Showing papers on "Obstacle published in 2004"

Inevitable collision states - a step towards safer robots?

Abstract: An inevitable collision state for a robotic system can be defined as a state for which, no matter what the future trajectory followed by the system is, a collision with an obstacle eventually occurs. An inevitable collision state takes into account the dynamics of both the system and the obstacles, fixed or moving. The main contribution of this paper is to lay down and explore this novel concept (and the companion concept of inevitable collision obstacle). Formal definitions of the inevitable collision states and obstacles are given. Properties fundamental for their characterization are established. This concept is very general, and can be useful both for navigation and motion planning purposes (for its own safety, a robotic system should never find itself in an inevitable collision state). To illustrate the interest of this concept, it is applied to a problem of safe motion planning for a robotic system subject to sensing constraints in a partially known environment (i.e. that may contain unexpected obst...

The effects of distant and on-line visual information on the control of approach phase and step over an obstacle during locomotion

Abstract: One of the goals of this study was to examine the nature and role of distant visual information sampled during locomotion in the feedforward control of leading and trailing limb while an individual is required to step over an obstacle in the travel path. In addition we were interested in whether or not on-line visual information available while the limb (lead or trail) is stepping over the obstacle influences limb trajectory control and whether the information provided during lead limb cross would be used to calibrate movement of the trail limb. Towards this end, we manipulated availability of vision following an initial dynamic sampling period during the approach phase in proximity to the obstacle and during the lead and trail limb stepping over the obstacle. Ten participants completed 40 trials of obstacle crossing in 8 testing conditions. Initial dynamic visual sampling was sufficient to ensure successful task performance in the absence of vision in the approach phase and during both lead and trail limb stepping over the obstacle. Despite successful task performance, foot placement of the lead and trail limb before obstacle crossing and limb elevation over the obstacle were increased after withdrawal of vision in the approach area. Furthermore, the correlation between toe clearance and foot placement was diminished. While both limbs require feedforward visual information to control the step over the obstacle, only lead limb elevation was influenced by availability of on-line visual information during obstacle crossing. Results were in agreement with the notion of primacy of information inherent in the optic array over those from static samples of the environment in guiding locomotion. It is suggested that the expected proprioceptive feedback information associated with the limb posture before the obstacle, reconstructed using visual memory from dynamic sampling of the environment, mismatched with those from the actual limb position. Accordingly, participants adopted a different strategy that enabled them to clear the obstacle with a higher safety margin.

Obstacle avoidance and path planning for humanoid robots using stereo vision

Abstract: This work presents methods for path planning and obstacle avoidance for the humanoid robot QRIO, allowing the robot to autonomously walk around in a home environment. For an autonomous robot, obstacle detection and localization as well as representing them in a map are crucial tasks for the success of the robot. Our approach is based on plane extraction from data captured by a stereo-vision system that has been developed specifically for QRIO. We briefly overview the general software architecture composed of perception, short and long term memory, behavior control, and motion control, and emphasize on our methods for obstacle detection by plane extraction, occupancy grid mapping, and path planning. Experimental results complete the description of our system.

Obstacle avoidance for kinematically redundant manipulators using a dual neural network

Abstract: One important issue in the motion planning and control of kinematically redundant manipulators is the obstacle avoidance. In this paper, a recurrent neural network is developed and applied for kinematic control of redundant manipulators with obstacle avoidance capability. An improved problem formulation is proposed in the sense that the collision-avoidance requirement is represented by dynamically-updated inequality constraints. In addition, physical constraints such as joint physical limits are also incorporated directly into the formulation. Based on the improved problem formulation, a dual neural network is developed for the online solution to collision-free inverse kinematics problem. The neural network is simulated for motion control of the PA10 robot arm in the presence of point and window-shaped obstacle.

High accuracy stereo vision system for far distance obstacle detection

Abstract: This paper presents a high accuracy stereo vision system for obstacle detection and vehicle environment perception in a large variety of traffic scenarios, from highway to urban. The system detects obstacles of all types, even at high distance, outputting them as a list of cuboids having a position in 3D coordinates, size and speed.

Information providing device for vehicle

Abstract: PROBLEM TO BE SOLVED: To perform a driving support of further high level even in a complicated traffic environment such as an intersection or T-shaped intersection. SOLUTION: The traveling state of an own vehicle is detected (steps S1 and S2), and forward obstacle data detected by an obstacle sensor 3, approaching vehicle information acquired from infrastructure facilities arranged in a traveling road by a road-to-vehicle radio device 4, traveling information of vehicles in a vehicle-to-vehicle communication destination, acquired by a vehicle-to-vehicle radio device 5, and the like are read (steps S3 to S5). With respect each detection means of the obstacle sensor 3, the road-to-vehicle radio 4 and the vehicle-to-vehicle radio 5, the sum of a multi-level showing the number of detection means in detection of the same object by different detection means and the reliability set to the detection means which is detecting an object is determined, and a total reliability is determined based on the resulting reliability (step S6). As higher reliability is predicted from the total reliability, driving support of higher level is performed. COPYRIGHT: (C)2006,JPO&NCIPI

Trajectory Planning for Autonomous Aerospace Vehicles amid Known Obstacles and Conflicts

Abstract: A discrete search strategy is presented for potential real-time generations of four-dimensional trajectories for a single autonomous aerospace vehicle amid known obstacles and conflicts. A model of autonomous operation isfirst developed. The problem of and requirements on real-time trajectory generations for autonomous aerospace vehicles are discussed. After an overview of various potential solution frameworks, a discrete search strategy is developed. In this strategy, a four-dimensional search space is defined and discretized. Potential obstacles and conflicts are represented by several basic geometric shapes and their combinations. Mathematical conditions are developed for a trajectory segment to be outside of an obstacle or conflict. Then, the A* search technique is used to obtain trajectory solutions, in which successor points are selected that avoid obstacles and conflicts and that satisfy dynamic motion constraints of the vehicle. A linear combination of flight distance and flight time is optimized in the trajectory generation process. A heuristic function that approximates this performance index is developed for the A * search procedure. Examples are provided that illustrate the application of the proposed method.

Reflective navigation: individual behaviors and group behaviors

Abstract: An approach to motion planning among moving obstacles is presented, whereby obstacles are modeled as intelligent decision-making agents. The decision-making processes of the obstacles are assumed to be similar to that of the mobile robot. A probabilistic extension to the velocity obstacle approach is used as a means for navigation and modeling uncertainty about the moving obstacles' decisions.

Obstacle detection using stereo vision

Abstract: A system and method for detecting an obstacle comprises determining a vegetation height of a vegetation canopy at corresponding coordinates within a field. An object height is detected, where the object height of an object exceeds the vegetation height. A range of the object is estimated. The range of the object may be references to a vehicle location, a reference location, or absolute coordinates. Dimensions associated with the object are estimated. An obstacle avoidance zone is established for the vehicle based on the estimated range and dimensions.

Self-propelled working robot

Abstract: A self-propelled working robot having a first distance sensor (4a) for measuring the distance to an obstacle (W) ahead and a second distance sensor (4b(4c)) for measuring the distance to the obstacle (W) diagonally ahead. The working robot has first determining means, second determining means, and changing means. The first determining means determines approach of the obstacle (W) by comparing a first measured distance (Dc) to the obstacle measured by the first distance sensor (4a) and a predetermined first threshold value. The second determining means determines approach of the obstacle by comparing a second measure distance (Dr (DL)) to the obstacle (W) measured by the second distance sensor (4b (4c)) and a predetermined second threshold value. The changing means changes the first or the second threshold value based on information on an inclination angle of the obstacle (W) obtained from the first and the second distance.

Stereovision approach for obstacle detection on non-planar roads

Abstract: This paper presents a high accuracy stereovision system for obstacle detection and vehicle environment perception in various driving scenarios. The system detects obstacles of all types, even at high distance, outputting them as a list of cuboids having a position in 3D coordinates, size, speed and orientation. For increasing the robustness of the obstacle detection the non-planar road model is considered. The stereovision approach was considered to solve the road-obstacle separation problem. The vertical profile of the road is obtained by fitting a first order clothoid curve on the stereo detected 3D road surface points. The obtained vertical profile is used for a better road-obstacle separation process. By consequence the grouping of the 3D points above the road in relevant objects is enhanced, and the accuracy of their positioning in the driving environment is increased.

High Accuracy Stereovision Approach for Obstacle Detection on Non-Planar Roads

Abstract: This paper will present an obstacle detection system that that relies on the 3D information provided by stereo reconstruction. The 3D features must be separated in road features and obstacle features. Instead of relying on the flatness of the road, the vertical road profile is modeled as a clothoid, and is estimated from the lateral projection of the 3D points. The points above the road are selected for grouping into objects, based on vicinity criteria and the variation of the point density with the distance. The resulted objects are used as measurements for a model-based tracking algorithm. The resulted system is a high-accuracy, far distance obstacle detector, able to function in a large variety of real-world scenarios.

Trapped waves between submerged obstacles

Abstract: Free-surface flows past submerged obstacles in a channel are considered The fluid is assumed to be inviscid and incompressible and the flow to be irrotational In previous work involving a single obstacle (Dias & Vanden-Broeck 2002), new solutions called ‘generalized hydraulic falls’ were found These solutions are characterized by a supercritical flow on one side of the obstacle and a train of waves on the other However, in the case of a single submerged object, the generalized hydraulic falls are unphysical because the waves do not satisfy the radiation condition In this paper new solutions for the flow past two obstacles of arbitrary shape are computed These solutions are characterized by a train of waves ‘trapped’ between the obstacles The generalized hydraulic falls are shown to describe locally the flow over one of the two obstacles when the distance between the two obstacles is large

Pedestrian navigation and spatial relation device

Abstract: A pedestrian navigation and spatial relation device including a position finder, a spatial relationship sensor, an input mechanism, and an output mechanism. The position finder can be configured to determine a geographic position of the device based upon received wireless signals. The spatial relationship sensor can provide data used to detect a position of at least one obstacle relative to the device. The input mechanism can specify a destination location. The output mechanism can present device output to a user. The device output can include sensory indicators for at least one of guiding a pedestrian to the destination location and warning a pedestrian about the detected obstacles.

Obstacle detection device

Abstract: An obstacle detection device includes: an obstacle detection section (11) for successively emitting a beam having a predetermined spread angle to a plurality of different directions and receiving a reflected wave from an obstacle in each of the directions, thereby detecting an obstacle existing in the beam emission angle range of each direction; a distance calculation section (12) for calculating a value representing a distance between an obstacle in each direction and an automobile having the obstacle detection device according to the reception signal of reflected wave in each direction output from the obstacle detection section; an obstacle image creation section (14) for treating the distance for each direction calculated by the distance calculation section, as an image creation reference, thereby creating as an obstacle image a graphic spread in two-dimensional way in the emission angle range of the beam emitted in each direction, and creating and outputting image data for displaying the obstacle image; and a display section (15) for receiving image data created by the obstacle image creation section and displaying an image showing the positional relationship between the obstacle and the automobile.

What is Climate Change

Abstract: Incompatibility between the definitions used by science and policy organizations is an obstacle to effective action.

Collision avoidance involving radar feedback

Abstract: Collision avoidance systems and methods are implemented on unmanned mobile vehicles to supplement map-based trajectories generated by the vehicles' navigation systems. These systems include radar, which detect obstacles in the path of the unmanned mobile vehicles, and collision avoidance modules, which enable the vehicles to avoid unexpected obstacles by adjusting their trajectories and velocities based on feedback received from the radar. In general, when an obstacle is detected by the radar, the collision avoidance module modifies the commanded velocity of an unmanned mobile vehicle by subtracting from the nominal commanded velocity the component that is in the direction of the obstacle. The magnitude of the velocity modification typically increases as the distance between the mobile vehicle and the obstacle decreases.

Autonomously moving robot

Abstract: An autonomously moving robot (1) has environment information acquisition means (6) for recognizing an obstacle and self-position so that it can move while evading the obstacle. The environment information acquisition means (6) includes: an image pickup device (71) for picking up an image of an environment on the movement route; image recognition processing means (72) for calculation-processing the picked up image and extracting an area having an attribute associated with a human body part; a distance measurement device (81) for measuring a distance up to an object existing in the environment on the movement route and its direction; distance information analysis means (82) for calculation-processing the distance information obtained so as to determine the object shape and recognizing that the object is a person candidate from the shape; and environment recognition means (9) for recognizing the environment information on the movement route. This environment recognition means (9) compares the direction of the area having the attribute extracted by the image recognition processing means (72) with the direction of the object recognized as a person candidate by the distance information analysis means (82) and if the directions are matched, the obstacle is recognized as a person. Thus, the autonomously moving robot judges what is an obstacle and moves smoothly and safely according to the obstacle.

Embedded free flight obstacle avoidance system

Abstract: A free flight obstacle avoidance system (OAS) (60) is a commanded obstacle resolution feedback system. The system employs insertion of hybridized elements to the existing designs of Adaptive Ground Collision Avoidance Systems and Midair Collision Avoidance Systems along with a newly design module, the obstacle avoidance dispatcher and resolver (65), to provide a coherent obstacle resolution. The system is capable of filtering data produced by the hybrid ground collision avoidance module (66) and the hybrid air collision avoidance module (67), inserting evaluating solution status and command directives before routing avoidance data to hybrid modules for validation. The dispatcher and resolver module (65) determines the final obstacle resolution (203) to generate avoidance control guidance (216) and appropriate warnings (217) clearly indicated obstacle situation and obstacle avoidance maneuvers (218) to the flight crew. In addition to the avoidance capabilities, the system also provides extended functions of terrain following guidance (308) and space separation warnings (210).

Self-propelled working robot having horizontally movable work assembly retracting in different speed based on contact sensor input on the assembly

Abstract: The present invention relates to a self-propelled working robot, including a first distance sensor 4 a and a second distance sensor 4 b ( 4 c ) for measuring the distance to an obstacle W in front of the robot. The robot includes first determination means for comparing a first measured distance Dc to the obstacle obtained by the first distance sensor 4 a with a predetermined first threshold value to determine the proximity to the obstacle W, second determination means for comparing a second measured distance Dr (D L ) to the obstacle W obtained by the second distance sensor 4 b ( 4 c ) with a predetermined second threshold value to determine the proximity to the obstacle, and changing means for changing the first or second threshold value based on information regarding an inclination angle of the obstacle W obtained from the first and second measured distances.

Obstacle detection in a road scene based on motion analysis

Abstract: This paper deals with the problem of obstacle detection in traffic applications. The proposed device allows a driver to receive the current road and vehicle environment information. The perception of the environment is performed through a fast processing of image sequences acquired from a single camera mounted on a vehicle. This approach is based on frame motion analysis. The road motion is first computed through a fast and robust wavelets analysis. Finally, we detect the areas that have a different motion thanks to a Bayesian modelization. Results shown in this paper prove that the proposed method permits the detection of any obstacle on all type of road in various image conditions.

Centralized data fusion for obstacle and road borders tracking in a collision warning system

Abstract: The proposed system, so-called EUCLIDE, is a collision warning and vision enhancement system merging the functionality of a far infrared and mmw radar sensor in order to warn the driver in case of lack of obstacle perception in adverse weather conditions. A centralized fusion scheme is adopted for obstacle and road tracking. A Kalman based curvelinear model predicts drivers’ behaviour and thus, the system is able to assess the level of threat for all moving obstacles and decide the warning policy. The system development is done in parallel with a proper design of the human machine interaction (head-up display) to bridge ‘system functionality’ to driver’s ‘enhanced perception’. The system has been tested with real data and results are presented in the paper and show the performance of the tracking system.

Vehicle traveling control device

Abstract: A control device sets avoidance traveling reaching points, avoidance traveling target points, and a final avoidance target point of an obstacle to be avoided based on the position of the obstacle to be avoided and the position of the vehicle for the target passing position based on obstacle information recognized by a stereo camera, and an environment recognition unit, inputs the target actual steering angle as a vehicle motion parameter obtained according to a vehicle motion model to an electric power steering control device with these target passing positions as a target, and guides the avoidance traveling. The increase of the number of operations is controlled thereby to a minimum, and the obstacle is smoothly, efficiently and stably avoided based on actual behavior of the vehicle.

Vehicle obstacle detecting device

Abstract: The vehicle obstacle detecting device improves safety of the vehicle by utilizing information detected by a plurality of sensors to appropriately handle situations in which an obstacle exists in a blind spot of the sensors. The vehicle obstacle detecting device includes at least first and second sensors arranged such that sensing scopes of the first and second sensors do not substantially overlap. The vehicle obstacle detecting device is configured to observe the behavior of an obstacle existing within the sensing scope of one of the first and second sensors and predict the blind spot behavior of the obstacle in a blind spot between the sensing scopes of the first and second sensors based on the observed behavior of the obstacle. Thus, the vehicle obstacle detecting device is configured to predict the existence of an obstacle in the blind spot where the first and second sensors cannot actually detect the obstacle.

Colliding obstacle detection apparatus for vehicle

Abstract: The present colliding obstacle detection apparatus comprises a pedestrian bumper, which is supported below a front bumper of the vehicle by a body of the vehicle, at least one collision detector, which is located on the pedestrian bumper, and a control circuit, which determines whether the collision has actually occurred based on a detection signal outputted by the at least one collision detector. The front end of the pedestrian bumper vertically aligns with or extending ahead of that of the front bumper. The at least one collision detector detects one of a collision of the pedestrian bumper with an obstacle, and a presence of the obstacle in a close proximity to the pedestrian bumper. When the control circuit determines that the collision has actually occurred, the circuit activates a colliding obstacle protector for protecting the obstacle, especially a pedestrian.

Obstacle recognition device

Abstract: PROBLEM TO BE SOLVED: To provide an obstacle recognition device capable of reducing false detection further and recognizing the obstacle. SOLUTION: A drive assist system 1 consists of an ECU10, and the ECU10 is equipped with a navigation system 12 and an object detection part 100 to which a forward millimeter-wave radar 30, and the like, is connected. A travelling lane recognition part 110 recognizes the travelling lane where its own vehicle is traveling from a measurement result of the navigation system 12 and decides a possibility in which other vehicles exist in either side of the own vehicle, when the traveling lane recognition part 110 decides that there are no possibilities in which other vehicles exist at the either side of the own vehicle, a radar wave detection part 102 extracts the object as the obstacle when reflectance of the forward millimeter-wave radar 30 and a short range millimeter-wave radar 32 are not less than a second threshold value which is higher than a usual first threshold value with respect to the side concerned. Consequently, the possibility of the falsely detecting the roadside objects, such as a guardrail and a side wall as the vehicles, is reduced, the false detection is further lessened and the obstacle can be recognized. COPYRIGHT: (C)2008,JPO&INPIT

Rapid Human-Assisted Creation of Bounding Models for Obstacle Avoidance in Construction

Abstract: State-of-the-art construction equipment control technology creates the opportunity to implement automated and semiautomated object avoidance for improved safety and efficiency during operation; however, methods for constructing models of local objects or volumes in real-time are required. A practical, interactive method for doing so is described here. The method: (1) exploits a human operator's ability to quickly recognize significant objects or clusters of objects in a scene, (2) exploits the operator's ability to acquire sparse range point clouds of the objects quickly, and then (3) renders models, such as planes, boxes, and generalized convex hulls, to be displayed graphically as visual feedback during equipment operation and/or for making proximity calculations in an obstacle detection system. Experiments were performed in which test subjects were asked to model objects of varying complexity and clutter. These models were then compared to control models using a ray-tracing algorithm to determine the operator's ability to create conservative models that are critical to construction operations. To demonstrate the applicability of the modeling method to obstacle avoidance, a scripted motion robot simulation was conducted using an artificial potential formulation that monitors position (closest point on manipulator link to nearest obstacle) as well as velocity (link inertia). Experimental results indicate that bounding models can be created rapidly and with sufficient accuracy for obstacle avoidance with the aid of human intelligence and that human-assisted modeling can be very beneficial for real-time construction equipment control.

Vehicle driving assist system

Abstract: In a vehicle driving assist system, an external environment recognition unit detects a 3-D obstacle inhibiting the driving direction of the vehicle based on an image captured by a stereo camera and determines whether the image ahead of the vehicle is in a condition that makes visual perception of the 3-D obstacle difficult. A controller calculates a required alarm working distance between the vehicle and the 3D obstacle, at which an alarm unit is worked when the vehicle approaches the 3D obstacle, and a required brake operating distance, at which a brake is operated by a brake applying unit, based on a vehicle traveling speed. If it is determined that an external environment is in a condition that makes visual perception difficult, the required working and operating distances are extended by predetermined values to set the working and operating timings earlier.

Automatically running wheelchair, wheelchair automatical running system, and wheechair automatical running method

Abstract: There is provided an automatically running wheelchair whose running is managed by a host computer and which automatically runs up to a destination along a guide path managed by the host computer The automatically running wheelchair includes: destination input means for inputting destination information; guide path route information acquisition means for calculating the guide path route information in accordance with the start point and the destination information by the automatically running wheelchair itself or acquiring the route information calculated by the host computer; obstacle detection means for detecting an obstacle on the guide path; and obstacle evading means for performing a predetermined obstacle evasion operation in accordance with the type of the obstacle