Department Publications

Research on outdoor autonomous mobile robots has received much attention in the past decade. Outdoor autonomy meets with many challenges due to unpredictable dynamic environments, hard to control lighting and unavailability of resources. Nevertheless, such robots find a wide variety of potential applications in exploration, surveillance, agriculture, rescue missions and self-driven vehicles. This paper presents the authors’ approach to achieve long distance autonomous navigation with a mobile robot on outdoor cluttered pedestrian paths. The expected outcome was to finish “The Real World Robot Challenge”, an event held in the City of Tsukuba in Japan, by navigating a 1km course autonomously in a real environment with pedestrians and cyclists. Utilized hardware components and software architecture are illustrated. Furthermore, the strategies and other tactics to overcome context-based complexities are explained. The experimental results demonstrate the effectiveness of the system for outdoor autonomous navigation. Finally, the problems the authors faced in the real event are discussed.

Sonar sensors are widely used in obstacle detection in mobile robotic applications and certain limitations of these sensors usually become the reason for failures in these applications. Therefore, a thorough analysis of the actual behavior of sonar sensors is required. This research studied Devantech SRF05 sonar sensor, which is the most common sonar sensor in practice. We have discovered its practical beam pattern in 3-dimension (3D), optimum trigger frequency, and maximum angle of detection.

Simultaneous localization and map-building (SLAM) continues to draw considerable attention in the robotics community due to the advantages it can offer in building autonomous robots. It examines the ability of an autonomous robot starting in an unknown environment to incrementally build an environment map and simultaneously localize itself within this map. Recent advances in computer vision have contributed a whole class of solutions for the challenge of SLAM. This paper surveys contemporary progress in SLAM algorithms, especially those using computer vision as main sensing means, i.e., visual SLAM. We categorize and introduce these visual SLAM techniques with four main frameworks: Kalman filter (KF)-based, particle filter (PF)-based, expectation-maximization (EM)-based and set membership-based schemes. Important topics of SLAM involving different frameworks are also presented. This article …

Map building and obstacle detection are basic tasks in mobile robot navigation. In this paper we present a probability based solution for map building which utilizes time of flight information from an ultrasonic sensor. In contrast to most of the available map building systems, this uses a single ultrasonic sensor, mounted on a rotating shaft. Discrete sonar observations taken at regular time intervals, by rotating the shaft in small step angles are incrementally merged into partial planes to produce a realistic representation of environment that is amenable to sonar localization. Readings of close proximity are averaged to suppress the transient errors and the results are further refined by using the sonar probability model to fill an occupancy grid and Bayesian combination for the purpose of data fusion. Experimental results obtained in a real indoor environment are presented to verify the validity of our algorithm.

In this paper, a semiautonomous low-cost wheelchair robot to supplement impaired mobility of handicapped or elderly people is presented. The motion of the wheelchair is controlled by the joystick and the sonar sensor in such a manner that the sonar sensor has higher priority than joystick in normal conditions. The wheelchair uses two permanent magnet DC motors which are differentially driven using pulse width modulation (PWM) control signals. The motors drive the worm to drive the wheelchair. The semiautonomous wheelchair is equipped with four ultrasonic range finders in the front, one at the back to avoid the obstacles in its path and another one near the foot rest to detect steps. The system totally uses six ultrasonic sensors. The semiautonomous wheelchair was successfully tested under various conditions and satisfactory results were obtained.

Monocular vision based robot navigation requires feature tracking for localization. In this paper we present a tracking system using discriminative features as well as less discriminative features. Discriminative features such as SIFT are easily tracked and useful to obtain the initial estimates of the transforms such as affinities and homographies. On the other hand less discriminative features such as Harris corners and manually selected features are not easily tracked in a subsequent frame due to problems in matching. We use SIFT features to obtain the the estimates of the planar homographies representing the motion of the major planar structures in the scene. Planar structure assumption is valid for indoor and architectural scenes. The combination of discriminative and less discriminative feature are tracked using the prediction by these homographies. Then normalized cross correlation matching is used to find the …

An autonomous mobile robot is an intelligent agent which explores an unknown environment with minimal human intervention. Building a relative map which describes the spatial model of the environment is essential for exploration by such a robot. Recent advances for robot navigation motivate mapping algorithms to evolve into simultaneous localization and map-building (SLAM). Initial uncertainty is one of the key factors in SLAM. An update scheme of the feature initialization in monocular vision based SLAM will be briefly introduced, which is within a detailed implementation of feature detection and matching, and 3-D reconstruction by multiple view geometry (MVG) within extended Kalman filter (EKF) framework. Experiments clearly show that the proposed scheme can maximize the optimization capacity of EKF.

This paper describes a baby sitting robot system, which has the capabilities of baby tracking , cry signal processing, map building and obstacle avoidance, path planning, entertain the baby or alarm the guardian if any defined anomalies found and voice interaction. For that purpose, the baby sitting robot system has a capability to track and follow the baby with obstacle avoidance. It is also potential enough to identify when the baby cries, or reach near to any defined anomalies. Further more it provides a convenient voice interface for easy usage and various entertainment services for the baby. Rather than just notify the parents that the baby is approaching anomalies, it will try to prevent it from reaching the anomalies by either blocking or distracting with music. In this paper, the overall system is introduced and the detailed subsystems and functions are presented. Baby tracking, cry detection and step detection have …

The velocity dipole field method is presented for real-time collision avoidance of mobile robots. The direction of motion of the obstacle is used as the axis of the dipole field, and the speed of the obstacle is used to proportionally strengthen the dipole field. The elliptical field lines of the dipole field are useful to skillfully guide the robot around obstacles, quite similar to the way humans avoid moving obstacles. Field modulation coefficient is also introduced to weaken the field effect as the obstacle recedes. The real-time algorithm of the velocity dipole field has been devised and experimentally tested on the robot soccer test-bed. The results show the capability of the new real-time collision avoidance strategy and how it can overcome the weaknesses in the conventional potential field method. The new method makes an explicit and proactive action of collision avoidance, unlike the conventional method, which forces the robot merely away from the obstacle aimlessly. The proposed method delivers greater capability with no considerable computational overhead

The structure and camera pose obtained using multiple view geometry based techniques cannot readily be used for robot localization and mapping. This is due to the fact that the structure and pose obtained relate to the actual environment and motion only up to a transform. In this paper, a method to localize the robot using monocular vision is presented. The assumptions are that the initial pose of the robot is known and that five or more landmarks (true, world points) can be identified. If two or more dissimilar views of at least five non coplanar feature points are initially available, subsequent robot locations with respect to the landmarks in view can be established. The exploration of the environment can then take place incorporating new feature points as the robot moves and successive images are acquired. The feature points which are no longer present in the field of view have to be handled along with the occluded …

The simultaneous localization and map-building (SLAM) problem of robots with Extended Kalman Filter (EKF) framework were studied. Two types of sensing systems, ultrasound and computer vision, were mounted on the robot to perceive the environment so as to simultaneously localize the robot. The Kalman Filter (KF) is a linear, discrete-time, finite dimensional system with recursive structure that makes a digital computer well suited for its implementation. EKF provides a real-time solution to the navigation problem and to on-going estimation of the uncertainty acquired from vehicle motion and landmark observation.

LiDAR Subsystems easily absorbed by the eye, thus maximum power is limited to make them'eye-safe'.▪ 1550nm is not focused by the eye, thus usable at higher power levels for longer range (lower accuracy). It does not show under night-vision goggles→ well suited to military applications.

In order to increase the scientific return and reduce the operational costs of long-duration robotic missions to Mars, more autonomous systems are being considered that employ several rovers working on cooperative and coordinated tasks.

Map building and obstacle detection are basic tasks in mobile robot navigation. In this paper we present a probability based solution for map building which utilizes time of flight information from an ultrasonic sensor. In contrast to most of the available map building systems, this uses a single ultrasonic sensor, mounted on a rotating shaft. Discrete sonar observations taken at regular time intervals, by rotating the shaft in small step angles are incrementally merged into partial planes to produce a realistic representation of environment that is amenable to sonar localization. Readings of close proximity are averaged to suppress the transient errors and the results are further refined by using the sonar probability model to fill an occupancy grid and Bayesian combination for the purpose of data fusion. Experimental results obtained in a real indoor environment are presented to verify the validity of our algorithm.

one of the most challenging problems of field robots is self-localization, which involves incremental update of position while in motion. Though wheel based odometry is cheaper to implement its accuracy degrades when wheels slip. In this paper performance of low-cost visual odometry approach is experimented as a feasibility test for field robot localization. We have used a downward-facing camera and tested localization error in view of various parameters such as frame size, frame rate, etc. A FFT-based image registration techniques was utilized to determine the precise translation distances and heading between consecutive frames captured from ground surface. Basic navigation experiments, including a loop-closing test and error propagation were conducted and interesting numerical results have been reported