scispace - formally typeset
Search or ask a question

Showing papers on "Obstacle published in 2005"


Proceedings Article
Urs A. Muller, Jan Ben, Eric Cosatto1, Beat Flepp, Yann Le Cun 
05 Dec 2005
TL;DR: A vision-based obstacle avoidance system for off-road mobile robots that is trained from end to end to map raw input images to steering angles and exhibits an excellent ability to detect obstacles and navigate around them in real time at speeds of 2 m/s.
Abstract: We describe a vision-based obstacle avoidance system for off-road mobile robots. The system is trained from end to end to map raw input images to steering angles. It is trained in supervised mode to predict the steering angles provided by a human driver during training runs collected in a wide variety of terrains, weather conditions, lighting conditions, and obstacle types. The robot is a 50cm off-road truck, with two forward-pointing wireless color cameras. A remote computer processes the video and controls the robot via radio. The learning system is a large 6-layer convolutional network whose input is a single left/right pair of unprocessed low-resolution images. The robot exhibits an excellent ability to detect obstacles and navigate around them in real time at speeds of 2 m/s.

538 citations


Journal ArticleDOI
TL;DR: An obstacle detection technique that does not rely on typical structural assumption on the scene; a color-based classification system to label the detected obstacles according to a set of terrain classes; and an algorithm for the analysis of ladar data that allows one to discriminate between grass and obstacles, even when such obstacles are partially hidden in the grass are proposed.
Abstract: Autonomous navigation in cross-country environments presents many new challenges with respect to more traditional, urban environments. The lack of highly structured components in the scene complicates the design of even basic functionalities such as obstacle detection. In addition to the geometric description of the scene, terrain typing is also an important component of the perceptual system. Recognizing the different classes of terrain and obstacles enables the path planner to choose the most efficient route toward the desired goal. This paper presents new sensor processing algorithms that are suitable for cross-country autonomous navigation. We consider two sensor systems that complement each other in an ideal sensor suite: a color stereo camera, and a single axis ladar. We propose an obstacle detection technique, based on stereo range measurements, that does not rely on typical structural assumption on the scene (such as the presence of a visible ground plane)s a color-based classification system to label the detected obstacles according to a set of terrain classess and an algorithm for the analysis of ladar data that allows one to discriminate between grass and obstacles (such as tree trunks or rocks), even when such obstacles are partially hidden in the grass. These algorithms have been developed and implemented by the Jet Propulsion Laboratory (JPL) as part of its involvement in a number of projects sponsored by the US Department of Defense, and have enabled safe autonomous navigation in high-vegetated, off-road terrain.

500 citations


Proceedings ArticleDOI
20 Jun 2005
TL;DR: An artificial vision algorithm for real-time obstacle detection in unstructured environments using a new approach, of low computational load, to calculate a V-disparity image between left and right corresponding images in order to estimate the cameras pitch oscillation caused by the vehicle movement.
Abstract: In this paper we present an artificial vision algorithm for real-time obstacle detection in unstructured environments. The images have been taken using a stereoscopical vision system. The system uses a new approach, of low computational load, to calculate a V-disparity image between left and right corresponding images, in order to estimate the cameras pitch oscillation caused by the vehicle movement. Then, the obstacles are localized by stereo matching and mapped in real world coordinates. Experimental results on sequences taken from a moving vehicle (which partecipated to the DARPA Grand Challenge 2004) in different unstructured scenarios are then presented, to demonstrate the validity of the approach.

181 citations


Proceedings ArticleDOI
01 Jan 2005
TL;DR: In this paper, the authors present an autonomous exploration method for unmanned aerial vehicles in unknown urban environment by building local obstacle maps and solving for confli ct-free trajectory using model predictive control framework.
Abstract: §In this paper, we present an autonomous exploration method for unmanned aerial vehicles in unknown urban environment. We address two major aspects of explorationgathering information about the surroundings and avoiding obstacles in the flight path- by building local obstacle maps and solving for confli ct-free trajectory using model predictive control (MPC) framework. For obstacle sensing, an onboard laser scanner is used to detect nearby objects around the vehicle. An MPC algorithm with a cost function that penalizes the proximity to the nearest obstacle replans the fligh t path in real-time. The adjusted trajectory is sent to the position tracking layer in the UAV a vionics. The proposed approach is implemented on Berkeley rotorcraft UAVs and successfully tested in a series of flights in urban obstacle setup.

144 citations


Journal ArticleDOI
TL;DR: In this paper, the effect of using different obstacles on thermal stratification in a cylindrical hot water tank is analyzed numerically using both experimental and numerical results, and the results indicate that placing obstacle in the tank provides better thermal stratified compared to the no obstacle case.

143 citations


Proceedings ArticleDOI
18 Apr 2005
TL;DR: A vision-based obstacle detection system for small unmanned aerial vehicles (UAVs) is presented and the feasibility of this approach is demonstrated by using the vision output to steer a small unmanned aircraft to fly towards an obstacle.
Abstract: A vision-based obstacle detection system for small unmanned aerial vehicles (UAVs) is presented. Obstacles are detected by segmenting the image into sky and non-sky regions and treating the non-sky regions as obstacles. The feasibility of this approach is demonstrated by using the vision output to steer a small unmanned aircraft to fly towards an obstacle. The experiment was first verified in a hardware in the loop (HIL) simulation and then successfully implemented on a small modified remote control plane using a large inflatable balloon as the obstacle.

135 citations


Journal ArticleDOI
TL;DR: A navigation strategy that exploits the optic flow and inertial information to continuously avoid collisions with both lateral and frontal obstacles has been used to control a simulated helicopter flying autonomously in a textured urban environment.

125 citations


Patent
24 Jan 2005
TL;DR: In this paper, the authors present a system for navigating a UAV that includes piloting the UAV under control of a navigation computer, in accordance with a navigation algorithm, while reading from the GPS receiver a sequence of GPS data and identifying an obstacle in dependence upon the future position.
Abstract: Methods, systems, and computer program products are provided for navigating a UAV that include piloting the UAV, under control of a navigation computer, in accordance with a navigation algorithm. While piloting the UAV, embodiments include reading from the GPS receiver a sequence of GPS data, anticipating a future position of the UAV, identifying an obstacle in dependence upon the future position, selecting an obstacle avoidance algorithm, and piloting the UAV in accordance with an obstacle avoidance algorithm. Identifying an obstacle in dependence upon the future position may include comprises retrieving obstacle data from a database in dependence the future position. Identifying an obstacle in dependence upon the future position may also include depicting an anticipated flight of the UAV with 3D computer graphics in dependence upon the future position and identifying an obstacle in dependence upon the depiction of the anticipated flight.

125 citations


Proceedings ArticleDOI
18 Apr 2005
TL;DR: The method uses a novel combination of a 3D occupancy grid for robust sensor data interpretation and a 2.5D height map for fine resolution floor values for humanoid robot QRIO to generate detailed maps for autonomous navigation.
Abstract: With the development of biped robots, systems became able to navigate in a 3 dimensional world, walking up and down stairs, or climbing over small obstacles. We present a method for obtaining a labeled 2.5D grid map of the robot's surroundings. Each cell is marked either as floor or obstacle and contains a value telling the height of the floor or obstacle. Such height maps are useful for path planning and collision avoidance. The method uses a novel combination of a 3D occupancy grid for robust sensor data interpretation and a 2.5D height map for fine resolution floor values. We evaluate our approach using stereo vision on the humanoid robot QRIO and show the advantages over previous methods. Experimental results from navigation runs on an obstacle course demonstrate the ability of the method to generate detailed maps for autonomous navigation.

93 citations


Patent
Setsuo Tokoro1
02 Jun 2005
TL;DR: In this article, a radar detects existence of an object around a vehicle, an image taking part such as a camera takes an image of the object around the vehicle, a determination threshold is set at a low value when it is determined based on image information of the photographic image that a possibility of presence of an obstacle is high, the determination threshold was set at high value when the possibility of the presence of the obstacle is low, and these determination threshold values are used to detect the obstacle to travel of the vehicle on the basis of the output from the radar.
Abstract: The present invention relates to an obstacle recognition system and an obstacle recognition method. A radar detects existence of an object around a vehicle, an image taking part such as a camera takes an image of the object around the vehicle, a determination threshold is set at a low value when it is determined based on image information of the photographic image that a possibility of presence of an obstacle is high, the determination threshold is set at a high value when it is determined that the possibility of the presence of the obstacle is low, and these determination threshold values are used to detect the obstacle to travel of the vehicle on the basis of the output from the radar.

68 citations


Proceedings ArticleDOI
05 Dec 2005
TL;DR: The obstacle-restriction technique is a method that avoids common limitations of previous obstacle avoidance methods, improving their navigation performance in difficult scenarios and is illustrated with experimental results obtained with a robotic wheelchair vehicle.
Abstract: This paper addresses the obstacle avoidance problem in difficult scenarios that usually are dense, complex and cluttered. The proposal is a method called the obstacle-restriction. At each iteration of the control cycle, this method addresses the obstacle avoidance in two steps. First there is procedure to compute instantaneous subgoals in the obstacle structure (obtained by the sensors). The second step associates a motion restriction to each obstacle, which are managed next to compute the most promising motion direction. The advantage of this technique is that it avoids common limitations of previous obstacle avoidance methods, improving their navigation performance in difficult scenarios. Furthermore, we obtain similar results to the recent methods that achieve navigation in troublesome scenarios. However, the new method improves their behavior in open spaces. The performance of this method is illustrated with experimental results obtained with a robotic wheelchair vehicle.

Journal ArticleDOI
TL;DR: It is suggested that children partition obstacle avoidance into two tasks, initially steering with proactive movement of the head and trunk segments and finally making adjustments to their gait trajectory, via stride and step width changes, to ensure adequate obstacle clearance just prior to obstacle crossing.
Abstract: Carrying out the daily activities of work and play requires the ability to integrate available sensory information in order to navigate complex, potentially cluttered, environments The expression of locomotor adjustment behaviour is still maturing during mid- to late-childhood (Grasso et al in Neurosci Biobehav Rev 22(4): 533-539, 1998a; McFadyen et al in Gait Posture 13:7-16, 2001), which raises the question, do children coordinate their body segments differently than adults when circumventing an obstacle in their travel path? Healthy young children (n=5; age 103+/-15 years) and adults (n=6; age 263+/-29 years) were asked to walk at their natural pace during unobstructed walking, as well as during the avoidance to the right or left of a cylindrical obstacle located in the travel path 3 m from the initial starting position Fourteen infrared markers were fixed to participants and tracked using the Optotrak motion analysis system (60 Hz; Northern Digital Inc, Canada) Data analyses included center of mass (COM) clearance from the obstacle, gait speed, angular movement of the head and trunk (yaw, pitch and roll) and medial-lateral (M-L) COM displacement Onset of change in these variables from unobstructed walking was also calculated as the time from OBS crossing Although there were no differences in when adults or children altered their M-L COM trajectory, adults reoriented their head and trunk segments at the same time as their COM while children reoriented their head and trunk prior to changing COM direction A comparison of foot placement data for this task indicated that while adults changed their gait patterns well in advance of obstacle crossing, children initiated M-L adjustments to gait patterns just prior to OBS crossing Vallis and McFadyen (Exp Brain Res 152 (3):409-414, 2003) indicated that during circumvention of an obstacle, adults coordinate body segments for a single transient change in COM trajectory while maintaining the underlying travel direction The present data suggest, however, that children partition obstacle avoidance into two tasks, initially steering with proactive movement of the head and trunk segments and finally making adjustments to their gait trajectory, via stride and step width changes, to ensure adequate obstacle clearance just prior to obstacle crossing This study demonstrates different anticipatory control strategies used by children as compared to adults to circumvent obstacles in the travel path The different head and trunk anticipatory segmental coordination suggests that children gather visual information differently when circumventing an obstacle in their travel path and are more dependent on visual input to guide their circumvention strategy

Patent
08 Dec 2005
TL;DR: A rear obstacle detection and avoidance system for use on a vehicle comprises a rear obstacle detector that is coupled to the vehicle and measures the distance between the vehicle between an obstacle and an obstacle substantially to its rear, a speed sensor that determines vehicle speed, and an alert generator that notifies an occupant of the vehicle of a rear obstruction.
Abstract: A rear obstacle detection and avoidance system for use on a vehicle comprises a rear obstacle detector that is coupled to the vehicle and measures the distance between the vehicle and an obstacle substantially to the vehicle's rear, a speed sensor that determines vehicle speed, an alert generator that notifies an occupant of the vehicle of a rear obstacle, and a processor that is coupled to the rear obstacle detector, the speed sensor, and the alert generator. The processor causes the generation of a first alert when the vehicle's speed is less than a threshold speed and the distance between the vehicle and an obstacle substantially to the vehicle's rear is less than a first distance determined in accordance with a first function of speed vs. distance. Additionally, the processor causes the generation of a second alert when the vehicle's speed is greater than the threshold speed and the distance between the vehicle and an obstacle substantially to the vehicle's rear is less than a second distance determined in accordance with second function of speed vs. distance.

Patent
19 Oct 2005
TL;DR: In this article, a vehicle warning system consisting of an obstacle sensor for detecting an approaching obstacle to a vehicle, tactile information-generating elements for notifying a driver of the obstacle information based on the information of the sensor, and a controller for controlling the actuation of the tactile information generator is presented.
Abstract: The present invention ensures easy identification of an approaching object by the driver, and guides the driver to a destination by a car navigation system by allowing the driver to keep watching ahead. Wherein a warning is not issued if the driver has been aware of an approaching obstacle and that his vehicle is being guided to the destination. (Means of Solving the Problems) A vehicle warning system comprises: an obstacle sensor for detecting approach of an obstacle to a vehicle; tactile information-generating elements for notifying a driver of the obstacle information based on the information of the obstacle sensor; and a controller for controlling the actuation of the tactile information-generating elements. The tactile information-generating elements are installed in a cushion of a driver seat with a fore-and-aft arrangement and/or a left-right arrangement. The controller controls the tactile information-generating elements based on the information from the obstacle sensor and information as to any of a steering wheel-sensor, a winker-sensor, a brake-sensor, and a vehicle-speedometer.

Proceedings ArticleDOI
06 Jun 2005
TL;DR: A model-based algorithm employing only disparity information is demonstrated to be able to segment the whole road surface without knowledge of infrastructures and features like lane markings, which helps navigation in suburban and country-road environments, and recovery from critical failure of lane-markings trackers.
Abstract: This paper presents a method for road detection and obstacle detection entirely based on stereovision. The ground plane is estimated online by least square fitting of disparity data. This operation allows deleting road features for obstacle detection, estimating directly camera roll and pitch, and deriving some clues on road-surface image regions. A model-based algorithm employing only disparity information is demonstrated to be able to segment the whole road surface without knowledge of infrastructures and features like lane markings. This helps navigation in suburban and country-road environments, and recovery from critical failure of lane-markings trackers.

01 Jan 2005
TL;DR: The system aims at increasing the mobility of visually impaired people by offering new sensing abilities by detects the nearest obstacle via a stereoscopic sonar system and sends back vibro-tactile feedback to inform the user about its localization.
Abstract: This paper presents an obstacle detection system for visually impaired people. User can be alerted of closed obstacles in range while traveling in their environment. The system we propose detects the nearest obstacle via a stereoscopic sonar system and sends back vibro-tactile feedback to inform the user about its localization. The system aims at increasing the mobility of visually impaired people by offering new sensing abilities.

01 Jun 2005
TL;DR: JPL has evaluated the performance of seven obstacle detection algorithms on a General Dynamics Robotic Systems surveyed obstacle course containing 21 obstacles and found that 20 of the 21 obstacles were detected, and there were no false obstacle detections.
Abstract: Reliable detection of non-traversable hazards is a key requirement for off-road autonomous navigation. A detailed description of each obstacle detection algorithm and their performance on the surveyed obstacle course is presented in this paper.

Patent
21 Jan 2005
TL;DR: In this paper, a running support system for a vehicle, which supports running of a vehicle by using a radar and image recognition means as obstacle detecting means, and in which appropriate support control based on a result of detection performed by each control means is set.
Abstract: There is provided a running support system for a vehicle, which supports running of a vehicle by using a radar and image recognition means as obstacle detecting means, and in which appropriate support control based on a result of detection performed by each control means is set. A result of obstacle detection performed by a millimeter wave radar (21) is checked against a result of obstacle detection performed by image recognition means (22). Then, a starting condition for the running support control is changed depending on whether an obstacle has been detected by both the millimeter wave radar (21) and the image recognition means (22), or an obstacle has been detected by only one of the millimeter wave radar (21) and the image recognition means (22). Thus, the control support is performed based on an inattentive condition of a driver.


Proceedings ArticleDOI
25 May 2005
TL;DR: Fuzzy logic based approach to path tracking and obstacle avoidance is explored and it is considered that obstacles are either still or moving and appear along the predetermined flight path unexpectedly.
Abstract: This paper addresses the problem of how to make a UAV track a given flight trajectory while at the same time avoid unexpected obstacle(s). If the information about the existence of the obstacle is known in advance, the problem can be readily solved by carefully pre-planning the desired flight path for the vehicle. However, obstacle(s) might appear unexpectedly in practical applications, as such the pre-planned flight path might become "misleading" to the vehicle if no correcting action is taken. Furthermore, obstacles might be of any shape (not necessarily a point mass) and might be either inert or hostile (including seeking a collision). How to avoid unexpected, irregular, even moving obstacles while maintaining close path tracking of UAV is an interesting yet challenging problem. In this paper, we explore fuzzy logic based approach to path tracking and obstacle avoidance. We consider the case that obstacles are either still or moving and appear along the predetermined flight path unexpectedly. By using suitable sensors we identify the relative distance between the vehicle and the obstacle and make timely adjustment to the pre-planned flight path. Fuzzy logic control algorithms are developed to achieve close path tracking while avoiding obstacles. Simulation studies on multiple obstacles with various shapes are conducted and the effectiveness of the proposed method is verified

Patent
02 Mar 2005
TL;DR: In this article, a system and method for assisting a driver operating a vehicle traveling on a road includes a scene recognition device detecting an obstacle in the path of the vehicle, based on a distance (X) to the detected obstacle and a vehicle speed (Vh), a first target discrimination is effected.
Abstract: A system and method for assisting a driver operating a vehicle traveling on a road includes a scene recognition device detecting an obstacle in the path of the vehicle. Based on a distance (X) to the detected obstacle and a vehicle speed (Vh) of the vehicle, a first target discrimination is effected. Based on the distance (X) and a relative vehicle speed (Vr) of the vehicle with respect to the detected obstacle, a second target discrimination is effected. A first reaction force value (FA1, FB1) is determined versus a first risk (RP1) from the detected obstacle upon determination, by the first target discrimination, that the detected obstacle

Proceedings Article
01 Jan 2005
TL;DR: This paper investigates an obstacle detection system that uses optical flow to obtain range in formation to objects and demonstrates that optical flow is capable of pro viding good obstacle information but has obvi ous failure modes.
Abstract: Motion has been examined in biology to be a critical component for obstacle avoidance and navigation. In particular, optical flow is a pow erful motion cue that has been exploited in many biological systems for survival. In this paper, we investigate an obstacle detection sys tem that uses optical flow to obtain range in formation to objects. Our experimental results demonstrate that optical flow is capable of pro viding good obstacle information but has obvi ous failure modes. We acknowledge that our optical flow system has certain disadvantages and cannot be solely used for navigation. In stead, we believe that optical flow is a critical visual subsystem used when moving at reason able speeds. When combined with other visual subsystems, considerable synergy can result.

Proceedings ArticleDOI
18 Jan 2005
TL;DR: This paper focuses on the OARSMT problem and presents an algorithm, named An-OARSMan, based on ant colony optimization, which can handle complex obstacle cases including both convex and concave polygon obstacles with good length performance.
Abstract: Routing is one of the important steps in VLSI/ULSI physical design. The rectilinear Steiner minimum tree (RSMT) construction is an essential part of routing. Since macro cells, IP blocks, and pre-routed nets are often regarded as obstacles in the routing phase, obstacle-avoiding RSMT (OARSMT) algorithms are useful for practical routing applications. This paper focuses on the OARSMT problem and presents an algorithm, named An-OARSMan, based on ant colony optimization. A greedy obstacle penalty distance (OP-distance) local heuristic is used in the algorithm and performed on the track graph. The algorithm has been implemented and tested on different kinds of obstacles. Experimental results show that An-OARSMan can handle complex obstacle cases including both convex and concave polygon obstacles with good length performance. It can always achieve the optimal solution in the cases with no more than 7 terminals.

Journal ArticleDOI
TL;DR: A specialized seismic `echolocation' system could be used by subterranean mammals to determine the most energy-conserving strategy with which to bypass an obstacle, as well as to estimate their distance from the surface, keeping their tunnels at the optimal depth.
Abstract: Subterranean mammals like the blind mole-rat (Rodentia: Spalax ehrenbergi ) are functionally blind and possess poor auditory sensitivity, limited to low-frequency sounds. Nevertheless, the mole-rat demonstrates extremely efficient ability to orient spatially. A previous field study has revealed that the mole-rat can assess the location, size and density of an underground obstacle, and accordingly excavates the most efficient bypass tunnel to detour around the obstacles. In the present study we used a multidisciplinary approach to examine the possibility that the mole-rat estimates the location and physical properties of underground obstacles using reflected self-generated seismic waves (seismic `echolocation'). Our field observations revealed that all the monitored mole-rats produced low-frequency seismic waves (250-300 Hz) at intervals of 8±5 s (range: 1-13 s) between head drums while digging a bypass to detour an obstacle. Using a computerized simulation model we demonstrated that it is possible for the mole-rat to determine its distance from an obstacle boundary (open ditch or stone) by evaluating the amplitude (intensity) of the seismic wave reflected back to it from the obstacle interface. By evaluating the polarity of the reflected wave the mole-rat could distinguish between air space and solid obstacles. Further, the model showed that the diffracted waves from the obstacle's corners could give the mole-rat precise information on the obstacle size and its relative spatial position. In a behavioural experiment using a special T-maze setup, we tested whether the mole-rat can perceive seismic waves through the somatosensory system and localize the source. The results revealed that the mole-rat is able to detect low frequency seismic waves using only its paws, and in most cases the mole-rats determined accurately the direction of the vibratory source. In a histological examination of the glabrous skin of the mole-rat's paws we identified lamellate corpuscle mechanoreceptors that might be used to detect low frequency seismic waves. The combined findings from these different approaches lead us to suggest that a specialized seismic `echolocation' system could be used by subterranean mammals to determine the most energy-conserving strategy with which to bypass an obstacle, as well as to estimate their distance from the surface, keeping their tunnels at the optimal depth.

Journal ArticleDOI
TL;DR: In this paper, an analytical solution for linear long-wave reflection by an obstacle of general trapezoidal shape is explored, which depends on the relative lengths of the two slopes and top of the obstacle as well as the depth ratios in front of and behind the obstacle versus that above the obstacle.
Abstract: In this paper, an analytical solution for linear long-wave reflection by an obstacle of general trapezoidal shape is explored. A closed-form expression in terms of first and second kinds of Bessel functions is obtained for the wave reflection coefficient, which depends on the relative lengths of the two slopes and top of the obstacle as well as the depth ratios in front of and behind the obstacle versus that above the obstacle. The analytical solution obtained in this study finds a few well-known analytical solutions to be its special cases, which include the wave reflection from a rectangular obstacle, an infinite step, and an infinite step behind a linear slope. The present analytical solution, however, covers a much wider range of problems. It is found that the periodicity of the wave reflection coefficient as the function of the relative length of the obstacle remains when two slopes are present but with a reduced magnitude. The phenomenon of zero wave reflection from the structure is special to a rectangular obstacle only, which disappears with the addition of a slope in front or at the rear. The new solution may be very useful in some engineering applications, for example, the design of a submerged breakwater of trapezoidal shape.

Journal ArticleDOI
TL;DR: This paper presents an efficient method to integrate spatial and temporal constraints for detecting and tracking obstacles in urban environments, which does not consider the urban roads as rigid planes, but as quasi-planes, whose normal vectors have orientation constraints.
Abstract: Obstacle detection is an essential capability for the safe guidance of autonomous vehicles, especially in urban environments. This paper presents an efficient method to integrate spatial and temporal constraints for detecting and tracking obstacles in urban environments. In order to enhance the reliability of the obstacle detection task, we do not consider the urban roads as rigid planes, but as quasi-planes, whose normal vectors have orientation constraints. Under this flexible road model, we propose a fast, robust stereovision based obstacle detection method. A watershed transformation is employed for obstacle segmentation in dense traffic conditions, even with partial occlusions, in urban environments. Finally a UKF (Unscented Kalman filter) is applied to estimate the obstacles parameters under a nonlinear observation model. To avoid the difficulty of the computation in metric space, the whole detection process is performed in the disparity image. Various experimental results are presented, showing the advantages of this method.

Journal ArticleDOI
TL;DR: A new approach for trajectory optimization of a mobile robot in a general dynamic environment that combines the static and dynamic modes of trajectory planning to provide an algorithm that gives fast and optimal solutions for static environments, and generates a new path when an unexpected situation occurs.
Abstract: This paper proposes a new approach for trajectory optimization of a mobile robot in a general dynamic environment. The new method combines the static and dynamic modes of trajectory planning to provide an algorithm that gives fast and optimal solutions for static environments, and generates a new path when an unexpected situation occurs. The particularity of the method is in the representation of the static environment in a judicious way facilitating the path planning and reducing the processing time. Moreover, when an unexpected obstacle blocks the robot trajectory, the method uses the robot sensors to detect the obstacle, finds a best way to circumvent it and then resumes its path toward the desired destination. Experimental results showed the effectiveness of the proposed approach.

Proceedings ArticleDOI
25 Jul 2005
TL;DR: The fusion of two-obstacle tracking delivered by two independent systems: track-to-track fusion and extended Kalman filter or particle filters are used, which propose estimates characterizing obstacles positions and relative speeds.
Abstract: In road environment, road obstacle tracking is able to extract important information for driving safety. Indeed, kinematic characteristics estimation (relative position, relative speed, ...) provides a clearer road scene comprehension. This estimate is one of the important parameters of driver assistance systems. However, only one sensor generally does not allow to detect quickly (all the potentially dangerous obstacles) in all the directions, under all the atmospheric conditions. Moreover, the degree of obstacle recognition is different according to the sensor used. Multiplication of sensors makes it possible to face these various problems. Amalgamated information will represent entities in further details and with less uncertainty than with only one source. A system of higher level has been thus developed in order to have a robust management of all tracks and measurements coming from various sensors. This system, applied to radar and lidar measurements combination, gives important obstacles characteristics present in the front bumper of our experimental vehicle (VELAC: LASMEA's experimental vehicle for driving assistance). This state estimate is based on the use of various Bayesian methods (Extended Kalman Filter and Particle Filter). Here we will use the fusion of two-obstacle tracking delivered by two independent systems: track-to-track fusion. These two systems propose estimates characterizing obstacles positions and relative speeds. Fusion estimation is based on the use of extended Kalman filter (EKF) or particle filters. A comparison of these two methods is presented in this article.

Journal ArticleDOI
TL;DR: In this article, an obstacle detection and identification algorithm for an on-tractor laser range finder-based obstacle detector was presented. But the accuracy of this algorithm was limited to 0.052 m, 0.11 m, and 1.2 degrees, respectively.
Abstract: The capability of detecting and identifying obstacles on the expected path and taking appropriate collision avoidance actions automatically is critical for safe operation of autonomous agricultural vehicles. This article presents an obstacle detection and identification algorithm for an on-tractor laser range finder-based obstacle detector. This algorithm consists of a template matching function and a Kalman filter for detecting the location of an obstacle, reconstructing the silhouette of the detected obstacle, and estimating its relative motions. Field validation test results verified that this obstacle detector was capable of detecting a moving object within a semicircle of 8 m radius and reconstructing a 2D silhouette of the obstacle progressively in real time. The errors of this obstacle detector in estimating the position, speed, and moving direction of the obstacle relative to the tractor were 0.052 m, 0.11 m / s, and 1.2 degrees, respectively. Such accuracies are sufficient for providing safety warning and collision avoidance for autonomous tractors in field operation.

Proceedings ArticleDOI
15 Aug 2005
TL;DR: This paper describes a 3D obstacle modeling system which uses a 2D vision sensor for obstacle detection and describes the estimator design based on line information, instead of points, which uses more structural information than the point-based estimator to create an obstacle model.
Abstract: This paper describes a 3D obstacle modeling system which uses a 2D vision sensor. Prior work tracks feature points in a sequence of images and estimates their positions. However, in this paper we use obstacle edges instead. Using an image segmentation technique, edges are detected as line segments. Subsequently, these edges are modeled in a 3D space from the measured line segments using known camera motions. The z-test method is used for corresponding estimated line data with measurements. Line addition and deletion algorithms are also explained. Simulation results show that simple structures are accurately modeled by the suggested line-based estimator. Finally, this method is applied to a 3D terrain mapping problem. I. Introduction Unmanned aerial vehicles (UAVs) play an important role in military operations and have significant potential for commercial applications. UAVs are expected to operate in dangerous areas, such disaster site or enemy territory, and they can provide realtime information to the user. Various problems in UAV automation are still under investigation. One of these is obstacle detection and avoidance. If a vehicle operates in close proximity to unknown terrain or structures, its navigation system has to automatically detect obstacles and its guidance and control systems must avoid collisions with them. For obstacle detection, it is ideal to obtain 3D site mapping data of the terrain over which the UAV flies. Laser rangefinders can provide very accurate environmental data, 1 however, they are too large and heavy to install on small UAVs. Moreover, they are very expensive. Thus, a single 2D camera is chosen as a sensor for obstacle detection. It is reasonable to use a camera because they are low cost and meet the size and weight constraints of most small UAVs. Furthermore, a camera can be used to obtain sufficient information of the vehicles unknown operational environment in realtime. This paper considers the design of a 3D site modeling system using a single 2D camera. In some studies, vision-based terrain modeling is achieved by tracking many feature points in a sequence of images and updating estimates of their actual 3D positions 2 . 3 Unlike these studies, this paper describes the estimator design based on line information, instead of points. In general, edges of obstacles may appear as curved lines of finite length in an image. In particular, most artificial structures such as buildings have straight edges which appear as a set of straight line segments in an image. Therefore, our objective is to estimate actual obstacle edge lines from the line segments which are detected in an image through an image segmentation technique, and to create a 3D model of the obstacles. It is notable that the line-based estimator uses more structural information (points and their connectivity) than the point-based estimator to create an obstacle model. First, every line segment in a given measurement set is matched with estimated line data. The statistical z-test value is introduced to perform this correspondence. 4 The z-test value is taken for a certain error index. Then the z-test value is inversely related to the likelihood of an event that a given measurement corresponds to the line data chosen. When using the z-test, both estimation error and measurement error covariances are taken in account. For each measurement, the z-test value is calculated and a line which attains the least value is chosen. After a line is assigned, an extended Kalman filter (EKF) is applied to update the two endpoint positions for each line from the residuals of the two endpoints of the measured line segment