This paper proposes an energy-efficient collision avoidance system for an autonomous mobile manipulator (AMM) in dynamic environments. The system enables safe obstacle avoidance and energy-efficient path generation. A B-Spline-based path optimization algorithm is developed, incorporating an energy cost function for planning collision-free, energy-efficient paths. The Bi-RRT algorithm generates an initial path, segmenting it at curvature maxima for energy-efficient optimization. The local path planning creates a path with seven control points, applying the same optimization for safe, low-energy avoidance of dynamic obstacles. A Model Predictive Control (MPC) system ensures precise path following. Experiments with a TM5M-900 robot validate the method's effectiveness in avoiding obstacles. Compared to Bi-RRT and Hybrid-RRT systems, it improves motion smoothness by 29.35% and reduces energy consumption by 16.84%, providing a more efficient solution for an AMM in dynamic environments.

Robotic autonomous grasp requires the system to perform multiple functions such as gripper and robot control, making it a task with hybrid output nature. Existing methods based on closed-loop deep reinforcement learning rely on external models for termination evaluation. To achieve more effective grasp for novel objects, we propose a new autonomous grasp control scheme termed HAGrasp that considers the complete point cloud of the workspace. It integrates grasp pose estimation, end-effector pose evaluation, and motion planning of the robotic arm into a single model, enhancing the success rate while reducing computational load. We present a closed-loop grasp control system based on deep reinforcement learning. This control system can perform grasp tasks while dynamically adjusting to avoid end-effector collisions. The design of hybrid-action reinforcement learning module is trained with unified latent action space and further improve generalization, achieving real-time autonomous grasp control. Real robot experiments show that our method has 74.2% success rate for grasping 7 unseen objects. Comparative experiments show that the proposed HAGrasp outperforms open-loop baseline Contact-Graspnet in both success rate and inference time. It is demonstrated that with integrated multi-view input and sim-to-real training design, our method improves real-world applications of autonomous grasp.

This paper proposes a real-time obstacle avoidance control scheme for a 6-DOF manipulator with a tool in the end effector. The system consists of environment monitoring, robot-tool segmentation and collision-free motion planning of the manipulator. A Kinect V2 RGB-D camera is used to track obstacles including human and objects in the working environment. The K-D tree algorithm is then adopted to cluster point clouds of the tool and the obstacles. For robot-tool segmentation, we propose a method to model the tool in the end effector and predict its pose in order to solve the camera occlusion problem. For collision-free motion planning, a novel potential field algorithm is proposed to take into consideration of the pose of the tool. A virtual torque approach is proposed and added to the potential field in order to generate a smoother and shorter avoidance motion. The experimental results on a TM5-700 cobot show that the manipulator with a tool in the end effector effectively avoided an obstacle in real time and completed the assigned task. It is shown that the path length with the proposed virtual torque is shortened by 80.43% compared with the case without using the virtual torque.

This paper presents a real-time motion planning and control design of a robotic arm for human-robot collaborative safety. A novel collision-free motion planning method is proposed not only to keep robot body from colliding with objects but also preserve the execution of robot's original task under the Cartesian constraint of the environment. Multiple KinectV2 depth cameras are utilized to model and track dynamic obstacles (e.g. Humans and objects) inside the robot workspace. Depth images are applied to generate point cloud of segmented objects in the environment. A K-nearest neighbor (KNN) searching algorithm is used to cluster and find the closest point from the obstacle to the robot. Then a Kalman filter is applied to estimate the obstacle position and velocity. For the collision avoidance in collaborative operation, attractive and repulsive potential is generated for robot end effector based on the task specification and obstacle observation. Practical experiments show that the 6-DOF robot arm can effectively avoid an obstacle in a constrained environment and complete the original task.

This paper presents a mobile robot navigation control system based on integration of laser SLAM localization and real-time obstacle avoidance control to provide personnel guidance for daily-life services. The LiDAR SLAM localization system is implemented in a ROS software architecture, in which Cartographer SLAM is adopted and the adaptive Monte Carlo localization is employed onboard the robot. An integrated guidance system is proposed in this paper to combine obstacle avoidance and SLAM so that the robot can move to the desired location without colliding with any unexpected obstacles. A safety-weight parameter is used to integrate goal seeking controller with the obstacle avoidance controller. The experimental results show that the robot can localize itself and navigate to the target location while avoiding obstacles on the path.

Human voice provides a convenient and natural way to control a service robot. However, in practice simple voice commands are not sufficient to give continuous and safe motion of a mobile service robot in a complex environment. This paper presents a shared-control approach for voice remote control of a mobile robot. A remote control scheme for an omnidirectional mobile robot is proposed to overcome the delay-time problem of voice commands and maintain the safe motion of the robot. In this work, we combine the robot autonomy and human intention by using shared-control techniques. The human and robot interactive gains are obtained by computing posterior of free-space using a Bayesian recursive algorithm. Experimental results are presented to demonstrate the effectiveness of the proposed method.

Speech recognition is common in electronic appliances and personal services, but its use for industrial and medical purposes is rare because of the presence of motion ambiguity. For minimally invasive surgical robotic assistants, this ambiguity arises because the robotic motion is not calibrated to the camera images. This paper presents a design for a speech recognition interface for an HIWIN robotic endoscope holder. A new intentional speech control is proposed to control movement over long distances. To decrease ambiguity, a method is proposed for voice-to-motion calibration that compares the degree of change in the endoscope image for a voice command. A speech recognition algorithm is implemented on Ubuntu OS, using CMU Sphinx. The control signal is sent to the robot controller using serial-port communication through a RS232 cable. The experimental results show that the proposed intentional speech control strategy has a navigation precision of up to 3.1° of angular displacement for the endoscope. The overall system processing time, including robotic motion, is 3.22 s for ~1.8-s speech duration. The reference image navigation range is from 2.5 mm for ~0.5-s speech duration up to 6 mm for ~1.8-s speech duration, using a setup with camera tip that is located at a distance of 5 cm from the remote center of motion point.

This paper presents a shared-control-based design for teleoperation of a dual-arm omnidirectional mobile robot-a robot that can execute tasks commanded by a remotely user, or that can operate autonomously by adapting to its immediate environment, or that can operate in both modes simultaneously. To achieve this capability for the robot and for its effective remote control, a shared-control method has been developed. The controller determines the control gains for both the human and the autonomous commands by computing the user's confidence factor. For ease of use, a smartphone/tablet is used to control the robot. Using this approach, the robot allows the user to manipulate its motion from a remote site and compensates for a lack of local human knowledge. Practical experiments validate the proposed design and demonstrate the potential of the proposed shared-control method for home-service tasks.

The paper presents a walking pattern generator and a balance control system for a bipedal robot to handle an unknown slope. The robot uses onboard gyro and accelerometer sensors to detect the pose information of the upper-body. A controller is proposed for the robot to walk on an unknown slope by adjusting the tilt angle of the upper-body. The theory of central pattern generator (CPG) is applied to generate the walking trajectory. By using the pose information of the upper-body, we developed a method to determine the relationship between the slope surface and the upper-body pose and generate the compensation motion to adjust the tilt angle of the upper-body. The compensation control consists of predictive compensation and immediate compensation. The predictive compensation responds to adjust the upper-body pose before beginning of the next step. The immediate compensation is applied to adjust the upper-body pose during the single support phase. The integrated controller adapts to the unknown slope in real time while robot walking. Using the bipedal robot NAO, the experimental results show that the biped robot can walk successfully on unknown slopes.

It is usually difficult to remote control of a mobile robot using only an onboard camera. The robot can easily bump into an obstacle due to limited view angle of the on-site scene. This paper presents a shared-control design for effective remote control of an omnidirectional mobile platform. The platform is able to move in any direction without changing robot's heading, and a stable camera view is available for remote control. A user interface is designed for a smart phone/tablet to remote control the robot using a touch panel. The proposed controller determines the human and robot interactive gains by computing user's confidence factor. In this approach, the robot assists a user to manipulate its motion from a remote site by compensating local insufficiency of human remote control. Practical experiments validate the proposed design and demonstrate that the proposed shared-control approach of an omnidirectional platform can have potential use for future home service tasks.

For an on-demand robotic system, a location aware module provides location information of objects, users, and the mobile robot itself. This information supports various intelligent behaviors of a service robot in day-to-day scenarios. This paper presents a novel probability-based approach to building a location aware system. With this approach, the inconsistencies often seen in received signal strength indicator (RSSI) measurements are handled with a minimum of calibration. By taking off-line calibration measurement of a ZigBee sensor network, the inherent problem of signal uncertainty of to-be-localized nodes can be effectively resolved. The proposed RSSI-based algorithm allows flexible deployment of sensor nodes in various environments. The proposed algorithm has been verified in several typical environments and experiments show that the method outperforms existing algorithms. The location aware system has been integrated with an autonomous mobile robot to demonstrate the proposed on-demand robotic intruder detection system. In the experiments, three alarm sensors were employed to monitor abnormal conditions. If an intrusion was detected, the robot immediately moves to the location and transmits scene images to the user, allowing the user to respond to the situation in real time.

In this paper, a novel human-robot interaction(HRI) design is proposed where emotional recognition from the speech signal is used to create an emotion-aware music player that can be implemented in an embedded platform. The proposed system maps an inputted short-speech utterance to a two dimensional emotional plane of valence and arousal. This strategy allows the system to automatically select a piece of music from a database of songs, of which emotions are also expressed using arousal and valence values. Furthermore, a cheer-up strategy is proposed such that music songs with varying emotional content are played in order to cheer up the user to a more neutral/happy state. The proposed system has been implemented in a Beagle board. The online test verified the feasibility of the system. A questionnaire survey shows that 80% of subjects agree with the songs selected by the proposed cheer-up strategy based on the emotional model.

This paper presents a method of mood transition design of a robot for autonomous emotional interaction with humans. A 2-D emotional model is proposed to combine robot emotion, mood, and personality in order to generate emotional expressions. In this design, the robot personality is programmed by adjusting the factors of the five factor model proposed by psychologists. From Big Five personality traits, the influence factors of robot mood transition are determined. Furthermore, a method to fuse basic robotic emotional behaviors is proposed in order to manifest robotic emotional states via continuous facial expressions. An artificial face on a screen is a way to provide a robot with a humanlike appearance, which might be useful for human-robot interaction. An artificial face simulator has been implemented to show the effectiveness of the proposed methods. Questionnaire surveys have been carried out to evaluate the effectiveness of the proposed method by observing robotic responses to a user's emotional expressions. Preliminary experimental results on a robotic head show that the proposed mood state transition scheme appropriately responds to a user's emotional changes in a continuous manner.

Facial expression recognition can provide rich emotional information for human-robot interaction. This paper presents a facial expression recognition design that recognizes facial expressions as well as intensity and mixture ratio of six basic facial expressions. In this system, Active Appearance Model (AAM) and Lucas-Kanade image alignment algorithms are adopted to align the input facial images to obtain texture features. A novel method is proposed to recognize mixture ratio of basic facial expressions and the intensity of the expression. Three kinds of texture features are used in this method: 1. texture features of the whole face, which are used as inputs of facial expression intensity recognition; 2. texture features of the upside face, which are used as inputs of upper face action units recognition; 3. texture features of the downside face, which are used as the inputs of lower face action units recognition. Back propagation neural networks are used to obtain the recognition scores, which are then exploited to classify the facial expression results. Experimental results verified that the proposed method can effectively recognize mixture ratio of six basic expressions and the expression intensity.

This paper presents a vision-based obstacle avoidance design using a monocular camera onboard a mobile robot. An image processing procedure is developed to estimate distances between the robot and obstacles based-on inverse perspective transformation (IPT) in image plane. A robust image processing solution is proposed to detect and segment navigatable ground plane area within the camera view. The proposed method integrate robust feature matching with adaptive color segmentation for plane estimation and tracking to cope with variations in illumination and camera view. After IPT and ground region segmentation, a result similar to the occupancy grid map is obtained for mobile robot obstacle avoidance and navigation. Practical experimental results of a wheeled mobile robot show that the proposed imaging system successfully estimates distance of objects and avoid obstacles in an indoor environment.

This paper presents a novel compliant motion controller design for an omni-directional mobile robot. In this design, an external force observer is developed based on measuring motor current and speed without using an expensive force/torque sensor. The mobile robot has a handrail to assist the elderly to walk safely and stably. In this application, adaptive motion compliance is required in accordance with the applied force of the user. Practical experimental results show that the compliance of the walking helper can be adjusted by setting dynamic coefficients of the overall dynamical system. It was demonstrated that the external force observer successfully detected the pushing as well as pulling force of a user on the handrail. The velocity of the omni-directional walking helper is adjusted according to the inferred motion intent.

This paper presents a novel design of autonomous robotic facial expression generation using a fuzzy-neuro network. The emotional characteristics of a robot can be specified in this design by assigning weights in the fuzzy-neuro network. The robotic face generates appropriate expressions in responding to the image recognition results of a user's emotional state and the assigned robotic emotional characteristics. In this study, two contrast emotional characteristics, optimistic and pessimistic, have been designed and tested to verify their responses to the recognized user emotional states (neutral, happiness, sadness and anger). Computer simulations of a robotic face show that the proposed facial expression generation system effectively responds to a user's emotional states in a human-like manner by fusing outputs of four facial expressions (boring, happiness, sadness and surprise).

This paper presents a novel design of visual state estimation for an image-based tracking control system to estimate system state during visual tracking control process. The advantage of this design is that it can estimate the target status and target image velocity without using the knowledge of target’s 3D motion-model information. This advantage is helpful for real-time visual tracking controller design. In order to increase the robustness against random observation noise, a neural network based self-tuning algorithm is proposed using echo state network (ESN) technique. The visual state estimator is designed by combining a Kalman filter with the ESN-based self-tuning algorithm. The performance of this estimator design has been evaluated using computer simulation. Several interesting experiments on a mobile robot validate the proposed algorithms.

Because of its 360° field of view, an omni-directional camera is suitable for detecting and tracking environmental features in mobile robot navigation applications. This study aims to investigate simultaneous localization and mapping (SLAM) of a mobile robot using omni-directional images. A switching method of visual reference scans is proposed to facilitate fast visual scan matching in the SLAM design. In this method, new reference scans can be added to a database and an existent reference scan can be switched to be current reference scan automatically in SLAM calculation. Visual reference scans can be used repeatedly to reduce the computation complexity of extended Kalman filter (EKF) in the SLAM algorithm. Experimental results show that the correct matching rate of landmark features is 92.6%. Indoor navigation experiments validate the proposed localization algorithm. Average localization error of 10cm has been achieved in a 30m travel in an indoor environment using omni-directional images.

Human detection and tracking is important for user-friendly human-robot interaction. The robot should be able to find the user autonomously and keep its attention to the user in a human-like manner. In this paper, a design and experimental study of robust human detection and tracking is presented through fusion several modalities of sensory information. The multi-modal interaction design utilizes a combination of visual, audio, and laser scanner data for reliable detection and tracking of an interested user. During tracking motion, obstacle avoidance behavior will be activated any time required to ensure safety. Furthermore, user can further assign the robot to interact with other user by speech command. Experimental results show that the robot can robustly tracks person under complex scenarios.

This paper presents an intruder detection system which consists of a Zigbee sensor network and an autonomous mobile robot. Multiple Zigbee sensor modules installed in the environment can detect intruders and abnormal conditions. Sensor nodes transmit intrusion alarm to the monitoring center as well as the mobile robot via Zigbee wireless mesh network. The robot can navigate in the environment autonomously and approach to a target place using onborad localization system. If any possible intruder is detected, the robot immediately moves to that location and transmits images to remote mobile devices such as PDA or smart phone of security guards and users, in order to determine and response to the situation in real time.

Emotion recognition has become an important research area for advanced human-robot interaction. Through recognizing facial expressions, a robot can interact with a person with a more friendly manner. In this paper, we proposed a bimodal emotion recognition system by combining image and speech information. A novel information fusion strategy is proposed to set proper weights to two feature modalities based on their recognition reliability. The fusion weights are determined by the distance between test data and the classification hyperplane and the standard deviation of training samples. After normalization using the mean distance between training samples and the hyperplane, the fusion weight is set to represent the classification reliability of individual modality. In the latter bimodal SVM classification, the recognition result with higher weight is selected. The complete procedure has been implemented in a DSP-based system to recognize five facial expressions on-line in real time. The experimental results show that a recognition rate of 86.9% is achieved, an improvement of 5% compared with using only image information.

For a vision-based traffic monitoring and enforcement system, shadows of moving objects often cause serious errors in image analysis due to misclassification of shadows and moving vehicles. An effective shadow suppression method is thus required to improve the accuracy of image analysis and this paper proposes a novel color-space ratio model for detecting shadow pixels in traffic imagery. The proposed approach does not require many image sequences for constructing the model. Instead the model can be easily built up using a shadow region in a single image frame. To increase the accuracy of shadow detection, we design two types of spatial analysis to verify actual shadow pixels. Comparative results show that the proposed method works better than several well-known methods. The proposed methods have been applied to an image-based traffic monitoring system for detecting shadow pixels in traffic imagery. The experimental results not only validate the feasibility of the proposed algorithm but also successfully estimate traffic parameters such as traffic flows, traffic densities, vehicle turn ratios and vehicle speeds, all with satisfactory accuracy

This paper presents a novel heterogeneity-projection hard-decision (HPHD) color interpolation procedure for reproduction of Bayer mosaic images. The proposed algorithm aims to estimate the optimal interpolation direction and perform hard-decision interpolation, in which each pixel only needs to be interpolated once. A new heterogeneity-projection scheme based on a novel spectral-spatial correlation concept is proposed to estimate the best interpolation direction directly from the original mosaic image. Using the proposed heterogeneity-projection scheme, a hard-decision rule can be decided before performing the interpolation. The advantage of this scheme is that it provides an efficient way for decision-based algorithms to generate improved results using fewer computations. Compared with three recently reported demosaicing techniques, Gunturk's, Lu's, and Li's methods, the proposed HPHD outperforms all of them in both PSNR values and S-CIELAB deltaEab measures by utilizing 25 natural images from Kodak PhotoCD.

This paper presents a real-time human-robot interface system (HRIS), which processes both speech and vision information to improve the quality of communication between human and an autonomous mobile robot. The HRIS contains a real-time speech attention system and a real-time face tracking system. In the speech attention system, a microphone-array voice acquisition system has been developed to estimate the direction of speaker and purify the speaker's speech signal in a noisy environment. The developed face tracking system aims to track the speaker's face under illumination variation and react to the face motion. The proposed HRIS can provide a robot with the abilities of finding a speaker's direction, tracking the speaker's face, moving its body to the speaker, focusing its attention to the speaker who is talking to it, and purifying the speaker's speech. The experimental results show that the HRIS not only purifies speech signal with a significant performance, but also tracks a face under illumination variation in real-time

This paper presents a novel face tracking control scheme for human-robot interaction control in image plane. This control scheme is robust to the velocity quantization error in practical implementation. A visual tracking controller is designed for ensuring global asymptotic stability of the closed-loop visual tracking system based on an error-state control model in image plane. In order to overcome the quantization uncertainty encountered in practical systems, an image-based robust control law is proposed to guarantee the stability of the robotic control system based on Lyapunov theory. This design provides a useful solution for smooth visual tracking control of slow-motion robots in a home setting. Simulation and experimental results verify the effectiveness of the proposed visual tracking control scheme, both in terms of tracking performance and system convergence

This paper presents a design and implementation of a location-aware service system, which combines a radio-frequency-based positioning engine and a multimedia human-machine interface (HMI). In this system, a number of Zigbee sensors are deployed for the localization purpose. Users' locations can be estimated according to their received signal strength samples from the Zigbee sensors. In order to improve the positioning efficiency, a hierarchical positioning architecture is proposed. The multimedia HMI is to help users to access the provided services. A speech recognition system is designed as the input of the system and a visualization system has been developed as the output interface of the location-aware system. Moreover, the visualization service is integrated with the open service access (OSA) platform via mobile network systems. The whole system can be directed to future homecare applications.

This paper presents a design of behavior-fusion architecture for mobile robot navigation. We first design three behaviors for robot navigation, including obstacle avoidance, wall following, and goal seeking. We implement these primitive behaviors by using fuzzy-logic control approaches. Then, the fusion weight of each behavior is determined by using the proposed behavior-fusion neural network. The neural network maps the current environment sensor data to suitable fusion weights. Both computer simulation and practical experiments verify the effectiveness of the method.

Pan-tilt-zoom (PTZ) cameras have been widely used in recent years for monitoring and surveillance applications. These cameras provide flexible view selection as well as a wider observation range. This makes them suitable for vision-based traffic monitoring and enforcement systems. To employ PTZ cameras for image measurement applications, one first needs to calibrate the camera to obtain meaningful results. For instance, the accuracy of estimating vehicle speed depends on the accuracy of camera calibration and that of vehicle tracking results. This paper presents a novel calibration method for a PTZ camera overlooking a traffic scene. The proposed approach requires no manual operation to select the positions of special features. It automatically uses a set of parallel lane markings and the lane width to compute the camera parameters, namely, focal length, tilt angle, and pan angle. Image processing procedures have been developed for automatically finding parallel lane markings. Interesting experimental results are presented to validate the robustness and accuracy of the proposed method.

The measurement of vehicle turn ratio and based on that a prediction of the probability of a car to make a turn at an intersection are useful information for advanced traffic prediction and control. Conventional vision-based vehicle detection procedures that merely count the number of passing vehicles are not sufficient for turn ratio measurement, because they cannot tell where the vehicles come from at an intersection. This paper presents an image-based system for real-time turn ratio measurement. A method is proposed to estimate automatically the turn ratio of an intersection by using the techniques of detection window and optical flow calculation of motion vectors. A stand-alone image measurement system has been installed at a busy road junction in Hsinchu Science Park. Experimental results reveal that the average measurement error is within 2%.

This paper presents a real-time robotic vision system that provides visual information for a control scheme of mobile manipulation. The hardware implementation consists of a CMOS image board and a TI DSP board which uses C6416 as the main processor. The merits of using these two boards are the construction of a low cost embedded platform with high performance. Meanwhile the software implementation proposes a visual servoing using a behavior-based approach to solving the mobile manipulator control problem. The description of the hardware and software implementation is given and experimental results are discussed.

This paper presents an agent-based robot control (ARC) architecture. ARC features a flexible real-time control system, which is suitable for multi-robot cooperative tasks. It also provides an efficient platform for building up a multi-robot system consisting of heterogeneous robots. In this paper, an experimental study of this architecture is investigated. A cooperative exploration using two mobile robots will be demonstrated. In this experiment, one robot explores the environment by looking for a color-coded target and the other is responsible for task execution at the target position. While exploring in an unknown environment, the first robot, which is equipped with ultrasonic sensors for exploration, records its position as it sees deployed checkpoints. In a later phase, the second robot plans a path to the target directly using information passed from the first robot and get to the target position in an efficient way.

This paper presents a multi-agent approach to developing a flexible real-time control system for an autonomous mobile robot. The main purpose of this study is to integrate heterogeneous algorithms and functions onboard the robot, while still to guarantee a reasonable responding time. The balance between generality and flexibility is also addressed. This strategy provides a framework for developing complex intelligent machines through teamwork of several people. The proposed control system has been implemented on an experimental robot based on a real-time Linux platform. Practical experiments show that the robot successfully navigates through complex environments by combining visual tracking, obstacle avoidance, and command receiving behaviors in a single system.

This paper studies the general parking problem for unicycle-modeled mobile robots by combining the motion planning method with tracking controller design. We add a re-designed virtual trajectory to the original trajectory such that the parking problem can be transformed into a tracking problem. Consequently, a new global tracking controller is proposed to achieve the locally exponential convergence. Further improvement of the tracking performance is achieved using linearization and pole placement method. The proposed controllers are quite simple and can be easily implemented. The effectiveness of the proposed method is validated by several interesting experiments including the parallel parking and the back-into-garage parking.

This paper presents a study on a stand-alone image tracking system for automatic traffic monitoring. The proposed image tracker consists of three parts: an edge detection module, an image tracking module and a traffic monitoring module. The edge-detection module is a special designed circuit board, which features fast CCD image processing and feature extraction. Frame rate (60 Hz) edge detection of an image with resolution of 320/spl times/240 pixels is obtained on-board. The image tracking module performs the vehicle tracking in real time. Adopting active contour models and Kalman filtering techniques, we successfully achieved real-time image tracking of multi-lane moving vehicles. The traffic-monitoring module determines the traffic information from the tracked locations of vehicles. The current system provides three types of traffic information: the velocity of multi-lane vehicles, the number of vehicles and car accident detection. Experimental results are presented to demonstrate the real-time tracking of vehicles on an urban artery.

This paper presents a novel fast optical flow estimation algorithm and its application to real-lime obstacle avoidance of a guide-dog robot. The function of the laboratory-developed robot is to help blind or visually impaired pedestrians to move safely among obstacles. The proposed algorithm features a combination of the conventional correlation-based principle and the differential-based method for optical flow estimation. Employing image intensity gradients as features for pattern matching, we set up a brightness constraint to configure the search area. The merit of this scheme is that the computation load can be greatly reduced and in the mean time the possibility of estimation error is decreased. The vision system is installed on-board the robot to provide depth information of the immediate environment. The depth data are transformed to a safety distribution histogram and used for real-time obstacle avoidance. Experimental results demonstrate that the proposed method is effective for a guidance robot in a dynamic environment.

A general tracking control problem with saturation constraint for nonholonomic mobile robots is proposed and solved using the backstepping technique. A global result is given in which some artificial assumptions about the linear and the angular velocities of mobile robots from recent literature are dropped. The proposed controller can simultaneously solve both the tracking problem and the regulation problem of mobile robots. With the proposed control laws, mobile robots can now globally follow any path such as a straight line, a circle and the path approaching to the origin using a single controller. Computer simulations are presented which confirm the effectiveness of the tracking control laws. Moreover, practical experimental results concerning the tracking control are reported with saturation constraint for mobile robots.

A reactive navigation system for an autonomous mobile robot in unstructured dynamic environments is presented. The motion of moving obstacles is estimated for robot motion planning and obstacle avoidance. A multisensor-based obstacle predictor is utilized to obtain obstacle-motion information. Sensory data from a CCD camera and multiple ultrasonic range finders are combined to predict obstacle positions at the next sampling instant. A neural network, which is trained off-line, provides the desired prediction on-line in real time. The predicted obstacle configuration is employed by the proposed virtual force based navigation method to prevent collision with moving obstacles. Simulation results are presented to verify the effectiveness of the proposed navigation system in an environment with multiple mobile robots or moving objects. This system was implemented and tested on an experimental mobile robot at our laboratory. Navigation results in real environment are presented and analyzed.

The problem of navigating a mobile robot among moving obstacles is usually solved on the condition of knowing the velocity of obstacles. However, it is difficult to provide such information to a robot in real time. In this paper, we present an environment predictor that provides an estimate of future environment configuration by fusing multisensor data in real time. The predictor is implemented by an artificial neural network (ANN) trained using a relative-error-backpropagation (REBP) algorithm. The REBP algorithm enables the ANN to provide output data with a minimum relative error, which is better than conventional backpropagation (BP) algorithms in this prediction application. The mobile robot can, therefore, respond to anticipated changes in the environment. The performance is verified by prediction simulation and navigation experiments.

In this paper we present a virtual force guidance (VFG) system for dynamic motion planning and navigation of a mobile robot. This new method is developed to work with a predicted environment, which is provided by an artificial neural network (ANN) using the information from on-board sensor system. The proposed ANN predictor is trained by a relative-error-backpropagation (REBP) algorithm derived in this paper. The REBP algorithm allows the outputs of an ANN to have minimum relative error, which is better than the conventional backpropagation algorithm in this particular application. The VFG system, which can react to the future environment, assumes that the goal attracts the robot and the future obstacles repulse it. The resultant force determines the desired change in motion. This motion is therefore dependent on both the current motion of the robot and the future environment. Both simulation and experimental results are presented to show our approach can effectively navigate the robot in a human-like fashion.

The beam-opening angle problem of an ultrasonic range sensor is solved by using artificial neural networks to fuse multiple ultrasonic sensors. A mathematical model about the same problem is also derived. Both simulation and experimental results of scanning images are presented. The line extractor of the sensor image is developed by using the regression model with a little modification. The simulation results show this method is useful for environment recognition of robotic systems.

A navigation system based on fuzzy logic controllers is developed for a mobile robot in an unknown environment. The structure of this fuzzy navigation system features the com- bination of sensor system, fuzzy controllers for motion planning and the motion control system for real-time execution. Six ultrasonic sensors on-board the mobile robot are used for distance measurement to the immediate obstacles. Sensor data are fuzzified to be the inputs of the fuzzy controller. Three states, each with five quantized levels are used to define the fuzzy set. Two fuzzy controllers are designed to handle the naviga- tion problem. Each fuzzy controller, which cor- responds to the turn right or turn left condition, has four inputs, two outputs and 81 rules. The outputs are the command velocities to the left and right wheels, which drive the mobile robot. These command velocities are sent to the lower level motion control system. The performance of this navigation system is tested by computer sim- ulation. Satisfactory results have been obtained and are presented in this paper.

A planning procedure is developed for the navigation of a mobile robot in an unknown environment. A modified Gilles algorithm is used for path planning based on the world model which can be constructed from or modified by sensory information. with this algorithm, the environment is modelled as cells generated by using the safe-margin of obstacles. this method results in faster search than the original Gilles algorithm. The quadratic method is used to search for the desired path in a region of quadrant that is determined by the start and goal positions. To construct an environment model by means of the sensory information, the method of using bit-mapping sequences is developed. It is further fit into the world model and used by the path planning procedure. Smooth motion planning is achieved by using the predictor method in order to facilitate a direct commanding to the real robot. A monitor is developed using the techniques of expert systems to run the computer simulation.>