Learning to select distinctive landmarks for mobile robot navigation

In landmark-based navigation systems for mobile robots, sensory perceptions (e.g., laser or sonar scans) are used to identify the robot’s current location or to construct internal representations, maps, of the robot’s environment. Being based on an external frame of reference (which is not subject to incorrigible drift errors such as those occurring in odometry-based systems), landmark-based robot navigation systems are now widely used in mobile robot applications.The problem that has attracted most attention to date in landmark-based navigation research is the question of how to deal with perceptual aliasing, i.e., perceptual ambiguities. In contrast, what constitutes a good landmark, or how to select landmarks for mapping, is still an open research topic. The usual method of landmark selection is to map perceptions at regular intervals, which has the drawback of being inefficient and possibly missing ‘good’ landmarks that lie between sampling points.In this paper, we present an automatic landmark selection algorithm that allows a mobile robot to select conspicuous landmarks from a continuous stream of sensory perceptions, without any pre-installed knowledge or human intervention during the selection process. This algorithm can be used to make mapping mechanisms more efficient and reliable. Experimental results obtained with two different mobile robots in a range of environments are presented and analysed.     

An approach to robot SLAM based on incremental appearance learning with omnidirectional vision

Localisation and mapping with an omnidirectional camera becomes more difficult as the landmark appearances change dramatically in the omnidirectional image. With conventional techniques, it is difficult to match the features of the landmark with the template. We present a novel robot simultaneous localisation and mapping (SLAM) algorithm with an omnidirectional camera, which uses incremental landmark appearance learning to provide posterior probability distribution for estimating the robot pose under a particle filtering framework. The major contribution of our work is to represent the posterior estimation of the robot pose by incremental probabilistic principal component analysis, which can be naturally incorporated into the particle filtering algorithm for robot SLAM. Moreover, the innovative method of this article allows the adoption of the severe distorted landmark appearances viewed with omnidirectional camera for robot SLAM. The experimental results demonstrate that the localisation error is less than 1 cm in an indoor environment using five landmarks, and the location of the landmark appearances can be estimated within 5 pixels deviation from the ground truth in the omnidirectional image at a fairly fast speed.     

Robust omnidirectional mobile robot topological navigation system using omnidirectional vision

Robust topological navigation strategy for omnidirectional mobile robot using an omnidirectional camera is described. The navigation system is composed of on-line and off-line stages. During the off-line learning stage, the robot performs paths based on motion model about omnidirectional motion structure and records a set of ordered key images from omnidirectional camera. From this sequence a topological map is built based on the probabilistic technique and the loop closure detection algorithm, which can deal with the perceptual aliasing problem in mapping process. Each topological node provides a set of omnidirectional images characterized by geometrical affine and scale invariant keypoints combined with GPU implementation. Given a topological node as a target, the robot navigation mission is a concatenation of topological node subsets. In the on-line navigation stage, the robot hierarchical localizes itself to the most likely node through the robust probability distribution global localization algorithm, and estimates the relative robot pose in topological node with an effective solution to the classical five-point relative pose estimation algorithm. Then the robot is controlled by a vision based control law adapted to omnidirectional cameras to follow the visual path. Experiment results carried out with a real robot in an indoor environment show the performance of the proposed method.     

Gradual spatial pattern formation of homogeneous robot group

This paper proposes a gradual formation of a spatial pattern for a homogeneous robot group. The autonomous formation of spatial pattern is one of key technologies for the advancement of cooperative robotic systems because a pattern formation can be regarded as function differentiation of a multi-agent system. When multiple autonomous robots without a given local task cooperatively work for a global objective, the function differentiation is the first and indispensable step. For example, each member of cooperative insects or animals can autonomously recognize own local tasks through mutual communication with local members. There were a lot of papers that reported a spatial pattern formation of multiple robots, but the global information was supposed to be available in their approaches. It is however almost impractical assumption for a small robot to be equipped with an advanced sensing system for global localization due to robot’s scale and sensor size. The local information-based algorithm for the pattern formation is desired even if each robot is not equipped with a global localization sensor.We therefore propose a gradual pattern formation algorithm, i.e., a group of robots improves complexity of their pattern from to a simple pattern to a goal pattern like a polygon. In the algorithm, the Turing diffusion-driven instability theory is used so that it could differentiate roles of each robot in a group based only on local information. In experiment, we demonstrate that robots can make a few polygon patterns from a circle pattern by periodically differentiating robot’s roles into a vertex or a side. We show utilities of the proposed gradual pattern formation algorithm for multiple autonomous robots based on local information through some experiments.     

Development of an indoor navigation system for a monocular-vision-based autonomous mobile robot

We have developed a technology for a robot that uses an indoor navigation system based on visual methods to provide the required autonomy. For robots to run autonomously, it is extremely important that they are able to recognize the surrounding environment and their current location. Because it was not necessary to use plural external world sensors, we built a navigation system in our test environment that reduced the burden of information processing mainly by using sight information from a monocular camera. In addition, we used only natural landmarks such as walls, because we assumed that the environment was a human one. In this article we discuss and explain two modules: a self-position recognition system and an obstacle recognition system. In both systems, the recognition is based on image processing of the sight information provided by the robot’s camera. In addition, in order to provide autonomy for the robot, we use an encoder and information from a two-dimensional space map given beforehand. Here, we explain the navigation system that integrates these two modules. We applied this system to a robot in an indoor environment and evaluated its performance, and in a discussion of our experimental results we consider the resulting problems.     

Design and motion planning of an autonomous climbing robot with claws

This paper presents the design of a novel robot capable of climbing on vertical and rough surfaces, such as stucco walls. Termed CLIBO (claw inspired robot), the robot can remain in position for a long period of time. Such a capability offers important civilian and military advantages such as surveillance, observation, search and rescue and even for entertainment and games. The robot’s kinematics and motion, is a combination between mimicking a technique commonly used in rock climbing using four limbs to climb and a method used by cats to climb on trees with their claws. It uses four legs, each with four-degrees-of-freedom (4-DOF) and specially designed claws attached to each leg that enable it to maneuver itself up the wall and to move in any direction. At the tip of each leg is a gripping device made of 12 fishing hooks and aligned in such a way that each hook can move independently on the wall’s surface. This design has the advantage of not requiring a tail-like structure that would press against the surface to balance its weight. A locomotion algorithm was developed to provide the robot with an autonomous capability for climbing along the pre-designed route. The algorithm takes into account the kinematics of the robot and the contact forces applied on the foot pads. In addition, the design provides the robot with the ability to review its gripping strength in order to achieve and maintain a high degree of reliability in its attachment to the wall. An experimental robot was built to validate the model and its motion algorithm. Experiments demonstrate the high reliability of the special gripping device and the efficiency of the motion planning algorithm.     

Autonomous Mobile Robot Localization and Navigation Using a Hierarchical Map Representation Primarily Guided by Vision

While impressive progress has recently been made with autonomous vehicles, both indoors and on streets, autonomous localization and navigation in less constrained and more dynamic environments, such as outdoor pedestrian and bicycle‐friendly sites, remains a challenging problem. We describe a new approach that utilizes several visual perception modules—place recognition, landmark recognition, and road lane detection—supplemented by proximity cues from a planar laser range finder for obstacle avoidance. At the core of our system is a new hybrid topological/grid‐occupancy map that integrates the outputs from all perceptual modules, despite different latencies and time scales. Our approach allows for real‐time performance through a combination of fast but shallow processing modules that update the map's state while slower but more discriminating modules are still computing. We validated our system using a ground vehicle that autonomously traversed three outdoor routes several times, each 400 m or longer, on a university campus. The routes featured different road types, environmental hazards, moving pedestrians, and service vehicles. In total, the robot logged over 10 km of successful recorded experiments, driving within a median of 1.37 m laterally of the center of the road, and localizing within 0.97 m (median) longitudinally of its true location along the route.     

一种低功耗程控滤波器的设计

针对目前移动机器人同时定位与地图创建(SLAM)研究中多采用激光雷达或超声环作为测距传感器导致系统复杂、成本高的问题,提出了一种利用舵机带动单超声传感器扫描的低成本设计方案。在高斯超声模型基础上,利用贝叶斯公式对栅格地图进行概率更新,并结合Sobel边缘检测算法提取特征点,实现了由不确定的移动机器人坐标系向固定的以环境特征点为原点的全局环境坐标系的转换及全局定位,为在相同环境下通过重复实验进行多地图融合研究奠定了基础。该低成本移动机器人设计的有效性通过实验得以验证。     

Workspace mapping based on multisensor information fusion using heterogeneous onboard sensors

In recent years, multiple robot systems that perform team operations have been developed. These robot systems are expected to execute complicated tasks smoothly in a given congested workspace. In this article, we propose a workspace mapping algorithm using ultrasonic stereo sonar and an image sensor in order to operate the mobile robots among obstacles. This workspace mapping algorithm involves two steps: (1) the position detection of obstacles using ultrasonic stereo sonar, and (2) the shape detection of obstacles using an image sensor. While each robot moves around in the given workspace, the two steps of the mapping algorithm are repeated and sensor data are collected. The robot measures the distance and the direction of obstacles using ultrasonic stereo sonar. The shape of obstacles is also captured using an onboard image sensor. A workspace map is created based on the sensor data accumulated from the proposed method, and successful results are also obtained through experiments.     

Probabilistic models for robot-based object segmentation

This paper introduces a novel probabilistic method for robot based object segmentation. The method integrates knowledge of the robot’s motion to determine the shape and location of objects. This allows a robot with no prior knowledge of its workspace to isolate objects against their surroundings by moving them and observing their visual feedback. The main contribution of the paper is to improve upon current methods by allowing object segmentation in changing environments and moving backgrounds. The approach allows optimal values for the algorithm parameters to be estimated. Empirical studies against alternatives demonstrate clear improvements in both planar and three dimensional motion.     

People detection through quantified fuzzy temporal rules

The knowledge about the position and movement of people is of great importance in mobile robotics for implementing tasks such as navigation, mapping, localization, or human-robot interaction. This knowledge enhances the robustness, reliability and performance of the robot control architecture. In this paper, a pattern classifier system for the detection of people using laser range finders data is presented. The approach is based on the quantified fuzzy temporal rules (QFTRs) knowledge representation and reasoning paradigm, that is able to analyze the spatio-temporal patterns that are associated to people. The pattern classifier system is a knowledge base made up of QFTRs that were learned with an evolutionary algorithm based on the cooperative-competitive approach together with token competition. A deep experimental study with a Pioneer II robot involving a five-fold cross-validation and several runs of the genetic algorithm has been done, showing a classification rate over 80%. Moreover, the characteristics of the tests represent complex and realistic conditions (people moving in groups, the robot moving in part of the experiments, and the existence of static and moving people).     

Localization of a mobile robot based on an ultrasonic sensor using dynamic obstacles

In this article, we propose a localization scheme for a mobile robot based on the distance between the robot and moving objects. This method combines the distance data obtained from ultrasonic sensors in a mobile robot, and estimates the location of the mobile robot and the moving object. The movement of the object is detected by a combination of data and the object’s estimated position. Then, the mobile robot’s location is derived from the a priori known initial state. We use kinematic modeling that represents the movement of a robot and an object. A Kalman-filtering algorithm is used for addressing estimation error and measurement noise. Throughout the computer simulation experiments, the performance is verified. Finally, the results of experiments are presented and discussed. The proposed approach allows a mobile robot to seek its own position in a weakly structured environment. This work was presented in part at the 12th International Symposium on Artificial Life and Robotics, Oita, Japan, January 25–27, 2007     

Am I acceptable to you? Effect of a robot’s verbal language forms on people’s social distance from robots

This study is to examine the effect of robots’ language forms on people’s acceptance of robots. We applied a concept of social distance to measure people’s acceptance of robots. In an experiment, calling participants by name vs. not calling by name as well as the robot’s speech styles (familiar vs. honorific), were used to impose a verticality and horizontality of social relationships between participants and robots. After the conversation with a robot, participants rated the robot’s interpersonal traits and their comfortable approach distance to the robot, and their response to the robot during the experiment were analyzed. As a result, participants whom the robot called by their name perceived the robot as friendlier. They introduced themselves more actively, and were more intently focused on what the robot said. They asked the robot questions more frequently. Participants called by their names consequently approached the robot more closely than participants who were not called. An interaction effect was found between speech styles and whether names were used in regard to the perceived friendliness of robots, negative response to robots, and comfortable approach distance to robots. We discuss verbal interaction design for increasing people’s acceptance of robots.     

Cooperative passers-by tracking with a mobile robot and external cameras

In this paper, we present a cooperative passers-by tracking system between fixed view wall mounted cameras and a mobile robot. The proposed system fuses visual detections from wall mounted cameras and detections from a mobile robot–in a centralized manner–employing a “tracking-by-detection” approach within a Particle Filtering strategy. This tracking information is then used to endow the robot with passers-by avoidance ability to facilitate its navigation in crowds during the execution of a person following mission. The multi-person tracker’s ability to track passers-by near the robot distinctively is demonstrated through qualitative and quantitative off-line experiments. Finally, the designed perceptual modalities are deployed on our robotic platform, controlling its actuators via visual servoing techniques and free space diagrams in the vicinity of the robot, to illustrate the robot’s ability to follow a given target person in human crowded areas.     

Improving biped walk stability with complementary corrective demonstration

We contribute a method for improving the skill execution performance of a robot by complementing an existing algorithmic solution with corrective human demonstration. We apply the proposed method to the biped walking problem, which is a good example of a complex low level skill due to the complicated dynamics of the walk process in a high dimensional state and action space. We introduce an incremental learning approach to improve the Nao humanoid robot’s stability during walking. First, we identify, extract, and record a complete walk cycle from the motion of the robot as it executes a given walk algorithm as a black box. Second, we apply offline advice operators for improving the stability of the learned open-loop walk cycle. Finally, we present an algorithm to directly modify the recorded walk cycle using real time corrective human demonstration. The demonstrator delivers the corrective feedback using a commercially available wireless game controller without touching the robot. Through the proposed algorithm, the robot learns a closed-loop correction policy for the open-loop walk by mapping the corrective demonstrations to the sensory readings received while walking. Experiment results demonstrate a significant improvement in the walk stability.     

基于细胞自动机的移动机器人路径规划算法

针对移动机器人全局最优路径规划问题,提出一种基于细胞自动机的路径规划算法.该算法首先将移动机器人的起点、目标点和空间障碍物定义为一组离散的细胞状态,建立环境的细胞自动机模型;然后由机器人移动的曼哈顿距离设计演化规则;最后根据演化后的细胞状态搜索最优路径.对简单和复杂环境下的机器人路径规划问题进行了仿真实验,实验结果验证了该算法的有效性.     

基于显著场景BayesianSurprise的移动机器人自然路标检测

移动机器人在未知非结构化环境下的自然路标检测是层次化环境建模的基础。文中提出一种基于显著场景BayesianSurprise的自然路标检测方法。通过计算场景的视觉注意图,引导SURF特征采样聚集在显著区域内,提出融合空间关系的词袋模型构造场景表观的模式向量,建立基于该特征描述的地点MultivariatePolya模型,并通过度量传感器观测的Surprise来获取显著场景对应的路标。实验验证自然路标检测方法在大规模复杂室内环境中具有较低的漏检率和误检率,结合层次化SLAM方法验证路标检测器对生成拓扑节点的有效性。     

Dynamic Modeling of a Class of Continuum Manipulators in Fixed Orientation

A novel simultaneous localization and mapping (SLAM) technique based on independent particle filters for landmark mapping and localization for a mobile robot based on a high-frequency (HF)-band radio-frequency identification (RFID) system is proposed in this paper. SLAM is a technique for performing self-localization and map building simultaneously. FastSLAM is a standard landmark-based SLAM method. RFID is a robust identification system with ID tags and readers over wireless communication; further, it is rarely affected by obstacles in the robot area or by lighting conditions. Therefore, RFID is useful for self-localization and mapping for a mobile robot with a reasonable accuracy and sufficient robustness. In this study, multiple HF-band RFID readers are embedded in the bottom of an omnidirectional vehicle, and a large number of tags are installed on the floor. The HF-band RFID tags are used as the landmarks of the environment. We found that FastSLAM is not appropriate for this condition for two reasons. First, the tag detection of the HF-band RFID system does not follow the standard Gaussian distribution, which FastSLAM is supposed to have. Second, FastSLAM does not have a sufficient scalability, which causes its failure to handle a large number of landmarks. Therefore, we propose a novel SLAM method with two independent particle filters to solve these problems. The first particle filter is for self-localization based on Monte Carlo localization. The second particle filter is for landmark mapping. The particle filters are nonparametric so that it can handle the non-Gaussian distribution of the landmark detection. The separation of localization and landmark mapping reduces the computational cost significantly. The proposed method is evaluated in simulated and real environments. The experimental results show that the proposed method has more precise localization and mapping and a lower computational cost than FastSLAM.