Showing papers on "Obstacle avoidance published in 2008"

MPC-based yaw and lateral stabilisation via active front steering and braking

Abstract: In this paper we propose a path following Model Predictive Control-based (MPC) scheme utilizing steering and braking. The control objective is to track a desired path for obstacle avoidance maneuver, by a combined use of braking and steering. The proposed control scheme relies on the Nonlinear MPC (NMPC) formulation we used in [1] and [2]. In this work, the NMPC formulation will be used in order to derive two different approaches. The first relies on a full tenth order vehicle model and has high computational burden. The second approach is based on a simplified bicycle model and has a lower computational complexity compared to the first. The effectiveness of the proposed approaches is demonstrated through simulations and experiments.

Movement reproduction and obstacle avoidance with dynamic movement primitives and potential fields

Abstract: Robots in a human environment need to be compliant. This compliance requires that a preplanned movement can be adapted to an obstacle that may be moving or appearing unexpectedly. Here, we present a general framework for movement generation and mid-flight adaptation to obstacles. For robust motion generation, Ijspeert et al developed the framework of dynamic movement primitives which represent a demonstrated movement with a set of differential equations. These equations allow adding a perturbing force without sacrificing stability of the desired movement. We extend this framework such that arbitrary movements in end-effector space can be represented - which was not possible before. Furthermore, we include obstacle avoidance by adding to the equations of motion a repellent force - a gradient of a potential field centered around the obstacle. In addition, this article compares different potential fields and shows how to avoid obstacle-link collisions within this framework. We demonstrate the abilities of our approach in simulations and with an anthropomorphic robot arm.

3D path planning and stereo-based obstacle avoidance for rotorcraft UAVs

Abstract: We present a synthesis of techniques for rotorcraft UAV navigation through unknown environments which may contain obstacles. D* Lite and probabilistic roadmaps are combined for path planning, together with stereo vision for obstacle detection and dynamic path updating. A 3D occupancy map is used to represent the environment, and is updated online using stereo data. The target application is autonomous helicopter-based structure inspections, which require the UAV to fly safely close to the structures it is inspecting. Results are presented from simulation and with real flight hardware mounted onboard a cable array robot, demonstrating successful navigation through unknown environments containing obstacles.

Multimodal Approach to Human-Face Detection and Tracking

Abstract: The constructive need for robots to coexist with humans requires human-machine interaction. It is a challenge to operate these robots in such dynamic environments, which requires continuous decision-making and environment-attribute update in real-time. An autonomous robot guide is well suitable in places such as museums, libraries, schools, hospital, etc. This paper addresses a scenario where a robot tracks and follows a human. A neural network is utilized to learn the skin and nonskin colors. The skin-color probability map is utilized for skin classification and morphology-based preprocessing. Heuristic rule is used for face-ratio analysis and Bayesian cost analysis for label classification. A face-detection module, based on a 2D color model in the and YUV color space, is selected over the traditional skin-color model in a 3D color space. A modified continuously adaptive mean shift tracking mechanism in a 1D hue, saturation, and value color space is developed and implemented onto the mobile robot. In addition to the visual cues, the tracking process considers 16 sonar scan and tactile sensor readings from the robot to generate a robust measure of the person's distance from the robot. The robot thus decides an appropriate action, namely, to follow the human subject and perform obstacle avoidance. The proposed approach is orientation invariant under varying lighting conditions and invariant to natural transformations such as translation, rotation, and scaling. Such a multimodal solution is effective for face detection and tracking.

Autonomous Robots: Modeling, Path Planning, and Control

Abstract: This book covers the kinematics and dynamic modeling/ analysis of autonomous robots as well as methods suitable for their control Specifi c topics include the ap plication of autonomous robots, obstacle avoidance in two- and threedimensional workspaces using potential fi eld methods, kinematic and dynamic models of autonomous robots, and control methods such as PID, feedback linearization, and sliding modes The targeted audience is fiundergraduate and fi rst-year graduate students as well as practicing mechanical and electrical engineers

Driving with tentacles: Integral structures for sensing and motion

Abstract: In this paper we describe a LIDAR-based navigation approach applied at both the C-Elrob (European Land Robot Trial) 2007 and the 2007 DARPA Urban Challenge. At the C-Elrob 2007 the approach was used without any prior knowledge about the terrain and without global positioning system (GPS). At the Urban Challenge the approach was combined with a GPS-based path follower. At the core of the method is a set of “tentacles” that represent precalculated trajectories defined in the ego-centered coordinate space of the vehicle. Similar to an insect's antennae or feelers, they fan out with different curvatures discretizing the basic driving options of the vehicle. We detail how the approach can be used for exploration of unknown environments and how it can be extended to combined GPS path following and obstacle avoidance allowing safe road following in case of GPS offsets. © 2008 Wiley Periodicals, Inc.

Detection, prediction, and avoidance of dynamic obstacles in urban environments

Abstract: We present an approach for robust detection, prediction, and avoidance of dynamic obstacles in urban environments. After detecting a dynamic obstacle, our approach exploits structure in the environment where possible to generate a set of likely hypotheses for the future behavior of the obstacle and efficiently incorporates these hypotheses into the planning process to produce safe actions. The techniques presented are very general and can be used with a wide range of sensors and planning algorithms. We present results from an implementation on an autonomous passenger vehicle that has traveled thousands of miles in populated urban environments and won first place in the DARPA Urban Challenge.

Real-Time Adaptive Motion Planning (RAMP) of Mobile Manipulators in Dynamic Environments With Unforeseen Changes

Abstract: This paper introduces a novel and general real-time adaptive motion planning (RAMP) approach suitable for planning trajectories of high-DOF or redundant robots, such as mobile manipulators, in dynamic environments with moving obstacles of unknown trajectories. The RAMP approach enables simultaneous path and trajectory planning and simultaneous planning and execution of motion in real time. It facilitates real-time optimization of trajectories under various optimization criteria, such as minimizing energy and time and maximizing manipulability. It also accommodates partially specified task goals of robots easily. The approach exploits redundancy in redundant robots (such as locomotion versus manipulation in a mobile manipulator) through loose coupling of robot configuration variables to best achieve obstacle avoidance and optimization objectives. The RAMP approach has been implemented and tested in simulation over a diverse set of task environments, including environments with multiple mobile manipulators. The results (and also the accompanying video) show that the RAMP planner, with its high efficiency and flexibility, not only handles a single mobile manipulator well in dynamic environments with various obstacles of unknown motions in addition to static obstacles, but can also readily and effectively plan motions for each mobile manipulator in an environment shared by multiple mobile manipulators and other moving obstacles.

A low-cost laser distance sensor

Abstract: Many indoor robotics systems use laser rangeflnders as their primary sensor for mapping, localization, and obstacle avoidance. The cost and power of such systems is a major roadblock to the deployment of low-cost, efficient consumer robot platforms for home use. In this paper, we describe a compact, planar laser distance sensor (LDS) that has capabilities comparable to current laser scanners: 3 cm accuracy out to 6 m, 10 Hz acquisition, and 1 degree resolution over a full 360 degree scan. The build cost of this device, using COTS electronics and custom mechanical tooling, is under $30.

Collision and conflict avoidance system for autonomous unmanned air vehicles (UAVs)

Abstract: A collision and conflict avoidance system for autonomous unmanned air vehicles (UAVs) uses accessible on-board sensors to generate an image of the surrounding airspace. The situation thus established is analyzed for imminent conflicts (collisions, TCAS violations, airspace violations), and, if a probable conflict or collision is detected, a search for avoidance options is started, wherein the avoidance routes as far as possible comply with statutory air traffic regulations. By virtue of the on-board algorithm the system functions independently of a data link. By taking into account the TCAS zones, the remaining air traffic is not disturbed unnecessarily. The system makes it possible both to cover aspects critical for safety and to use more highly developed algorithms in order to take complicated boundary conditions into account when determining the avoidance course.

Optimal Control of Underactuated Nonholonomic Mechanical Systems

Abstract: In this paper, we use an affine connection formulation to study an optimal control problem for a class of nonholonomic, underactuated mechanical systems. In particular, we aim to minimize the norm-squared of the control input to move the system from an initial to a terminal state. We consider systems evolving on general manifolds. The class of nonholonomic systems we study in this paper includes, in particular, wheeled-type vehicles, which are important for many robotic locomotion systems. The two special aspects of this optimal control problem are the nonholonomic constraints and underactuation. Nonholonomic constraints restrict the evolution of the system to a distribution on the manifold. The nonholonomic connection is used to express the constrained equations of motion. Many robotic systems are underactuated since control inputs are usually applied through the robot's internal configuration space only. While we do not consider symmetries with respect to group actions in this paper, the fact that the system is underactuated is taken into account in our problem formulation. This allows one to compute reaction forces due to any inputs applied in directions orthogonal to the constraint distribution. We illustrate our ideas by considering a simple example on a three-dimensional manifold, including obstacle avoidance using the method of navigation functions.

Team Cornell's Skynet: Robust perception and planning in an urban environment

Abstract: Team Cornell's Skynet is an autonomous Chevrolet Tahoe built to compete in the 2007 DARPA Urban Challenge. Skynet consists of many unique subsystems, including actuation and power distribution designed in-house, a tightly coupled attitude and position estimator, a novel obstacle detection and tracking system, a system for augmenting position estimates with vision-based detection algorithms, a path planner based on physical vehicle constraints and a nonlinear optimization routine, and a state-based reasoning agent for obeying traffic laws. This paper describes these subsystems in detail before discussing the system's overall performance in the National Qualifying Event and the Urban Challenge. Logged data recorded at the National Qualifying Event and the Urban Challenge are presented and used to analyze the system's performance. © 2008 Wiley Periodicals, Inc.

Directional Associative Markov Network for 3-D Point Cloud Classification

Abstract: In this paper we address the problem of automated three dimensional point cloud interpretation. This problem is important for various tasks from environment modeling to obstacle avoidance for autonomous robot navigation. In addition to locally extracted features, classifiers need to utilize contextual information in order to perform well. A popular approach to account for context is to utilize the Markov Random Field framework. One recent variant that has successfully been used for the problem considered is the Associative Markov Network (AMN). We extend the AMN model to learn directionality in the clique potentials, resulting in a new anisotropic model that can be efficiently learned using the subgradient method. We validate the proposed approach using data collected from different range sensors and show better performance against standard AMN and Support Vector Machine algorithms.

Harmonic potential field path planning for high speed vehicles

Abstract: This paper presents a method to represent complex shaped obstacles in harmonic potential fields used for vehicle path planning. The proposed method involves calculating the potential field for a series of circular obstacles inserted into the unobstructed potential field. The potential field for the total obstacle is a weighted average of the circular obstacle potential fields. This method explicitly calculates a stream function for the potential field. The need for the stream function is explained for situations involving controlling a dynamic system such as a high speed ground vehicle. The traditional potential field controller is also augmented to take the stream function into account. Simulation results are presented to show the effectiveness of the potential field generation technique and the augmented vehicle controller.

A vision-based autopilot for a miniature air vehicle: joint speed control and lateral obstacle avoidance

Abstract: In our project on the autonomous guidance of Micro-Air Vehicles (MAVs) in confined indoor and outdoor environments, we have developed a vision based autopilot, with which a miniature hovercraft travels along a corridor by automatically controlling both its speed and its clearance from the walls. A hovercraft is an air vehicle endowed with natural roll and pitch stabilization characteristics, in which planar flight control systems can be developed conveniently. Our hovercraft is fully actuated by two rear and two lateral thrusters. It travels at a constant altitude (~2 mm) and senses the environment by means of two lateral eyes that measure the right and left optic flows (OFs). The visuo-motor control system, which is called LORA III (Lateral Optic flow Regulation Autopilot, Mark III), is a dual OF regulator consisting of two intertwined feedback loops, each of which has its own OF set-point and controls the vehicle's translation in one degree of freedom (surge or sway). Our computer-simulated experiments show that the hovercraft can navigate along a straight or tapered corridor at a relatively high speed (up to 1 m/s). It also reacts to any major step perturbations in the lateral OF (provided by a moving wall) and to any disturbances caused by a tapered corridor. The minimalistic visual system (comprised of only 4 pixels) suffices for the hovercraft to be able to control both its clearance from the walls and its forward speed jointly, without ever measuring speed and distance. The non-emissive visual sensors and the simple control system developed here are suitable for use on MAVs with a permissible avionic payload of only a few grams. This study also accounts quantitatively for previous ethological findings on honeybees flying freely in a straight or tapered corridor.

A Collaborative Wheelchair System

Abstract: This paper describes a novel robotic wheelchair, and reports experiments to evaluate its efficiency and understand how human operators use it. The concept at the heart of the collaborative wheelchair assistant (CWA) is to rely on the user's motion planning skills while assisting the maneuvering with flexible path guidance. The user decides where to go and controls the speed (including start and stop), while the system guides the wheelchair along software-defined guide paths. An intuitive path editor allows the user to avoid dangers or obstacles online and to modify the guide paths at will. By using the human sensory and planning systems, no complex sensor processing or artificial decision system is needed, making the system safe, simple, and low-cost. We investigated the performance of the CWA on its interaction with able-bodied subjects and motion efficiency. The results show that path guidance drastically simplifies the control. Using the CWA, the wheelchair user needs little effort from the first trial, while moving efficiently with a conventional wheelchair requires adaptation.

Dynamic model based formation control and obstacle avoidance of multi-robot systems

Abstract: This work presents, first, a complete dynamic model of a unicycle-like mobile robot that takes part in a multi-robot formation. A linear parameterization of this model is performed in order to identify the model parameters. Then, the robot model is input-output feedback linearized. On a second stage, for the multi-robot system, a model is obtained by arranging into a single equation all the feedback linearized robot models. This multi-robot model is expressed in terms of formation states by applying a coordinate transformation. The inverse dynamics technique is then applied to design a formation control. The controller can be applied both to positioning and to tracking desired robot formations. The formation control can be centralized or decentralized and scalable to any number of robots. A strategy for rigid formation obstacle avoidance is also proposed. Experimental results validate the control system design.

On-orbit assembly using superquadric potential fields

Abstract: The autonomous on-orbit assembly of a large space structure is presented using a method based on superquadric artificial potential fields. The final configuration of the elements which form the structure is represented as the minimum of some attractive potential field. Each element of the structure is then considered as presenting an obstacle to the others using a superquadric potential field attached to the body axes of the element. A controller is developed which ensures that the global potential field decreases monotonically during the assembly process. An error quaternion representation is used to define both the attractive and superquadric obstacle potentials allowing the final configuration of the elements to be defined through both relative position and orientation. Through the use of superquadric potentials, a wide range of geometric objects can be represented using a common formalism, while collision avoidance can make use of both translational and rotation maneuvers to reduce total maneuver cost for the assembly process.

Effects of a secondary task on obstacle avoidance in healthy young adults.

Abstract: Research on attention and gait stability has suggested that the process of recovering gait stability requires attentional resources, but the effect of performing a secondary task on stability during obstacle avoidance is poorly understood. Using a dual-task paradigm, the present experiment investigated the extent to which young adults are able to respond to a secondary auditory Stroop task (requiring executive attentional network resources) concurrently with obstacle crossing during gait when compared with performing unobstructed walking or sitting (control task). Our results demonstrated that as the level of difficulty in the postural task increased, there was a significant reduction in verbal response time from congruent to incongruent conditions in the auditory Stroop task, but no differences in gait parameters, indicating that these postural tasks require attention, and that young adults use a strategy of modulating the auditory Stroop task performance while keeping stable gait performance under the dual-task situations. Our findings suggest the existence of a hierarchy of control within both postural task (obstacle avoidance requires the most information processing resources) and dual-task (with gait stability being a priority) conditions.

UAV formation flight using 3D potential field

Abstract: The paper presents a solution for formation flight and formation reconfiguration of unmanned aerial vehicles (UAVs). Based on a virtual leader approach, combined with an extended local potential field, it is universal applicable by driving the vehiclepsilas auto pilot. The solution is verified, using a group of UAVs based on a simplified small-scale helicopter, which is simulated in MATLABtrade/Simulinktrade. As necessary for helicopters, the potential field approach is realized in 3D including obstacle and collision avoidance. The collision avoidance strategy could be used separately for the sense and avoid problem.

Missing in action: the effect of obstacle position and size on avoidance while reaching.

Abstract: When reaching to objects, our hand and arm rarely collide with non-target objects, even if our workspace is cluttered. The simplicity of these actions hides what must be a relatively sophisticated obstacle avoidance system. Recent studies on patients with optic ataxia and visual form agnosia have demonstrated that obstacle avoidance is an automatic process, likely governed by the dorsal stream (Schindler et al. 2004; Rice et al. 2006). The current study sought to quantify how normal participants react to changes in the size and position of non-target objects in and around their workspace. In the first experiment, 13 right-handed subjects performed reaches to a target strip in the presence of two non-target objects, which varied in depth and horizontal configuration. We found that objects with horizontal alignments that were asymmetric about midline created systematic deviations in reach trajectory away from midline, with participants seeming to maximize the distance away from the two objects. These deviations were significantly greater for objects nearer in depth and nearly disappeared when the objects were placed beyond the target strip. Accompanying this pattern of deviation were other significant obstructing effects whereby reaches were executed more slowly when objects were close in depth and close to the participants reaching (right) hand. In the second experiment, we varied the height of the two objects, as well as the depth. Object pairs were now both tall, both short, or one-short/one-tall. We replicated the significant depth effects of the first experiment, extending the finding to include sensitivity to the size of the objects. Here the obstructing effect caused by short objects was similar to tall objects when those objects were placed at the depth of the reach target, but less than the tall objects when placed at mid-reach. Taken together, these experiments suggest that humans possess a sophisticated obstacle avoidance system that is extremely sensitive and conservative in evaluating potential obstacles and adjusting the reach accordingly.

Improving path planning and mapping based on stereo vision and lidar

Abstract: 2D laser range finders have been widely used in mobile robot navigation. However, their use is limited to simple environments containing objects of regular geometry and shapes. Stereo vision, instead, provides 3D structural data of complex objects. In this paper, measurements from a stereo vision camera system and a 2D laser range finder are fused to dynamically plan and navigate a mobile robot in cluttered and complex environments. A robust estimator is used to detect obstacles and ground plane in 3D world model in front of the robot based on disparity information from stereo vision system. Based on this 3D world model, 2D cost map is generated. A separate 2D cost map is also generated by 2D laser range finder. Then we use a grid-based occupancy map approach to fuse the complementary information provided by the 2D laser range finder and stereo vision system. Since the two sensors may detect different parts of an object, two different fusion strategies are addressed here. The final occupancy grid map is simultaneously used for obstacle avoidance and path planning. Experimental results obtained form a Point Grey's Bumblebee stereo camera and a SICK LDOEM laser range finder mounted on a Packbot robot are provided to demonstrate the effectiveness of the proposed lidar and stereo vision fusion strategy for mobile robot navigation.

Mobile robot navigation using motor schema and fuzzy context dependent behavior modulation

Abstract: This paper presents a novel technique to autonomously select different motor schemas using fuzzy context dependant blending of robot behaviors for navigation. First, a set of motor schemas is formed as behaviors. Both strategic and reactive type schemas have been employed in order to facilitate both the aspects of global and local motion planning. While strategic schemas are formed using the prior knowledge of the environment, the reactive schemas are activated using current sensory data of the robot. For global path planning, a safe path is first created using a Voronoi diagram. For local planning, the Voronoi vertices are treated as immediate subgoals and are used to form schemas leading to achieve optimized traveled distance and goal oriented robot navigation. Two motor schemas are formed as reactive behaviors for obstacle avoidance. The unknown obstacles are modeled using the sensory data. The coordinated behavior is achieved while employing weighed vector summation of the schemas. The adaptation of weights are achieved through a fuzzy inference system where fuzzy rules are used to dynamically generate the weights during navigation. A novel approach is proposed for fuzzy context-dependent blending of schemas. Fuzzy rules are formed using two main criteria into account: the first criterion reasons out the context dependent activity of a schema for achieving goal and the second criterion reasons out cooperative activity of strategic schemas with high priority reactive schemas. Comprehensive results validate that the proposed technique eliminates the existing drawbacks of motor schema approaches available in literature and provides collision free goal oriented robot navigation.

The effects of an auditory startle on obstacle avoidance during walking

Abstract: Movement execution is speeded up when a startle auditory stimulus is applied with an imperative signal in a simple reaction time task experiment, a phenomenon described as StartReact. The effect has been recently observed in a step adjustment task requiring fast selection of specific movements in a choice reaction time task. Therefore, we hypothesized that inducing a StartReact effect may be beneficial in obstacle avoidance under time pressure, when subjects have to perform fast gait adjustments. Twelve healthy young adults walked on a treadmill and obstacles were released in specific moments of the step cycle. On average the EMG onset latency in the biceps femoris shortened by 20% while amplitude increased by 50%, in trials in which an auditory startle accompanied obstacle avoidance. The presentation of a startle increased the probability of using a long step strategy, enlarged stride length modifications and resulted in higher success rates, to avoid the obstacle. We also examined the effects of the startle in a condition in which the obstacle was not present in comparison to a condition in which the obstacle was visibly present but it did not fall. In the latter condition, the obstacle avoidance reaction occurred with a similar latency but smaller amplitude as in trials in which the obstacle was actually released. Our results suggest that the motor programmes used for obstacle avoidance are probably stored at subcortical structures. The release of these motor programmes by a startling auditory stimulus may combine intersensory facilitation and the StartReact effect.

Collision Avoidance for Unmanned Surface Vehicles

Abstract: Considerable progress has been achieved in recent years with respect to autonomous vehicles. A good example is the DARPA Grand Challenge, a competition for autonomous ground vehicles. None of the competing vehicles managed to complete the challenge in 2004, but returning in 2005, a total of five vehicles were successful. Effective collision avoidance is a requirement for autonomous navigation, and even though much progress has been done, it still remains an open problem. The focus of this thesis is on the development of a collision avoidance system for unmanned surface vehicles (USVs), which is compliant with the International Regulations for Avoiding Collisions at Sea (COLREGS). The system is based on a modified version of the Dynamic Window algorithm, taking both acceleration and lateral speeds into account for reactive collision avoidance. Path planning is provided by the Rapidly-Exploring Random Tree (RRT) algorithm, extended to use the A* algorithm as a guide, which significantly increases its efficiency. Extensive simulations have been performed in order to determine the value of the modifications done to the original algorithms, as well as the performance of the total control system. Full-scale experiments have also been carried out in an attempt to verify the results from the simulations. The collision avoidance system performed very well during the simulations, finding near-optimal paths through the environment and evading other vessels in a COLREGS-compliant fashion. In the full-scale experiments, important sensor data was erroneous, resulting in reduced avoidance margins. However, the collision avoidance system still kept the controlled vessel safe, showing significant robustness.

Real-Time Time-to-Collision from Variation of Intrinsic Scale

Abstract: Time-to-collision can be directly measured from a spatio-temporal image sequence obtained from an uncalibrated camera. This it would appear to offer a simple, elegant measurement for use in obstacle avoidance. However, previous techniques for computing time to collision from an optical flow have proven impractical for real applications.

Task maps in humanoid robot manipulation

Abstract: This paper presents an integrative approach to solve the coupled problem of reaching and grasping an object in a cluttered environment with a humanoid robot. While finding an optimal grasp is often treated independently from reaching to the object, in most situations it depends on how the robot can reach a pregrasp pose while avoiding obstacles. We tackle this problem by introducing the concept of task maps which represent the manifold of feasible grasps for an object. Rather than defining a single end-effector goal position, a task map defines a goal hyper volume in the task space. We show how to efficiently learn such maps using the rapidly exploring random tree algorithm. Further, we generalise a previously developed motion optimisation scheme, based on a sequential attractor representation of motion, to cope with such task maps. The optimisation procedure incorporates the robotpsilas redundant whole body controller and uses analytic gradients to jointly optimise the motion costs (including criteria such as collision and joint limit avoidance, energy efficiency, etc.) and the choice of the grasp on the manifold of valid grasps. This leads to a preference of grasps which are easy to reach. The approach is demonstrated in two reach-grasp simulation scenarios with the humanoid robot ASIMO.

UAV collision avoidance using cooperative predictive control

Abstract: This article describes the use of predictive control for the decentralized cooperative control of unmanned aerial vehicles in an unfamiliar three-dimensional environment. It is assumed that each vehicle is equipped with an autopilot and a trajectory control unit. The autopilot insures the stability of the vehicle. The setpoints of the autopilot are calculated by the trajectory control unit, thus forming a cascade control structure. The trajectory control unit relies on a predictive control algorithm to calculate the optimal commands (autopilot setpoints) such that the vehicle will reach fixed targets at known positions while avoiding static obstacles that are detected en route. The advantage in using predictive control is that it offers great flexibility in the objective function to optimize while respecting constraints such as command limits, limits on the displacement that a vehicle can carry out, and the constraints that allow obstacle avoidance. The principle proposed in order to avoid static obstacles (that are assumed ellipsoid) is to verify that the predicted vehicle trajectory does not intersect these obstacles. With the objective to increase performance, cooperation between vehicles must also be privileged. Thus, if some vehicles are within the communication range, they can share the position and shape of the obstacles they have detected. Simulations illustrate the method and higlight the benefits of cooperation.