Visual recognition of pointing gestures for human–robot interaction

In this paper, we present an approach for recognizing pointing gestures in the context of human–robot interaction. In order to obtain input features for gesture recognition, we perform visual tracking of head, hands and head orientation. Given the images provided by a calibrated stereo camera, color and disparity information are integrated into a multi-hypothesis tracking framework in order to find the 3D-positions of the respective body parts. Based on the hands’ motion, an HMM-based classifier is trained to detect pointing gestures. We show experimentally that the gesture recognition performance can be improved significantly by using information about head orientation as an additional feature. Our system aims at applications in the field of human–robot interaction, where it is important to do run-on recognition in real-time, to allow for robot egomotion and not to rely on manual initialization.     

Monocular Vision for Mobile Robot Localization and Autonomous Navigation

This paper presents a new real-time localization system for a mobile robot. We show that autonomous navigation is possible in outdoor situation with the use of a single camera and natural landmarks. To do that, we use a three step approach. In a learning step, the robot is manually guided on a path and a video sequence is recorded with a front looking camera. Then a structure from motion algorithm is used to build a 3D map from this learning sequence. Finally in the navigation step, the robot uses this map to compute its localization in real-time and it follows the learning path or a slightly different path if desired. The vision algorithms used for map building and localization are first detailed. Then a large part of the paper is dedicated to the experimental evaluation of the accuracy and robustness of our algorithms based on experimental data collected during two years in various environments.     

Center-configuration selection technique for the reconfigurable modular robot

The reconfigurable modular robot has an enormous amount of configurations to adapt to various environments and tasks. It greatly increases the complexity of configuration research in that the possible configuration number of the reconfigurable modular robot grows exponentially with the increase of module number. Being the initial configuration or the basic configuration of the reconfigurable robot, the center-configuration plays a crucial role in system’s actual applications. In this paper, a novel center-configuration selection technique has been proposed for reconfigurable modular robots. Based on the similarities between configurations’ transformation and graph theory, configuration network has been applied in the modeling and analyzing of these configurations. Configuration adjacency matrix, reconfirmation cost matrix, and center-configuration coefficient have been defined for the configuration network correspondingly. Being similar to the center-location problem, the center configuration has been selected according to the largest center-configuration coefficient. As an example of the reconfigurable robotic system, AMOEBA-I, a three-module reconfigurable robot with nine configurations which was developed in Shenyang Institute of Automation (SIA), Chinese Academy of Sciences (CAS), has been introduced briefly. According to the numerical simulation result, the center-configuration coefficients for these nine configurations have been calculated and compared to validate this technique. Lastly, a center-configuration selection example is provided with consideration of the adjacent configurations. The center-configuration selection technique proposed in this paper is also available to other reconfigurable modular robots. Supported in part by the National High-Technology 863 Program (Grant No. 2001AA422360), the Chinese Academy of Sciences Advanced Manufacturing Technology R&D Base Fund (Grant Nos. A050104 and F050108), and the GUCAS-BHP Billiton Scholarship     

基于神经网络租遗传算法的足球机器人路径规划

针对足球机器人在动态环境下的安全路径规划,提出一种将神经网络和遗传算法相结合的路径规划方法。用hopfield神经网络描述存在障碍物的动态环境,然后用遗传算法对代表路径的控制点进行寻优,并把路径安全性和最短路径要求融合为一个适应度函数。通过仿真实验表明该方法具有较高的实时性和有效性。     

模块化机器人的惯性参数辨识研究

提出了一种基于六维力/力矩传感器的模块化机器人惯性参数辨识的方法。首先,通过Newton-Euler方程建立模块化机器人的动力学方程,然后利用基座力旋量平衡原理建立辨识模型对动力学方程中的未知参数进行辨识,最后以德国AMTEC公司生产的PowerCube模块化机器人实体对这种方法进行了实验验证。     

一种机器人的寻迹算法

针对基于光电传感器组寻迹的自动导引机器人,设计了传感器阵列的布置方式。根据此布置方式,提出了三个处理规则结合而成的轨迹识别算法。即使在导引线复杂的情况下,用此算法也能得出行进方向,控制机器人沿轨迹运动。甚至遇到干扰走错时,机器人也能自动纠错。     

基于多传感器数据融合的智能机器人设计

提出一种基于多传感器数据融合技术的智能机器人系统设计，介绍了系统所选用的激光、超声、红外、光敏等传感器的类型．阐述了系统的硬件结构与软件设计及D—S数据融合算法。     

VFF^＋：改进的虚拟力场移动机器人避障算法

分析了虚拟力场法采用全局栅格表示环境信息具有累积误差大、信息存储量大的缺点，设计了动态栅格法表示环境信息，使用跟随机器人移动的扇形栅格表示环境信息，使用栅格中心坐标投影的方法存储多次超声测量数据信息，与势场法相结合对机器人进行导航控制。经仿真和实验验证，改进后的虚拟力场法取得了良好的应用效果。     

基于立体视觉的机械手未知平面内曲线跟踪

为了提高机械手应用的灵活性,增强机械手对动态环境的适应能力,降低机械手对工件位置的依赖性,采用立体视觉技术对未知平面的法线方向进行估计,根据工程应用中对末端执行器的速度以及位姿的实际要求,采用PID控制策略控制机械手末端执行器与工件之间的相对位姿.进行了仿真实验以验证所提方法的有效性,结果表明:该方法能够实现末端执行器和工件之间相对位姿的动态控制.     

中央空调风管吸尘机器人的开发

中央空调风管吸尘机器人借鉴了中央空调风管清洗机器人和家用吸尘机器人的技术,融合了计算机技术、控制技术、电子技术等诸多学科技术。它拥有完整的移动、检测、吸收、监控以及大功率低噪音的污物收集等功能,能够实现水平管道的清洁,解决中央空调通风系统的卫生死角,提高工作效率和工作质量。