Neural network approach to acquiring free-gait motion of quadruped robots in obstacle avoidance

In obstacle avoidance by a legged mobile robot, it is not necessary to avoid all of the obstacles by turning only, because it can climb or stride over some of them, depending on the obstacle configuration and the state of the robot, unlike a wheel-type or a crawler-type robot. It is thought that mobility efficiency to a destination is improved by crawling over or striding over obstacles. Moreover, if robots have many legs, like 4-legged or 6-legged types, then the robot's movement range is affected by the order of the swing leg. In this article a neural network (NN) is used to determine the action of a quadruped robot in an obstacle-avoiding situation by using information about the destination, the obstacle configuration, and the robot's self-state. To acquire a free gait in static walking, the order of the swing leg is realized using an alternative NN whose inputs are the amount of movement and the robot's self-state. The design parameters of the former NN are adjusted by a genetic algorithm (GA) off-line. This work was presented in part at the 9th International Symposium on Artificial Life and Robotics, Oita, Japan, January 28–30, 2004     

Event-triggered path tracking control with obstacle avoidance for underactuated surface vessel compliant with COLREGs-constraints: Theory and experiments

This paper addresses the path tracking problem for an underactuated surface vessel with model parametric uncertainties, in the presence of unknown ocean currents under input saturation and limited transmission resources, while guaranteeing no collision can occur with a nearby target ship (TS) in compliance with the International Regulations for Preventing Collisions at Sea (COLREGs) rules. In view of COLREGs practice, this paper proposes a strategy to address the issue of collision avoidance in the presence of an encounter situation. Based on different stages of encounter situation, a local path re-planning-based repulsive potential function technique is proposed, such that the potential force generated by a decision-making algorithm, is directly acted on the original desired trajectory deviating thus the Own Ship (OS) to take direction in compliance with the COLREG constraints. By restoring to the path-tracking framework, this paper proposes a novel navigation control algorithm with ship-to-ship collision avoidance. At the navigation level, a finite-time prescribed performance control strategy with the deployment of novel asymmetrical envelopes is proposed to prescribe path-tracking errors within user-defined constraints while reducing transient response overshoots. Furthermore, in order to enhance the tracking performance under model uncertainties and external disturbances, a radial basis function neural network (RBFNN) technique is used. We first propose a second-order neural network disturbance observer to restrain the compound disturbances which are combined with external disturbances and neural network approximation errors. Next, based on the estimated compound disturbances, an adaptive NN controller is designed via an event-triggering mechanism along with a transverse function approach and the backstepping technique. It is shown that with the proposed technique, all signals in closed-loop systems are semi-globally uniformly bounded, while the output tracking errors converge to a prescribed arbitrarily small region within a finite time. In addition, we prove via the direct Lyapunov approach, the existence of minimal inter-event time and thus Zeno-behavior is avoided. Finally, experiments are conducted to validate the effectiveness and performances of the proposed control strategy.     

脉冲振荡器的包络仿真

本文阐述了包络仿真的基本原理及其应用。以脉冲振荡器的ＣＡＤ为例,为脉冲振荡器分别进行谐波平衡仿真和包络仿真,列出了仿真结果,并对脉冲振荡器输出信号进行数学分析。将仿真与分析的结果进行对照,从而阐明了包络仿真在有关复杂信号的微波电路优化设计和仿真中的作用。     

接近觉智能小车的设计开发

本文介绍了一种接近觉智能小车,该智能小车基于接近觉和STC89C52CR微处理器,采用模块化设计方案,结构简单,易于搭建平台和维修,测量精度高,可靠性好。该智能小车能够实现自动控制、被动控制、自动循迹、自动避障、测速、调速、速度显示、无线蓝牙通讯等功能,既能实现自动控制巡航,若用相关通信系统又可完成人工在线控制的功能。另外,对智能小车的超声波测距进行了温度补偿,有利于提高测距精度。接近觉智能小车的研制有助于研究以智能小车为模型的自动化驾驶技术,对智能车辆的研制与开发、现代化交通工具的智能化、多功能化发展提供了一个可行的参考方案。     

新型智慧城市软件基础设施

现代城市的信息化建设伴随着"随业务而定制、随需求而变化"的软件模式.城市向数字化升级过程中,定制化需求以更快的速度发展;同时,城市治理与市民服务对覆盖率、效率、质量的要求持续提升.我们需要一套有效的、系统性的软件基础设施来满足这种"更快速、更精准、更多样、随需而变"的城市数字化业务需求.文章首先从宏观层面简单回顾了过去...     

Robox at Expo.02: A large-scale installation of personal robots

In this paper we present Robox, a mobile robot designed for operation in a mass exhibition and the experience we made with its installation at the Swiss National Exhibition Expo.02. Robox is a fully autonomous mobile platform with unique multi-modal interaction capabilities, a novel approach to global localization using multiple Gaussian hypotheses, and a powerful obstacle avoidance. Eleven Robox ran for 12 hours daily from May 15 to October 20, 2002, traveling more than 3315 km and interacting with 686,000 visitors.     

矢量距离值传播移动机器人路径规划算法

一种新型简单机器人路径规划算法：其模型把实际环境离散成由目标、障碍、自由空间组成的点拓扑组织的地图。系统通过特殊的数学模型把路面的不平整性对机器人行走的影响程度量化为通行便利程度并引入到路径规划模型中。实验验证该模型具有计算效率高,存储空间开销小,对实际地图模拟比较完全等优点,适合实际应用。     

基于滚动速度障碍法的无人机山地航测避障路径规划研究

无人机在进行山地航测时,经常遭遇鸟类等动态障碍,若不能及时规避掉障碍,极容易发生坠机事故。为此,研究一种基于滚动速度障碍法的无人机山地航测避障路径规划方法。基于山地环境模型,结合飞行路径长度、路径平滑度建立一个综合目标函数并利用改进布谷鸟搜索算法求解,得到无人机山地航测的初始路径。对图像进行预处理后,识别无人机初始路径飞行过程中遇到的障碍物,并通过超声波测量无人机与障碍物之间的距离,以此建立速度障碍模型,实现速度障碍碰撞分析,通过滚动窗口的方式确定无人机与障碍物是否存在飞行冲突。基于滚动速度障碍避障方法实现滚动角度避障和速度避障,获取最终的优化路径,完成基于滚动速度障碍法的无人机山地航测避障路径规划。测试结果表明:航测避障路径长度为571.45m,平滑度为165.52,规划的方案更具合理性。     

避障小车转向系统的设计

设计了一种具有方向控制功能小车的转向系统.该小车在前行过程中能自动避开赛道上设置的等距障碍物.由于凸轮机构能实现复杂的运动规律,本设计采用凸轮机构完成小车的转向功能,通过MATLAB软件对凸轮轮廓曲线进行了拟合,并对导向杆运动规律进行了分析,结果表明本转向机构的设计是合理可行的.