A metric approach for simultaneous localization and map building

This thesis presents a recent research on the problem of environmental modeling for both localization and map building for wheel-based, differential driven, fully autonomous and self-contained mobile robots. The robots behave in an indoor office environment. They have a multi-sensor setup where the encoders are used for odometry and two exteroperceptive sensors, a 360° laser scanner and a monocular vision system, are employed to perceive the surrounding. The whole approach is feature based meaning that instead of directly using the raw data from the sensor features are firstly extracted. This allows the filtering of noise from the sensors and permits taking account of the dynamics in the environment. Furthermore, a properly chosen feature extraction has the characteristic of better isolating informative patterns. When describing these features care has to be taken that the uncertainty from the measurements is taken into account. The representation of the environment is crucial for mobile robot navigation. The model defines which perception capabilities are required and also which navigation technique is allowed to be used. The presented environmental model is both metric and topological. By coherently combining the two paradigms the advantages of both methods are added in order to face the drawbacks of a single approach. The capabilities of the hybrid approach are exploited to model an indoor office environment where metric information is used locally in structures (rooms, offices), which are naturally defined by the environment itself while the topology of the whole environment is resumed separately thus avoiding the need of global metric consistency. The hybrid model permits the use of two different and complementary approaches for localization, map building and planning. This combination permits the grouping of all the characteristics which enables the following goals to be met: Precision, robustness and practicability. Metric approaches are, per definition, precise. The use of an Extended Kalman Filter (EKF) permits to have a precision which is just bounded by the quality of the sensor data. Topological approaches can easily handle large environments because they do not heavily rely on dead reckoning. Global consistency can, therefore, be maintained for large environments. Consistent mapping, which handle large environments, is achieved by choosing a topological localization approach, based on a Partially Observable Markov Decision Process (POMDP), which is extended to simultaneous localization and map building. The theory can be mathematically proven by making some assumptions. However, as stated during the whole work, at the end the robot itself has to show how good the theory is when used in the real world. For this extensive experimentation for a total of more than 9 km is performed with fully autonomous self-contained robots. These experiments are then carefully analyzed. With the metric approach precision with error bounds of about 1 cm and less than 1 degree is further confirmed by ground truth measurements with a mean error of less than 1 cm. The topological approach is successfully tested by simultaneous localization and map building where the automatically created maps turned out to work better than the a priori maps. Relocation and closing the loop are also successfully tested.

This paper represents a SLAM(simultaneous localization and map building) system with odometry and indoor GPS sensor. This paper presents an accurate localization method by relative and absolute sensor fusion for map building system of mobile robot, we developed a sensor based absolution position tracking algorithm and grid based map building algorithm using this algorithm. A wall following decision engine like a fuzzy algorithm was proposed for map building navigation. Generally, while the robot is navigating the environment for map building position is estimated by odometry. However the position estimation using encoder data is not accurate owing to slipping and odometry linearization error. To solve this problem we proposed a sensor fusion method using encoder and indoor GPS. We proved this system' s validity through field test.

This paper develops a simultaneous localisation and map building (SLAM) algorithm which utilises the split covariance intersection (SCI) update rule. This algorithm decomposes estimates into a correlated component (whose precise structure is unknown) and a lower bound on an independent component. For a map of n beacons, the storage is O(n) and the computational costs are constant irrespective of map size. In a simple simulation example we show that the SCI algorithm, through exploiting a lower bound on independent information, performs substantially better than the traditional covariance intersection SLAM algorithm.

This paper describes recent progress toward the development and deployment of large-scale simultaneous localisation and map building (SLAM) systems. Two main theoretical results are presented. The first describes a closed form solution to the SLAM problem. This solution explains the many experimental and theoretical results obtained so far in the study of the SLAM problem and allows a precise means of analysing the performance of large scale, efficient, SLAM algorithms. The second result describes how best to choose landmarks to best maintain the performance of a large scale SLAM systems, and consequently which sets of landmarks may be deleted from a SLAM algorithm without compromising overall performance. This is the key to large-scale SLAM problems as it provides an efficient and systematic means of reducing the computational complexity of the problem with minimal loss of optimality. We conclude by describing an experimental program aimed at verifying and testing these SLAM algorithms in particular applications.

Simultaneous Localization and Mapping SLAM is one of the most important capabilities for autonomous mobile robots, and many researches have been proposed demonstrating the effective SLAM methods. However, these SLAM methods sometimes require assumptions such as the sensor model, which is difficult to implement and use the SLAM methods. In our previous work, a SLAM method based on Evolution Strategy ES was proposed and the on-line SLAM in indoor environments was realized. However, the definition of the map building method was not clear. Therefore, we propose a SLAM method based on a simple map building and search method. In this paper, we explain our autonomous mobile robot system and propose our SLAM method based on µ+1-ES. The experimental results show the effectiveness of the proposed method.

In this paper, we propose a vision-based simultaneous localization and map-building (SLAM) algorithm using compressed extended Kalman filter (CEKF). SLAM addresses the problem of locating a mobile robot in unknown environments. Extended Kalman filters (EKF) are widely used to solve this problem. However, this filter is very time consuming. To reduce the computational complexity, we apply a CEKF to stereo images while compensating for some of the limitation shown in previous implementations of CEKF. Moreover, we estimate the full DOF, its position and pose, of the mobile robots which is required when operating in the outdoor environment. Outdoor experiments have been conducted to test the effectiveness of the proposed SLAM algorithm.

Addresses the problem of implementing simultaneous localisation and map building (SLAM) in very large outdoor environments. A method is presented to reduce the computational requirement from /spl sim/O(N/sup 2/) to /spl sim/O(N), N being the states used to represent all the landmarks and vehicle pose. With this implementation the memory requirements are also reduced to /spl sim/O(N). This algorithm presents an efficient solution to the full update required by the compressed extended Kalman filter algorithm. Experimental results are also presented.

Feature point extraction and matching are the key modules in the front-end of visual simultaneous localization and mapping (SLAM), which determines the accuracy of locating and map Nbuilding robots. To obtain a good performance, the image extraction algorithm being applied should have high efficiency and robustness to the changes of the surrounding environment. In this paper, three widely used feature extraction algorithms, namely Scale-invariant feature transform (SIFT), speed up robust features (SURF) and oriented FAST, and rotated BRIEF (ORB), are studied. The basic concepts and details of the three algorithms are introduced. Then the execution time of the three algorithms is compared to evaluate their efficiency. Meanwhile, the key points matching rate of the three algorithms are compared under various transformations and distortions. The experiment results show that ORB has higher efficiency than SIFT and SURF. However, SIFT has better robustness to image rotation, illumination change, scaling transformation, Gaussian noise and salt-and-pepper noise. In addition, the performance of the ORB-SLAM system is tested on different datasets. It has great ability in camera trajectory estimation and map building and therefore is suitable for deploying in industry.

This paper focuses on developing a robust solution for the Simultaneous Localization and Mapping (SLAM) problem to increase the autonomy of Unmanned Aerial Vehicles (UAV). The investigated topics are related to data fusion, localization, features extraction and matching, map building, 3D pose estimation and SLAM. One important aspect of the autonomous navigation which should be investigated as well as the fusion of data from the different sensor. The data fusion algorithms are very important and their performances are closely dependent on both performances of the constructed map and the accuracy of the UAV position within this map. Optimal and robust filter using centred Gaussian noises is implemented. The original contribution of this work is the proposition and the adaptation of the Extended Kalman Filter (EKF) to solve the Inertial Navigation Systems INS/3D laser UAV navigation problem. Simulation results for 3D flight scenario are presented to demonstrate the advantages of the hybrid localization based on EKF compared with results of the INS relative localization based technique. Good results were obtained with the EKF using noise process and/or measurement noise characteristics, particularly in the case of centred Gaussian noises.

For autonomous navigation in workspace, a mobile robot has to be able to know its position in this space in a precise way that means that the robot must be able to self-localize to move and perform successfully the different entrusted tasks. At present, one of the most used systems in open spaces is the GPS navigation system; however, in indoor spaces (factories, buildings, hospitals, warehouses...) GPS signals are not operative because their intensity is too weak. The absence of GPS navigation systems in these environments has stimulated the development of new local positioning systems with their particular problems. Such systems have required in many cases the installation of beacons that operate like satellites (similar to GPS), the use of landmarks or even the use of other auxiliary systems to determine the robot’s position. The problem of mobile robot localization is a part of a more global problem because in autonomous navigation when a robot is exploring an unknown environment, it usually needs to obtain some important information: a map of the environment and the robot’s location in the map. Since mapping and localization are related to each other, these two problems are usually considered as a single problem called simultaneous localization and mapping (SLAM). The problem of Simultaneous Localization and Map Building is a significant open problem in mobile robotics which is difficult because of the following paradox: to localize itself the robot needs the map of the environment, and, for building a map the robot location must be known precisely. Mobile robots use different kinds of sensors to determine their position: for instance it is very common the use of odometric or inertial sensors, however it is remarkable to consider that in wheel slippage, sensor drifts a noise causing error accumulation, thus leading to erroneous estimates. Another kind of external sensors used in robotics in order to solve localization are for instance CCD cameras, infrared sensor, ultra sonic sensor, mechanical wave and laser. Other sensors recently applied are the instruments sensible to the magnetic field known as the electronic compass (Navarro & Benet, 2009). Mobile robotics are interested on those able to measure the Earths magnetic field and express it through an electrical signal. One type of electronic compass is based on magneto-resistive transducers, whose electrical resistance varies with the changes on the applied magnetic field. This type of sensors presents sensitivities below 0.1 milligauss, with response times below 1 sec, allowing its reliable use in vehicles moving at high speeds (Caruso, 2000). In SLAM some applications with electronic compass have been developed working simultaneously with other sensors such as artificial vision (Kim et al., 2006) and ultrasonic sensors (Kim et al., 2007).

This paper tackles the problem of Simultaneous Localization and Map Building (SLAM) carried out by a team of robots. Particularly these robots build landmark-based maps by extracting interest points from the environment. These points are characterized by a local descriptor and a 3D position on the environment, constituting the visual landmarks. In this approach we consider the situation in which the robots start their mapping task independently. That is to say, the path followed by the robots and the observations are estimated independently. After a while, there is a set of independent local maps that can be fused in order to obtain a global map. For that reason, we have also solved the problem of aligning and fusing visual maps. Finally, once a global map is obtained, the robots continue the map building task jointly. Regarding the sensors used in order to extract information from the environment, some authors use range sensors such as SONAR (Wijk & Christensen, 2000; Kwak et al., 2008) or LASER (Leonard & Durrant-Whyte, 1991; Thrun, 2001). However, in the last years, there is a great interest on using cameras as sensors. This approach is denoted as visual SLAM (Valls-Miro et al., 2006). The cameras are less expensive than laser and offer a higher amount of information from the environment. This advantage makes it possible to incorporate additional applications to the robot, such as face recognititon. Additionally, 3D information can be obtained from the environment when using stereo vision (Murray & Little, 2000; Gil, Reinoso, Fernandez, Vicente, Rottmann M Little et al., 2002) and SURF (Murillo et al., 2007). In (Gil et al., 2009; Ballesta, Gil, Reinoso & Ubeda, 2010) we performed an evaluation comparing several detection and description methods in order to obtain the most suitable feature extractor for visual SLAM. As a result, we obtained that the Harris Corner Detector in combination with the u-SURF descriptor satisfied our requirements in visual SLAM. The task of building a map of the environment while simultaneously localizing in it can be performed by a single robot. However, it will be carried out with more efficiency if there is a team of robots which collaborates in this task. This approach is denoted as multi-robot SLAM (Konolige et al., 2003). In this field, two main solutions can be found. On the one hand, in some proposals the robots build a unique global map (Gil, Reinoso, Martinez-Mozos, Stachniss & Burgard, 2006; Fenwick et al., 2002). In this case, the exploration task can be performed more efficiently since the robots have a global notion 6

The imprecision of sensor measurements due to systematic and nonsystematic errors can give rise to severe problems in several autonomous navigation tasks. In particular, the errors due to sensor bias can render existing Simultaneous Localization and Map Building (SLAM algorithms useless as such biases cause the estimators to diverge. This paper describes a method to estimate and compensate these ever present and particularly cumbersome sensor and input biases in real time in the context of SLAM applications without an a priori map of the environment. The validity of the proposed methodology is verified via simulations for the case of an autonomous land vehicle navigating in a completely unknown 20 terrain. It is assumed that biased and noisy range and bearing measurements to point landmarks are obtainable in real-time, using a sensor such as a laser scanner.

Simultaneous localization and Mapping is a key technology in the field of unmanned vehicle technology. Aiming at the present stage laser SLAM technology of gravity vector drift and elevation estimation error problem, based on the carrying of inertial measurement unit (IMU) and laser radar as experiment platform, Apollo suite with NDT method as the theoretical basis, in the Cyber RT operating system environment realize the car to the scene at the same time localization and map building. Firstly, the time stamp registration of laser and IMU is realized by calibrating the lidar. Secondly, IMU pre-integration is introduced to eliminate the motion distortion of point cloud. Then, reliable plane and edge features are obtained by feature extraction, and the depth information of environmental features is obtained. Finally, the current pose is estimated by NDT algorithm. The experimental results show that the map constructed by the combined SLAM method based on NDT algorithm has high precision and strong stability.

When Simultaneous Localization and Map Building is carried out in complex environments, reduction of computational complexity is a key problem. With a view to the high computational complexity of particle filter, a SLAM solution named ‘Fast Kalman SLAM’ is introduced. Adopting the ‘decomposition’ idea in the FastSLAM algorithm, Fast Kalman SLAM factors the joint SLAM state into a path component and a conditional map component. The robot pose is estimated recursively with Mean Extended Kalman Filter (MEKF) or Unscented Kalman Filter (UKF), while the map with Extended Kalman Filter (EKF). Simulative experiments are carried out to evaluate the performance of the presented algorithm. And Simulation analysis is made for the presented algorithm. The experimental results indicate that the new algorithm reduces computational complexity greatly and ensures estimation accuracy at the same time.

During the past decade, an explosion of interest in the estimation of an autonomous robot's location state and that of its surroundings, known as simultaneous localization and map building (SLAM), is evident. The goal of an autonomous vehicle performing SLAM is to build a map incrementally by using the uncertain information extracted from its sensors, while simultaneously using that map to localize itself with respect to a reference coordinate frame. To demonstrate the state of the art in autonomous navigation, this article focuses on outdoor research work within complex, semi-structured environments with an array of vehicles, using RADAR and laser range finders. Two classes of sensors that we use to get information are proprioceptive sensors and exteroceptive sensors. This paper focuses on sensor data interpretation, information extraction, and data association.