiveness of the method.     

Autonomous navigation and obstacle avoidance using navigation laws with time-varying deviation functions

In this paper we introduce a new family of navigation functions for robot navigation and obstacle avoidance. The method can be used for both path finding and real-time path planning. Each navigation function is composed of three parts: a proportionality term, a deviation function and a deviation constant. Deviation functions are time-varying functions satisfying certain conditions. These functions and parameters are updated in real-time to avoid collision with obstacles. Our strategy uses polar kinematics equations to model the navigation problem in terms of the range and direction between the robot and the goal. The obstacles are mapped to polar planes, and represented by the range and the direction from the robot or the final goal in polar coordinates. This representation gives a certain weight to the obstacles based on their relative position from the robot and facilitates the design of the navigation law. There exists an infinite number of navigation functions obtained by changing the proportionality constant, the deviation constant or the deviation function. This offers an infinite number of possibilities for the robot's path. Our navigation strategy is illustrated using an extensive simulation where different navigation parameters are used.     

An autonomous mobile robot for carrying food trays to the aged and disabled

Our research objective is to realize sensor-based navigation for car-like mobile robots. We adopt the generalized Voronoi graph (GVG) for the robot's local path and a map representation. It has the advantage to describe the mobile robot's path for sensor-based navigation from the point of view of completeness and safety. However, it is impossible to apply the path to car-like mobile robots directly, because the limitation of the minimum turning radius for a car-like robot may prevent it from following the GVG exactly. To solve this problem, we propose a local smooth path-planning algorithm for car-like mobile robots. Basically, an initial local path is generated by a conventional path-planning algorithm using GVG theory and it is modified smoothly by a Bezier curve to enable the car-like robots to follow it by maximizing our evaluation function. In this paper, we introduce a local smooth path-planning algorithm based on the GVG and explain the details of our evaluation function. Simulation and experimental results support the validity of the algorithm.     

Learning to transfer optimal navigation policies

Autonomous agents that act in the real world utilizing sensory input greatly rely on the ability to plan their actions and to transfer these skills across tasks. The majority of path-planning approaches for mobile robots, however, solve the current navigation problem from scratch, given the current and goal configuration of the robot. Consequently, these approaches yield highly efficient plans for the specific situation, but the computed policies typically do not transfer to other, similar tasks. In this paper, we propose to apply techniques from statistical relational learning to the path-planning problem. More precisely, we propose to learn relational decision trees as abstract navigation strategies from example paths. Relational abstraction has several interesting and important properties. First, it allows a mobile robot to imitate navigation behavior shown by users or by optimal policies. Second, it yields comprehensible models of behavior. Finally, a navigation policy learned in one environment naturally transfers to unknown environments. In several experiments with real robots and in simulated runs, we demonstrate that our approach yields efficient navigation plans. We show that our system is robust against observation noise and can outperform hand-crafted policies.     

Autonomous Navigation of an Unmanned Air Vehicle Towards a Moving Ship

This paper deals with the problem of autonomous navigation of an unmanned air vehicle towards a moving ship. The ship is moving in the horizontal plane; however, its motion is not a priori known to the air vehicle. The control laws for the flight path angle and the heading angle of the air vehicle are based on the relative kinematics equations between the vehicle and the moving ship. The goal of the control law is to drive the vertical line of sight angle to zero, while the horizontal line of sight angle tracks the heading angle of the ship. This results in a decreasing range in both the horizontal and vertical planes. The kinematics equations under the control law are derived and our results are rigorously proven. Simulation of various scenarios is carried out.     

Supervised fuzzy reinforcement learning for robot navigation

This paper addresses a new method for combination of supervised learning and reinforcement learning (RL). Applying supervised learning in robot navigation encounters serious challenges such as inconsistent and noisy data, difficulty for gathering training data, and high error in training data. RL capabilities such as training only by one evaluation scalar signal, and high degree of exploration have encouraged researchers to use RL in robot navigation problem. However, RL algorithms are time consuming as well as suffer from high failure rate in the training phase. Here, we propose Supervised Fuzzy Sarsa Learning (SFSL) as a novel idea for utilizing advantages of both supervised and reinforcement learning algorithms. A zero order Takagi–Sugeno fuzzy controller with some candidate actions for each rule is considered as the main module of robot's controller. The aim of training is to find the best action for each fuzzy rule. In the first step, a human supervisor drives an E-puck robot within the environment and the training data are gathered. In the second step as a hard tuning, the training data are used for initializing the value (worth) of each candidate action in the fuzzy rules. Afterwards, the fuzzy Sarsa learning module, as a critic-only based fuzzy reinforcement learner, fine tunes the parameters of conclusion parts of the fuzzy controller online. The proposed algorithm is used for driving E-puck robot in the environment with obstacles. The experiment results show that the proposed approach decreases the learning time and the number of failures; also it improves the quality of the robot's motion in the testing environments.     

Inverse reinforcement learning-based time-dependent A* planner for human-aware robot navigation with local vision

In an environment where robots coexist with humans, mobile robots should be human-aware and comply with humans' behavioural norms so as to not disturb humans' personal space and activities. In this work, we propose an inverse reinforcement learning-based time-dependent A* planner for human-aware robot navigation with local vision. In this method, the planning process of time-dependent A* is regarded as a Markov decision process and the cost function of the time-dependent A* is learned using the inverse reinforcement learning via capturing humans' demonstration trajectories. With this method, a robot can plan a path that complies with humans' behaviour patterns and the robot's kinematics. When constructing feature vectors of the cost function, considering the local vision characteristics, we propose a visual coverage feature for enabling robots to learn from how humans move in a limited visual field. The effectiveness of the proposed method has been validated by experiments in real-world scenarios: using this approach robots can effectively mimic human motion patterns when avoiding pedestrians; furthermore, in a limited visual field, robots can learn to choose a path that enables them to have the larger visual coverage which shows a better navigation performance.     

Autonomous robot navigation using optimal control of probabilistic regular languages

This paper addresses autonomous intelligent navigation of mobile robotic platforms based on the recently reported algorithms of language-measure-theoretic optimal control. Real-time sensor data and model-based information on the robot's motion dynamics are fused to construct a probabilistic finite state automaton model that dynamically computes a time-dependent discrete-event supervisory control policy. The paper also addresses detection and avoidance of livelocks that might occur during execution of the robot navigation algorithm. Performance and robustness of autonomous intelligent navigation under the proposed algorithm have been experimentally validated on Segway RMP robotic platforms in a laboratory environment.     

Line of sight robot navigation toward a moving goal.

In this paper, we consider the problem of robot tracking and navigation toward a moving goal. The goal's maneuvers are not a priori known to the robot. Thus, off-line strategies are not effective. To model the robot and the goal, we use geometric rules combined with kinematics equations expressed in a polar representation. The intent of the strategy is to keep the robot between a reference point, called the observer, and the goal. We prove under certain assumptions that the robot navigating using this strategy reaches the moving goal successfully. In the presence of obstacles, the method is combined with an obstacle avoidance algorithm. The robot then moves in two modes, the navigation mode and the obstacle avoidance mode. Simulation of various scenarios highlights the efficiency of the method and provides an instructive comparison between the paths obtained for different reference points.     

Adaptive hybrid control of manipulators on uncertain flexible objects

This paper presents an adaptive hybrid control approach for a robot manipulator to interact with its flexible object. Because of its flexibility, the object dynamics influence the robot's control system, and since it is usually a distributed parameter system, the object dynamics as seen from the robot change when the robot moves. The problem becomes further complicated such that it is difficult to decompose the robot's position and contact force control loops. In this paper, we approximate the object's distributed parameter model into a lumped 'position state-varying' model. Then, by using the well-known nonlinear feedback compensation, we decompose the robot's control space into a position control subspace and object torque control subspace. We design the optimal state feedback for the position control loop and control the robot's contact force through controlling the resultant torque of the object. We use the model-reference simple adaptive control strategy to control the torque control loop. We also study the problem on how to select a reasonable reference model for this control loop. Experiments of a PUMA robot interacting with an aluminum beam show the effectiveness of our approach.     

A geometric approach to solving the stable workspace of quadruped bionic robot with hand–foot-integrated function

This paper discusses stable workspace of a hand–foot-integrated quadruped walking robot, which is an important issue for stable operation of the robot. This robot was provided with combined structure of parallel and serial mechanisms, whose stable workspace was the subspace of the workspace in which the system was considered stable. The reachable region was formed under structural conditions, while the stable space was formed by the overall conditions of stability which changed with the robot's pose and the mass of grabbed object. In this paper, based on the robot's main structure, the key issues in solving the robot's workspace are discussed in detail, including searching steady conditions of operation of the robot. To research the robot's workspace, working leg's motion curve needed to be solved by kinematics analysis. Due to the redundant drive, it was problematic to deal analytically with the kinematics of the quadruped walking robot. A geometric method of kinematic analysis was proposed as well. Based on the geometric method, the workspace of the robot under varying postures was analyzed by the method of grid partition and in combination with Matlab, VB and Solidworks software programs. An automated computational system of the stable workspace was developed and an example was given to illustrate the whole process in detail. The theory and analysis procedures were also verified by simulation of the robot and its actual grabbing of an object.     

Modeling and simulation for fatigue life analysis of robots with flexible joints under percussive impact forces

This paper presents a method for modeling and analyzing the fatigue life of robots with flexible joints, with a particular focus on applications under percussive impact forces. This development is motivated by growing interests in robotic automation for operations with percussive impact tools. The most important characteristic of percussive operations is the repetitive impacts generated by the tool, such as a percussive rivet gun. After modeling of a flexible joint robot, a forced vibration solution is provided by including the impact forces generated by the percussive gun, projecting them onto the robot joint space and treating them in terms of the Fourier transform. As a result, the joint angular displacements can be solved using a standard vibration method. Then the joint stresses can be determined through Hooke's law. To consider the stress variations caused by the robot operating at different poses using different rivets, a multiple-loading fatigue model is applied from which an equation is derived to determine the total number of the rivets that can be riveted before robot's fatigue failure. Based on simulation using our model, the following observations are received. First, the joint torsional stresses vary with robot's position and orientation. Second, no joint will always experience the maximum stress and the joint stress dominancy also varies with robot's position and orientation. Third, at a given riveting point, the rivet gun direction considerately affects the joint stresses. Fourth, the fatigue life of each joint is different; therefore robot's fatigue life should be evaluated based on the shortest joint fatigue life.     

基于轨迹引导的移动机器人导航策略优化算法

针对在杂乱、障碍物密集的复杂环境下移动机器人使用深度强化学习进行自主导航所面临的探索困难,进而导致学习效率低下的问题,提出了一种基于轨迹引导的导航策略优化（TGNPO）算法。首先,使用模仿学习的方法为移动机器人训练一个能够同时提供专家示范行为与导航轨迹预测功能的专家策略,旨在全面指导深度强化学习训练;其次,将专家策略预测的导航轨迹与当前时刻移动机器人所感知的实时图像进行融合,并结合坐标注意力机制提取对移动机器人未来导航起引导作用的特征区域,提高导航模型的学习性能;最后,使用专家策略预测的导航轨迹对移动机器人的策略轨迹进行约束,降低导航过程中的无效探索和错误决策。通过在仿真和物理平台上部署所提算法,实验结果表明,相较于现有的先进方法,所提算法在导航的学习效率和轨迹平滑方面取得了显著的优势。这充分证明了该算法能够高效、安全地执行机器人导航任务。     

爆炸箔起爆器参数对电爆性能的影响

针对爆炸箔起爆系统的能量利用率问题,对爆炸箔起爆器中脉冲电源的电容量、起爆回路的等效电感和起爆回路电阻等参数进行了研究;采用尺寸为250 μm×250 μm×3 μm的A1薄膜材料,且爆炸箔使用方形桥区结构,并通过Simulink仿真软件对脉冲电源的电容量、起爆回路的等效电感和起爆回路电阻分别使用不同数值进行了计算;其中利用基尔霍夫回路方程和改进的Fireset模型,分析了爆炸箔电爆参数中对应的爆发电压、爆发电流和爆发时间等影响因子,经过实验得出电容量对电爆性能有较大影响,而电感和电阻对电爆炸性能影响有限;当电容量为100 nF、200 nF和300 nF时,最大功率为100 nF对应的37.3 kW;电感为200 nH、260 nH和320 nH时,最大功率为200 nH对应的15.2 kW;电阻为0.12 Ω、0.24 Ω和0.36 Ω时,最大功率为0.12 Ω对应的14.4 kW;电爆炸过程中电容量、电感和电阻相对应的功率幅值变动分别为59.5%、26.3%和20.8%,因此在实际应用中脉冲电源的电容量、回路等效电感和起爆回路电阻参数越小,则电爆炸过程中能量利用率越高,电爆性能越...     

Control of an articulated wheeled mobile robot in pipes

We propose a control method in which an articulated wheeled mobile robot moves inside straight, curved and branched pipes. This control method allows the articulated wheeled mobile robot to inspect a larger area. The articulated wheeled mobile robot comprises pitch and yaw joints is and propelled by active wheels attached to the robot. Via the proposed control method, the robot takes on two different shapes; one prevents the robot from slipping inside straight pipes and the other allows movement in a pipe that curves in any direction. The robot is controlled by a simplified model for the robot's joint angles. The joint angles of the robot are obtained by fitting to a continuous curve along the pipe path. In addition, the angular velocity of the robot's active wheels is determined by a simplified model. The effectiveness of the proposed the control method was demonstrated with a physical implementation of the robot, and the robot was able to move inside straight, curved and branched pipes.     

A simple PID control for asymptotic visual regulation of robot manipulators

This paper addresses the asymptotic regulation problem of robot manipulators with a vision‐based feedback. A simple image‐based transpose Jacobian proportional‐integral‐derivative (PID) control is proposed. The closed‐loop system formed by the proposed PID control and robot system is shown to be asymptotically stable by using Lyapunov's direct method and LaSalle's invariance theorem. Advantages of the proposed control include the absence of dynamical model parameters in the control law formulation and the control gains are easily chosen according to simple inequalities including some well‐known bounds extracted from robot dynamics and kinematics. Simulations performed on a two degree‐of‐freedom manipulator are provided to illustrate the effectiveness of the proposed approach. Copyright © 2010 John Wiley & Sons, Ltd.     

基于D-H法的农业采摘机器人运动协作控制系统设计

为提升农业采摘机器人运动协作控制性能,降低机器人碰撞概率,利用D-H法优化设计机器人运动协作控制系统。改装位置、力矩以及碰撞传感器设备,优化运动协作控制器与驱动器,调整系统通信模块结构,完成硬件系统的优化。利用D-H法构建农业采摘机器人数学模型,在该模型下,利用传感器设备实现机器人实时位姿的量化描述,通过机器人采摘流程的模拟,分配机器人运动协作任务,从位置和姿态等多个方面,确定运动协作控制目标,经过受力分析求解机器人实际作用力,最终通过控制量的计算,实现农业采摘机器人的运动协作控制功能。通过系统测试实验得出结论：与传统控制系统相比,机器人位置、姿态角和作用力的控制误差分别降低了约40mm、0.2°和1.2N,在优化设计系统控制下,机器人的碰撞次数得到明显降低。     

A fast robot homing approach using sparse image waypoints

This paper proposes a fast image sequence-based navigation approach for a flat route represented in sparse waypoints. Instead of purely optimizing the length of the path, this paper aims to speed up the navigation by lengthening the distance between consecutive waypoints. When local visual homing in a variable velocity is applied for robot navigation between two waypoints, the robot's speed changes according to the distance between waypoints. Because long distance implies large scale difference between the robot's view and the waypoint image, log-polar transform is introduced to find a correspondence between images and infer a less accurate motion vector. In order to maintain the navigation accuracy, our prior work on local visual homing with SIFT feature matching is adopted when the robot is relatively close to the waypoint. Experiments support the proposed navigation approach in a multiple-waypoint route. Compared to other prior work on visual homing with SIFT feature matching, the proposed navigation approach requires fewer waypoints and the navigation speed is improved without compromising the accuracy in navigation.     

Simulation of football based on PID controller and BP neural network

Wheel robot soccer speed control system using a ball object detection method and PID controller. A control system is based on the object detection system's behavior based on the robot position's orientation to the target position. PIDs are instruments, pressure, speed, and other operational factors used in control, temperature adjustment flow, and industrial control applications. The PID controller uses control loop feedback dynamics to control functional variables and is the most accurate and stable controller. The robot position is held by placing the ball vertically. When the robot's work is perpendicular to the ball, the robot moves with a certain speed controlled by the PIT controller based on the robot's distance and the ball. Standard conditions (standard ball) test results show that the robot can detect the ball material while in the vertical position, whether on the robot's right or left. In the random test that changes direction, the robot can move more dynamically as the ball's change in place.