Showing papers on "Obstacle published in 2015"

StixelNet: A Deep Convolutional Network for Obstacle Detection and Road Segmentation.

Abstract: General obstacle detection is a key enabler for obstacle avoidance in mobile robotics and autonomous driving. In this paper we address the task of detecting the closest obstacle in each direction from a driving vehicle. As opposed to existing methods based on 3D sensing we use a single color camera. The main novelty in our approach is the reduction of the task to a column-wise regression problem. The regression is then solved using a deep convolutional neural network (CNN). In addition, we introduce a new loss function based on a semi-discrete representation of the obstacle position probability to train the network. The network is trained using ground truth automatically generated from a laser-scanner point cloud. Using the KITTI dataset, we show that the our monocularbased approach outperforms existing camera-based methods including ones using stereo. We also apply the network on the related task of road segmentation achieving among the best results on the KITTI road segmentation challenge.

The obstacle detection and obstacle avoidance algorithm based on 2-D lidar

Abstract: Obstacle avoidance ability is the significant embodiment of the ground mobile robot, and the basic guarantee of the ground mobile robot to perform various tasks. Obstacle avoidance technologies are divided into two kinds, one is based on the global map and another is based on sensors respectively. This paper mainly aims at the local obstacle avoidance method based on sensors. The study of obstacle detection and obstacle avoidance are two inseparable parts in the research of obstacle avoidance ability. This paper proposes an efficient obstacle detection and obstacle avoidance algorithm based on 2-D lidar. A method is proposed to get the information of obstacles by filtering and clustering the laser-point cloud data. Also, this method generates the forward angle and velocity of robot based on the principle of minimum cost function. The obstacle detection and obstacle avoidance algorithm has advantages of a simple mathematical model and good real-time performance. The effectiveness of the proposed algorithm is verified on MATLAB simulation platform.

Obstacle detection for self-driving cars using only monocular cameras and wheel odometry

Abstract: Mapping the environment is crucial to enable path planning and obstacle avoidance for self-driving vehicles and other robots. In this paper, we concentrate on ground-based vehicles and present an approach which extracts static obstacles from depth maps computed out of multiple consecutive images. In contrast to existing approaches, our system does not require accurate visual inertial odometry estimation but solely relies on the readily available wheel odometry. To handle the resulting higher pose uncertainty, our system fuses obstacle detections over time and between cameras to estimate the free and occupied space around the vehicle. Using monocular fisheye cameras, we are able to cover a wider field of view and detect obstacles closer to the car, which are often not within the standard field of view of a classical binocular stereo camera setup. Our quantitative analysis shows that our system is accurate enough for navigation purposes of self-driving cars and runs in real-time.

Virtual proxemics: Locomotion in the presence of obstacles in large immersive projection environments

Abstract: In this paper, we investigate obstacle avoidance behavior during real walking in a large immersive projection setup. We analyze the walking behavior of users when avoiding real and virtual static obstacles. In order to generalize our study, we consider both anthropomorphic and inanimate objects, each having his virtual and real counterpart. The results showed that users exhibit different locomotion behaviors in the presence of real and virtual obstacles, and in the presence of anthropomorphic and inanimate objects. Precisely, the results showed a decrease of walking speed as well as an increase of the clearance distance (i. e., the minimal distance between the walker and the obstacle) when facing virtual obstacles compared to real ones. Moreover, our results suggest that users act differently due to their perception of the obstacle: users keep more distance when the obstacle is anthropomorphic compared to an inanimate object and when the orientation of anthropomorphic obstacle is from the profile compared to a front position. We discuss implications on future large shared immersive projection spaces.

Fast image-based obstacle detection from unmanned surface vehicles

Abstract: Obstacle detection plays an important role in unmanned surface vehicles (USV). The USVs operate in highly diverse environments in which an obstacle may be a floating piece of wood, a scuba diver, a pier, or a part of a shoreline, which presents a significant challenge to continuous detection from images taken onboard. This paper addresses the problem of online detection by constrained unsupervised segmentation. To this end, a new graphical model is proposed that affords a fast and continuous obstacle image-map estimation from a single video stream captured onboard a USV. The model accounts for the semantic structure of marine environment as observed from USV by imposing weak structural constraints. A Markov random field framework is adopted and a highly efficient algorithm for simultaneous optimization of model parameters and segmentation mask estimation is derived. Our approach does not require computationally intensive extraction of texture features and comfortably runs in real-time. The algorithm is tested on a new, challenging, dataset for segmentation and obstacle detection in marine environments, which is the largest annotated dataset of its kind. Results on this dataset show that our model outperforms the related approaches, while requiring a fraction of computational effort.

UAV obstacle avoidance using potential field under dynamic environment

Abstract: In this paper, the potential field principle is applied to several UAVs (Unmanned Aerial Vehicles) for optimal path planning. Each UAV has its own goals and it is used the attractive potential field to reach the goals. On the contrary, each UAV is considered as obstacle for other UAVs that must be avoided. In this research, there are two types of obstacles, i.e the static and dynamic. The repulsive potential field principle is used to avoid for both static and dynamic obstacles. The whole method is implemented into Parrot AR Drone 2.0 Quadcopter model of UAV and simulated in Gazebo Simulator by Robot Operating System (ROS). The results of this research are to control the thrust of quadcopter so that it is in flying position, the value of value of roll (α) or pitch (β) must set to not equal or approaching 90° or −90° and not between −180° and 180° or between −90° and 90°. Based on the dynamic obstacle performance test with parameter tuning, the optimal avoidance is when the η value is 7.8 while when in static and dynamic test with parameter tuning, the optimal avoidance is when the η value is 7.9 noted by the fastest time and the shortest path.

An Indoor Obstacle Detection System Using Depth Information and Region Growth.

Abstract: This study proposes an obstacle detection method that uses depth information to allow the visually impaired to avoid obstacles when they move in an unfamiliar environment. The system is composed of three parts: scene detection, obstacle detection and a vocal announcement. This study proposes a new method to remove the ground plane that overcomes the over-segmentation problem. This system addresses the over-segmentation problem by removing the edge and the initial seed position problem for the region growth method using the Connected Component Method (CCM). This system can detect static and dynamic obstacles. The system is simple, robust and efficient. The experimental results show that the proposed system is both robust and convenient.

Toward an Autonomous Sailing Boat

Abstract: Among autonomous surface vehicles, sailing robotics could be a promising technology for long-term missions and semipersistent presence in the oceans. Autonomy of such vehicles in terms of energy will be achieved by renewable solar and wind power sources. Autonomy in terms of sailing decision will be achieved by innovative perception and navigation modules. The main contribution of this paper is to propose a complete hardware and software architecture for an autonomous sailing robot. The hardware architecture includes a comprehensive set of sensors and actuators as well as a solar panel and a wind turbine. For obstacle detection, a segmentation is performed on data coming from an omnidirectional camera coupled with an inertial measurement unit and a sonar. For navigation and control of the vehicle, a potential-based reactive path-planning approach is proposed. The specific sailboat kinematic constraints are turned into virtual obstacles to compute a feasible and optimal heading in terms of cost of gybe and tack maneuver as well as safety relative to obstacle danger. Finally, field test experiments are presented to validate the various components of the system.

The obstacle problem for the porous medium equation

Abstract: We prove existence results for the obstacle problem related to the porous medium equation. For sufficiently regular obstacles, we find continuous solutions whose time derivative belongs to the dual of a parabolic Sobolev space. We also employ the notion of weak solutions and show that for more general obstacles, such a weak solution exists. The latter result is a consequence of a stability property of weak solutions with respect to the obstacle.

Mobile robot obstacle detecting and avoiding method and system

Abstract: The invention provides a mobile robot obstacle detecting and avoiding method and a system. The method comprises steps: information of an obstacle in a detection region is acquired, the state of the obstacle in the detection region is judged according to the acquired obstacle information, states comprise a static state and a mobile state, and an avoiding strategy of the mobile robot is determined according to the state of the obstacle. The invention also provides a mobile robot obstacle detecting and avoiding system, which comprises a ranging sensor, a state judger and a mobile robot driving structure. When the method and the system of the invention are used, different obstacle avoiding strategies can be adjusted according to obstacle appearing time, an obstacle avoiding behavior of walking along the original path is increased compared with the existing obstacle detouring mode, if the obstacle leaves in a set time or the obstacle leaves after appearing instantaneously, the mobile robot can walk continuously according to the planned path, and demands of a path planner can be better met.

Collision avoidance for quadrotor using stereo vision depth maps

Abstract: A collision avoidance algorithm for a quadrotor unmanned aerial vehicle using a stereo vision sensor is proposed. A mathematical model for the quadrotor is developed, and the underactuated problem of the quadrotor is treated by introducing virtual inputs. Stereo vision is used to obtain depth map information, which is used to detect an obstacle. The collision cone approach is adopted to avoid collisions between the quadrotor and the detected obstacle. The collision prediction is conducted by using the relation between the velocity vector of the quadrotor and the collision cone. Information of the detected obstacles is accumulated to determine the location and size of the obstacles, which is used to prevent the quadrotor from colliding with the obstacle. Multiple obstacles can also be managed by creating obstacle clusters in the image plane. A waypoint guidance law and controller are designed using a feedback linearization scheme and a linear quadratic tracker. Numerical simulations are performed to demonstrate the performance of the proposed algorithm.

Methane–air explosion characteristics with different obstacle configurations

Abstract: To investigate the flame and overpressure characteristics of methane–air explosion with different obstacle configurations, an experimental study has been conducted, taking account of the number of obstacles, obstacle distance from ignition source, and stream-wise and cross-wise obstacle positions. The results show that the flame speed and peak overpressure increase with the increasing number of obstacles, while the time to reach the peak is not fully determined by it. And the configuration having the farthest obstacle produces a higher overpressure and takes a longer time to reach the peak, but a slower flame propagation speed is obtained. Similar explosion characteristics are also observed in the configurations with two obstacles fixed at different stream-wise positions. Furthermore, the experimental results demonstrate that the peak overpressures and flame speeds in configurations with central or staggered obstacles are relatively higher, which should to be avoided in practical processes to minimize the risk associated with methane–air explosion.

An L^1 Penalty Method for General Obstacle Problems

Abstract: We construct an efficient numerical scheme for solving obstacle problems in divergence form. The numerical method is based on a reformulation of the obstacle in terms of an $L^1$-like penalty on the variational problem. The reformulation is an exact regularizer in the sense that for a large (but finite) penalty parameter, we recover the exact solution. Our formulation is applied to classical elliptic obstacle problems as well as some related free boundary problems, for example, the two-phase membrane problem and the Hele--Shaw model. One advantage of the proposed method is that the free boundary inherent in the obstacle problem arises naturally in our energy minimization without any need for problem specific or complicated discretization. In addition, our scheme also works for nonlinear variational inequalities arising from convex minimization problems.

Omnidirectional visual obstacle detection using embedded FPGA

Abstract: For autonomous navigation of Micro Aerial Vehicles (MAVs) in cluttered environments, it is essential to detect potential obstacles not only in the direction of flight but in their entire local environment. While there exist systems that do vision based obstacle detection, most of them are limited to a single perception direction. Extending these systems to a multi-directional sensing approach would exhaust the payload limit in terms of weight and computational power. We present a novel light-weight sensor setup comprising of four stereo heads and an inertial measurement unit (IMU) to perform FPGA-based dense reconstruction for obstacle detection in all directions. As the data-rate scales up with the number of cameras we use an FPGA to perform streaming based tasks in real-time and show a light-weight polar-coordinate map to allow a companion computer to fully process the data of all the cameras and perform obstacle detection in real-time. The system is able to process up to 80 frames per second (fps) freely distributed on the four stereo heads while maintaining a low power budget. The perception system including FPGA, image sensors and stereo mounts is 235 g in weight.

UAV obstacle avoidance using RGB-D system

Abstract: This work proposes an obstacle avoidance strategy for UAV navigation in indoor environments. The proposal is able to compute the distance among the UAV and the obstacles (which change their position dynamically), and then to select the closest one. When a collision risk is pointed out, the algorithm establish some escape points, whose orientation is aligned tangentially to the obstacle edge or to the UAV normal displacement. Considering that only the desired point is change during the avoidance maneuver, the stability of the whole nonlinear system is demonstrated in the sense of Lyapunov. Information Filter is used to track the 3D positioning of the UAV and the obstacles. Moreover, UAV state variables are given by a Decentralized Information Filter, which fuses information from the Inertial Measurement Unit onboard the aircraft and the depth-camera sensor (RGB-D). The effectiveness of the proposal is demonstrated by simulation results, which take into account the AR.drone rotorcraft dynamic model.

Instantaneous impact point based unmanned aerial vehicle non-collaborative real-time obstacle avoidance method

Abstract: The invention discloses an instantaneous impact point based unmanned aerial vehicle non-collaborative real-time obstacle avoidance method. The instantaneous impact point based unmanned aerial vehicle non-collaborative real-time obstacle avoidance method comprises the steps of 1 performing obstacle detection, namely obtaining a relative motion state of an obstacle, 2 performing obstacle motion estimation, namely obtaining machine state information based on satellite navigation information and calculating a motion state of an inertial space obstacle, 3 performing impact conflict detection, namely judging whether obstacle impact occurs or not, 4 performing obstacle avoidance decision making, namely making an obstacle avoidance decision based on a detection result in the step 3, 5 performing obstacle avoidance route re-planning based on a quick expanding random tree algorithm considering an instantaneous impact point, namely introducing route evaluation heuristic information based on the instantaneous impact point and achieving obstacle avoidance route re-planning. The instantaneous impact point based unmanned aerial vehicle non-collaborative real-time obstacle avoidance method has the advantages of being simple in principle, easy to achieve, capable of improving unmanned aerial vehicle safety and the like.

Aerial Obstacle Detection With 3 - D Mobile Devices

Abstract: In this paper, we present a novel approach for aerial obstacle detection (e.g., branches or awnings) using a 3-D smartphone in the context of the visually impaired (VI) people assistance. This kind of obstacles are especially challenging because they cannot be detected by the walking stick or the guide dog. The algorithm captures the 3-D data of the scene through stereo vision. To our knowledge, this is the first work that presents a technology able to obtain real 3-D measures with smartphones in real time. The orientation sensors of the device (magnetometer and accelerometer) are used to approximate the walking direction of the user, in order to look for the obstacles only in such a direction. The obtained 3-D data are compressed and then linearized for detecting the potential obstacles. Potential obstacles are tracked in order to accumulate enough evidence to alert the user only when a real obstacle is found. In the experimental section, we show the results of the algorithm in several situations using real data and helped by VI users.

Mobile robot obstacle avoidance navigation method and system

Abstract: The invention discloses a mobile robot obstacle avoidance navigation method and system. The method includes the following steps that: a global map of a home environment is established; the starting point and destination of the movement of a robot are set; the movement path of the robot is planned according to the A* algorithm; the position of a obstacle is marked in the global map; the movement path of the robot is re-planned according to the A* algorithm; the robot is controlled to move according to the planned path; and the robot arrives at the destination and stops moving. With the mobile robot obstacle avoidance navigation method and system of the invention adopted, unknown environment can be detected, so that the information of unknown obstacles can be obtained, and the estimation function is adopted to plan the shortest and most economical path, and therefore, the equipment cost of the obstacle avoidance navigation of the robot can be decreased; the position and movement attitude of the robot can be monitored in real time, and the walking attitude of the robot can be adjusted and controlled in real time, and the accuracy and effectiveness of the obstacle avoidance navigation of the robot can be ensured.

How Obstacles Perturb Population Fronts and Alter Their Genetic Structure.

Abstract: As populations spread into new territory, environmental heterogeneities can shape the population front and genetic composition. We focus here on the effects of an important building block of heterogeneous environments, isolated obstacles. With a combination of experiments, theory, and simulation, we show how isolated obstacles both create long-lived distortions of the front shape and amplify the effect of genetic drift. A system of bacteriophage T7 spreading on a spatially heterogeneous Escherichia coli lawn serves as an experimental model system to study population expansions. Using an inkjet printer, we create well-defined replicates of the lawn and quantitatively study the population expansion of phage T7. The transient perturbations of the population front found in the experiments are well described by a model in which the front moves with constant speed. Independent of the precise details of the expansion, we show that obstacles create a kink in the front that persists over large distances and is insensitive to the details of the obstacle’s shape. The small deviations between experimental findings and the predictions of the constant speed model can be understood with a more general reaction-diffusion model, which reduces to the constant speed model when the obstacle size is large compared to the front width. Using this framework, we demonstrate that frontier genotypes just grazing the side of an isolated obstacle increase in abundance, a phenomenon we call ‘geometry-enhanced genetic drift’, complementary to the founder effect associated with spatial bottlenecks. Bacterial range expansions around nutrient-poor barriers and stochastic simulations confirm this prediction. The effect of the obstacle on the genealogy of individuals at the front is characterized by simulations and rationalized using the constant speed model. Lastly, we consider the effect of two obstacles on front shape and genetic composition of the population illuminating the effects expected from complex environments with many obstacles.

Track obstacle detection system based on machine vision

Abstract: The invention discloses a track obstacle detection system based on machine vision, and belongs to the field of railway safety. Black and white video images are obtained by an on-board camera installed at the head of a train, and the track is similarly linear or bent is judged according to that whether the camera is over travel. Manual detection of bend states is achieved by fixing a high definition camera and a wireless transmitting device at a bend for receiving wireless images. A similar straightway analyzes the obtained real-time image sequence, and divides forward obstacles into a non-dangerous class (including static small obstacles, moving objects quickly crossing the track) and a dangerous class (static large obstacles, moving obstacles influencing pass of the train) by adopting a track edge extraction algorithm based on hood conversion and Otsu threshold value, combining an inter-frame difference method based on mathematical morphology improvement with a background difference method and adopting an angular point feature matching tracking algorithm. The track obstacle detection system based on machine vision can quickly process track images, more effectively and accurately extract track edges, and is high in detection precision of track obstacles.

Obstacle avoidance system

Abstract: On a basis of a relative position of an obstacle 401 , a size of the obstacle in an own vehicle 12 width direction and a width of the own vehicle 12 , a maximum amount D t of movement of the own vehicle 12 in the vehicle width direction as required to avoid the obstacle 401 is calculated. A point displaced over the maximum amount of movement toward a side of the adjacent lane from the relative position of the obstacle 401 is determined as an avoiding point 250 . If a distance d between the avoiding point 250 and the adjacent lane is greater than the width Wm of the own vehicle 12 , an avoiding path is generated for allowing the own vehicle 12 to pass the avoiding point 250.

Flame Acceleration in Tube Explosions with up to Three Flat-bar Obstacles with Variable Obstacle Separation Distance

Abstract: The effect of obstacle separation distance on the severity of gas explosions has received little methodical study It was the aim of this work to investigate the influence of obstacle spacing of up to three flat-bar obstacles The tests were performed using methane-air (10% by vol), in an elongated vented cylindrical vessel 162 mm internal diameter with an overall length-to-diameter, L/D, of 277 The obstacles had either 2 or 4 flat-bars and presenting 20% blockage ratio to the flow path The different number of flat-bars for the same blockage achieved a change of the obstacle scale which was also part of this investigation The first two obstacles were kept at the established optimum spacing and only the spacing between the second and third obstacles was varied The profiles of maximum flame speed and overpressure with separation distance were shown to agree with the cold flow turbulence profile determined in cold flows by other researchers However, the present results showed that the maximum effect in explosions is experienced at 80 to 100 obstacle scales about 4 times further downstream than the position of maximum turbulence determined in the cold flow studies Similar trends were observed for the flames speeds In both cases the optimum spacing between the second and third obstacles corresponded to the same optimum spacing found for the first two obstacles demonstrating that the optimum separation distance does not change with number of obstacles In planning the layout of new installations, the worst case separation distance needs to be avoided but incorporated when assessing the risk to existing set-ups The results clearly demonstrate that high congestion in a given layout does not necessarily imply higher explosion severity as traditionally assumed Less congested but optimally separated obstructions can lead to higher overpressures

Similarities and differences of the body control during professional collision with a vertical obstacle of men aged 24 and 65

Abstract: Background & Study Aim: Both the epidemiology of body injuries due to collision with vertical obstacles or objects in motion and the prevention of such events are very rarely discussed in the scientific literature. Understanding the kinematics of body movement during a collision with vertical obstacle may constitute a significant element used to create rational methodology for injury prevention in these circumstances. The aim of the study is to answer the question whether significant age difference of men training combat sports results in differentiation of the body control during professional collision with hard vertical obstacle forced by an external force and as a consequence whether it affects the way to protect head in particular and the amount of dissipated energy. Material & Methods: Two men have been subjected to the study: a 65-years-old scientist (A), who has been training judo and other combat sports for over than fifty years and is professionally involved in teaching people how to fall down safely; a 24-years-old physiotherapist (B), who trains judo as an amateur, has completed specialist course on safe falling and used those exercises in his kinesitherapy practice (including patients with psychological disorders). The analysis of kinematics of body movement during a collision with vertical obstacle was conducted. The collisions were forced by the assistant. Tested person was standing freely (with muscles relaxed) facing the front of the concrete wall at the distance of 2 metres. Assistant pushed the tested person each time towards the wall with similar force in the same way (by pressing the neck with one hand and lumbar spine with another). Measurements have been performed with the use of MVN Biomech system (XSENS) based on inertial sensors equipped with accelerometer, gyroscope and magnetic field sensor. The analysis involved four registered collisions with the wall of each tested person. Results: Since the contact of the upper limbs with the wall to the moment of stopping the body centre mass movement, both men shielded and protected the head by lifting their arms up and simultaneously flexing the arms in the elbows. This proves that the body surface in contact with the obstacle is almost identical in both men. Men A more effectively amortises the collision with the vertical obstacle. This is reflected in the average values of the head mass accelerations, which were lower by approx. 16% than in man B; the average energy absorbed by the body tissues of man A amounted to approx. 77%, whereas man B to 91% of the collision energy (man A dissipated energy more effectively). More effective amortisation of the collision with vertical obstacle by man A resulted moreover from the movements of his body segments after the collision (mainly flexing the knees, which is possible due to the relaxation of the muscles around this joint). The movement of body segments of man A in the second phase results in the increase of the mass centre movement in the direction of sagittal axis and in the increase in the body movement range. Authors’ Contribution: A Study Design B Data Collection C Statistical Analysis D Manuscript Preparation E Funds Collection  ORIGINAL ARTICLE

Path planning of mobile robot by mixing experience with modified artificial potential field method

Abstract: In this article, a new method is proposed to help the mobile robot to avoid many kinds of collisions effectively, which combined past experience with modified artificial potential field method. In the process of the actual global obstacle avoidance, system will invoke case-based reasoning algorithm using its past experience to achieve obstacle avoidance when obstacles are recognized as known type; otherwise, it will invoke the modified artificial potential field method to solve the current problem and the new case will also be retained into the case base. In case-based reasoning, we innovatively consider that all the complex obstacles are retrieved by two kinds of basic build-in obstacle models (linear obstacle and angle-type obstacle). Our proposed experience mixing with modified artificial potential field method algorithm has been simulated in MATLAB and implemented on actual mobile robot platform successfully. The result shows that the proposed method is applicable to the dynamic real-time obstacle avo...