Training a Vision Guided Mobile Robot

This paper presents the design, implementation and evaluation of a trainable vision guided mobile robot. The robot, CORGI, has a CCD camera as its only sensor which it is trained to use for a variety of tasks. The techniques used for training and the choice of natural light vision as the primary sensor makes the methodology immediately applicable to tasks such as trash collection or fruit picking. For example, the robot is readily trained to perform a ball finding task which involves avoiding obstacles and aligning with tennis balls. The robot is able to move at speeds up to 0.8 ms^-1 while performing this task, and has never had a collision in the trained environment. It can process video and update the actuators at 11 Hz using a single $20 microprocessor to perform all computation. Further results are shown to evaluate the system for generalization across unseen domains, fault tolerance and dynamic environments.     

Robust Hybrid Control of Constrained Robot Manipulators via Decomposed Equations

Basing on a constraint Jacobian induced orthogonal decomposition of the task space and by requiring the force controller to be orthogonal to the constraint manifold, the dynamics of the constrained robots under hybrid control is decomposed into a set of two equations. One describes the motion of robots moving on the constraint manifold, while the other relates the constraint force with the hybrid controller. This decomposition does not require the solution of the constraint equation in partition form. In this setting, the hybrid control of constrained robots can be essentially reduced to robust stabilization of uncertain nonlinear systems whose uncertainties do not satisfy the matching condition. A continuous version of the sliding-mode controller (from Khalil [12]) is employed to design a position controller. The force controller is designed as a proportional force error feedback of high gain type. The coordination of the position controller and the force controller is shown to achieve ultimately bounded position and force tracking with tunable accuracy. Moreover, an estimate of the domain of attraction is provided for the motion on the constraint manifold. Simulation for a planar two-link robot constraining on an ellipse is given to show the effectiveness of a hybrid controller. In addition, the friction effect, viewed as external disturbance to the system, is also examined through simulations.     

Rough Terrain Autonomous Mobility—Part 1: A Theoretical Analysis of Requirements

A basic requirement of autonomous vehicles is that of guaranteeing the safety of the vehicle by avoiding hazardous situations. This paper analyses this requirement in general terms of real-time response, throughput, and the resolution and accuracy of sensors and computations. Several nondimensional expressions emerge which characterize requirements in canonical form.The automatic generation of dense geometric models for autonomously navigating vehicles is a computationally expensive process. Using first principles, it is possible to quantify the relationship between the raw throughput required of the perception system and the maximum safely achievable speed of the vehicle. We derive several useful expressions for the complexity of terrain mapping perception under various assumptions. All of them can be reduced to polynomials in the response distance.The significant time consumed by geometric perception degrades real-time response characteristics. Using our results, several strategies of active geometric perception arise which are practical for autonomous vehicles and increasingly important at higher speeds.     

A Probabilistic Approach to Concurrent Mapping and Localization for Mobile Robots

This paper addresses the problem of building large-scale geometric maps of indoor environments with mobile robots. It poses the map building problem as a constrained, probabilistic maximum-likelihood estimation problem. It then devises a practical algorithm for generating the most likely map from data, along with the most likely path taken by the robot. Experimental results in cyclic environments of size up to 80 by 25 meter illustrate the appropriateness of the approach.     

Bayesian Landmark Learning for Mobile Robot Localization

To operate successfully in indoor environments, mobile robots must be able to localize themselves. Most current localization algorithms lack flexibility, autonomy, and often optimality, since they rely on a human to determine what aspects of the sensor data to use in localization (e.g., what landmarks to use). This paper describes a learning algorithm, called BaLL, that enables mobile robots to learn what features/landmarks are best suited for localization, and also to train artificial neural networks for extracting them from the sensor data. A rigorous Bayesian analysis of probabilistic localization is presented, which produces a rational argument for evaluating features, for selecting them optimally, and for training the networks that approximate the optimal solution. In a systematic experimental study, BaLL outperforms two other recent approaches to mobile robot localization.     

Human-like natural behavior generation based on involuntary motions for humanoid robots

Human behaviors consist of both voluntary and involuntary motions. Almost all behaviors of task-oriented robots, however, consist solely of voluntary motions. Involuntary motions are important for generating natural motions like those of humans. Thus, we propose a natural behavior generation method for humanoid robots that is a hybrid generation between voluntary and involuntary motions. The key idea of our method is to control robots with a hybrid controller that combines the functions of a communication behavior controller and body balancing controllers. We also develop a wheeled inverted pendulum type of humanoid robot, named “Robovie-III”, in order to generate involuntary motions like oscillation. By applying our method to this robot and conducting preliminary experiments, we verify its validity. Experimental results show that the robot generates both voluntary and involuntary motions.     

Drift-free attitude estimation for accelerated rigid bodies

In this paper we study the attitude estimation problem for an accelerated rigid body using gyros and accelerometers. The application in mind is that of a walking robot and particular attention is paid to the large and abrupt changes in accelerations that can be expected in such an environment. We propose a state estimation algorithm that fuses data from rate gyros and accelerometers to give long-term drift free attitude estimates. The algorithm does not use any local parameterization of the rigid body kinematics and can thus be used for a rigid body performing any kind of rotations. The algorithm is a combination of two non-standard, but in a sense linear, Kalman filters between which a trigger based switching takes place. The kinematics representation used makes it possible to construct a linear algorithm that can be shown to give convergent estimates for this nonlinear problem. The state estimator is evaluated in simulations demonstrating how the estimates are long-term stable even in the presence of gyro drift.     

乒乓球机器人的视觉伺服系统

视觉伺服的乒乓球机器人系统作为典型的"手眼系统",是研究高速视觉感知和快速伺服运动的理想平台,其涉及的高速物体识别跟踪、快速精确轨迹预测及机械臂伺服准确回球等关键技术在工业、军事等领域有广泛的应用前景.本文提出了乒乓球机器人的高速视觉伺服系统实现方法,包括基于特征直方图统计和快速轮廓搜索的目标识别算法,基于模型参数学习和自适应模型调整的物体运动状态估计和轨迹预测算法,及基于轨迹预测的灵巧臂回球规划算法.通过实验验证了各算法的实时性和高效性,并在165cm高的仿人机器人"悟"和"空"上成功实现了双机器人对打和与人对打任务.     

基于观测器的轮式移动机器人路径跟踪控制

研究基于状态观测器的轮式移动机器人的路径跟踪控制问题.首先简要回顾了基于状态反馈的移动机器人的路径跟踪控制问题;进而通过适当的状态变换将移动机器人模型转换为合适的形式,并在移动机器人的位置可以测量的情况下设计了一种可保证状态观测误差指数收敛的状态观测器;最后结合状态反馈路径跟踪控制器和所设计的观测器得到了一种基于观测器的路径跟踪控制器,该控制器可以保证移动机器人的运动轨迹指数收敛到期望路径上.仿真结果证实了所提出的基于观测器的路径跟踪控制器的有效性.     

仿生学在人工肌肉研究中的应用

本文从仿生学的角度出发，提出一种仿生物肌肉驱动性能的磁性橡胶人工肌肉，并对其结构和特点进行了分析。