• 专利附录
  • 专利说明
  • 权利要求
  • 类似技术
  • 同族专利
  • 引用文献
  • 法律状态
  • 优先权
    • 专利摘要:
    The invention relates to a method for controlling a vehicle (1) around obstacles (7) starting from a starting position (2) into an end position (3), wherein the vehicle is controlled along a path, the path comprising linear partial paths (4) defined by a step size ɳ and a steering angle δ, the method comprising the steps of: a) determining a maximum steering angle range and a maximum and minimum incremental range; b) determining the current distance eP to the end position (3) and the target angle θO and the angular difference eθ of the current vehicle angle to the target angle; c) performing an optimization method for determining a sub-path (4) by minimizing the value of a cost function assigned to the sub-path lO, where (i) the cost function the current distance eP to the end position (3) and the current angular difference eθ to the target angle as independently weighted optimization variables and (ii) as boundary conditions the maximum steering angle range, the maximum and minimum incremental range and a collision check are provided; d) determining the new position by adding the determined sub-path (4) to the current position; e) repetition of steps (b) to (d) until the end position (3) is reached with sufficient accuracy.
    公开号:AT514588A4
    申请号:T670/2013
    申请日:2013-08-29
    公开日:2015-02-15
    发明作者:Patrik Zips；Martin Böck；Andreas Kugi
    申请人:Tech Universität Wien；
    IPC主号:
    专利说明:

    Method for controlling a vehicle
    The invention relates to a method for controlling a vehicle around obstacles, starting from a start position to an end position, wherein the vehicle is controlled along a path.
    Methods are known from the prior art for calculating the parking curve and the parking curve of a vehicle from a parking space or a garage. Such parking curves are used in automatic parking systems of vehicles to give the driver assistance in parking and parking or fully automatically a parking or Ausparkvorgang perform.
    Thus, the document DE 10 2012 211 721 A1 shows a method for deriving a parking curve, in which the vehicle is guided along linear sections and a single curved section with a constant turning radius in order to drive into the parking space. This document also shows an improved method in which the vehicle is passed along a first extension straight, a second extension straight and a third extension straight.
    In such methods, however, it is problematic that it is necessary to determine how many linear or curved sections should be used even before the start of the path planning.
    In other known methods, a mathematical optimization of the entire path is performed, the path being parameterized by a composition of linear segments and curve segments.
    However, such methods are only applicable in limited cases as compared to manual parking in and out and often fail in practice. Also, in-vehicle computing typically has very limited computational power, which places narrow limits on the overall pathway global optimization.
    The object of the present invention is therefore to provide a method for determining a path for parking or parking a vehicle, which, in view of the low computing capacity in vehicles, is fast enough and nevertheless versatile enough to be safely applicable in practice.
    This object is achieved according to the invention in that the entire path is subdivided into linear partial paths, which are respectively defined by a step size η and a steering angle δ, the method comprising the following steps:
    First, a maximum steering angle range and a maximum and minimum step width range are determined.
    Thereafter, the current distance ep to the end position and the current vehicle target angle θο and the angular difference βθ = Θ - 0o of the current vehicle angle Θ to the target angle θο are determined.
    It is provided that the target angle θo can assume different values in different sections of the path.
    On the basis of this information, an optimization method for determining a partial path is carried out by minimizing the value of a cost function l0 assigned to the partial path, the cost function comprising the current distance ep to the final position and the current angular difference ee as independently weighted components. The cost function 10 may also include other components, in particular as a function of the maximum steering angle range and step width range. The weighting of the individual terms in the cost function can be adapted to the respective scenario.
    The result of the optimization is a partial path defined by a step size and a steering angle. As boundary conditions, the maximum steering angle range, the minimum and maximum step size range and a collision check with the obstacles are provided.
    After the optimization, the new position, the distance to the end position and, if appropriate, a new target angle and the new angle difference are determined on the basis of the determined subpath. The optimization and adaptation to the new values is repeated until the end position is reached with sufficient accuracy.
    Thus, the optimization does not take place globally for the entire path from the start point to the end point, but separately for each individual part path. After passing through a partial path, a new optimization task is set up. Starting from the starting point, each partial path is defined by a step size and a steering angle, wherein a steering angle range is predefined, for example +/- 45 °. In addition, a maximum and minimum step size is specified, for example a range of 1mm to 20cm.
    In each individual optimization method, the minimum of a cost function whose components are, on the one hand, the current distance to the end point and, on the other hand, the angle difference of the current vehicle angle to a target angle adapted to the respective scenario is determined to determine the step size and the steering angle. These two components are weighted independently.
    As a boundary condition of the optimization serve the Schrittweiten- and steering angle ranges, as well as a collision detection based on the coordinates of the vehicle outer edges and the obstacles. After the partial path has been optimized, the new distance and angle to the end point and the difference to the vehicle angle are determined and continued with the optimization for the next partial path until the end point is reached with sufficient accuracy. This method requires significantly less computational power compared to global optimizations of the entire path since the optimization is split into several, typically 30 to 100, single optimizations. No curve sections are needed, but the entire path is composed of linear partial paths.
    According to the invention, it can be provided that, initially with the vehicle stationary, the complete path to the end point is calculated, and only then is the vehicle steered along the path.
    However, it may also be provided that the vehicle is already controlled during the calculation of the path to the end point along the calculated partial paths.
    Furthermore, it can be provided that, depending on the position of a point of the vehicle, in particular a vertex relative to the obstacles, the method is subdivided into at least two sections, wherein in a first section a target angle .theta.o = .alpha. Is selected, where .alpha Essential normal to a boundary line between the obstacles is.
    As a corner, preferably that outer edge or outer corner of the vehicle can be selected, by which the vehicle must rotate in the movement from the start position to the end position in order to avoid the obstacles. However, other points on the vehicle can also be selected.
    By appropriate choice of the target angle θo which is substantially normal to a boundary line between the obstacles, it is achieved that the optimization method provides solutions which favor a rotation of the vehicle and thus guide the vehicle as fast as possible around an obstacle, for example move out of a parking space.
    On the other hand, it can also be provided that a target angle is chosen which is substantially parallel to the longitudinal extent of the obstacles. This choice is advantageous in order not to rotate the vehicle as much as possible, but rather to move as quickly as possible along a straight line, for example, after leaving the parking space, to seek out the final position without excessive angular corrections.
    The choice of the target angle is preferably adapted to the respective scenario.
    For example, a target angle normal to a boundary line between the obstacles may be advantageous when the vehicle is to be moved out of a longitudinal parking situation (parallel parking) or a transverse parking situation (garage parking).
    On the other hand, a target angle that is substantially parallel to the longitudinal extent of the obstacles may be advantageous if the vehicle is to be moved out of an oblique parking situation.
    According to the invention, it may further be provided that, depending on the position of a corner point of the vehicle relative to the obstacles, the method is divided into at least two sections, wherein in a second section a target angle θo = 0s is chosen, which is selected to be substantially parallel to a boundary line between the obstacles.
    Thereby, the case can be solved that the vehicle is first moved out of a parking space in a first section by strong rotational movement, and thereafter, in a second section, as far as possible without rotational movement, the end position is searched.
    The distinction between the respective sections is preferably made by means of the position of one of, for example, four corner points of the vehicle with respect to the obstacles, for example that corner point around which the vehicle has to turn most closely in order to reach the final position. This vertex may be determined, for example, in the initialization phase of the algorithm based on the measured sensor data. However, the condition for the section change can also be made on the basis of other criteria, in particular with respect to the position of a point of the vehicle with respect to a derived criterion of the obstacles, for example a very specific boundary line between the obstacles.
    A certain safety distance around the obstacles can also be calculated in order to avoid collisions with certainty and, for example, to counteract measuring errors with regard to the position and extent of the obstacles.
    According to the invention, it can be provided that the different sections differ by respectively different weighting factors of the optimization variables ep and ee.
    In a variant of the invention, the method is divided into two phases A and B, wherein in phase A, the weighting of the current distance eP to the end position over the weighting of the actual angular difference ee to the target angle predominates to move the vehicle rapidly towards the end position, in phase B, the weighting of the angular difference ee to the target angle relative to the weighting of the current distance p to the end position predominates to bring the vehicle to the correct angular position, switching at a switching point between phase A and phase B as soon as the position of a vertex of the vehicle passes a boundary line between the obstacles ,
    However, situations are also provided according to the invention in which there are more than two sections with different weighting factors, for example, if there are additional obstacles in the vicinity of the end position as well, which must be avoided. The number of sections having different weighting factors is not limited in the present invention.
    According to the invention, provision can be made for additional direction change points to be determined during the method in which the direction of the sub-path to be determined is changed. In this case, the direction change points can be defined as those points in which either no partial path can be determined, whose associated cost function is improved compared with the previously determined partial path, or no partial path can be determined which lies within the permitted step width range.
    In particular, the direction change points can be defined as those points in which no partial path can be determined in phase A, whose associated cost function is improved compared to the previously determined partial path, or in phase B can not be determined a partial path that is within the allowed step size range.
    This mimics a driving behavior similar to the human vehicle driver by reversing the current direction of travel if no improvement in position or no further movement without collision is possible in the current direction.
    In addition to the method, the present invention also extends to a computer-readable data carrier with a computer program implementing a method according to the invention, and to an apparatus for carrying out a method according to the invention, comprising sensors for determining the start position, the end position, the vehicle angle, the steering angle and the coordinates of the obstacles, as well as a Control unit, as well as on a vehicle with such a device.
    Further features of the invention will become apparent from the claims, the description and the drawings. The invention will be explained in more detail below with reference to exemplary embodiments.
    Fig. 1 shows a schematic sketch of the kinematic model used for the vehicle;
    Figures 2a-2b show schematic sketches of a parking operation of a vehicle under the execution of the method according to the invention;
    Fig. 3 shows a schematic representation of various parking scenarios;
    4 shows a schematic representation of a parking scenario;
    Fig. 5 shows an illustration of the method according to the invention using pseudocode.
    Fig. 1 shows a schematic sketch of the kinematic model used for the vehicle. The vehicle 1 (not shown) has a length l0 and a width wc, for example in accordance with the illustrated table, and moves in the direction of the vector v, initially having the vehicle orientation in with respect to the coordinate system used. Both wheels of one axle are in this case combined into a respective intended wheel 10 in the middle of the axle, the front wheel having the steering angle δ. The maximum steering angle is 45 ° in this embodiment. The distance between the two wheels is the corresponding wheelbase of the vehicle L.
    Fig. 2a shows a vehicle 1 which is in a start position 2 and is to be steered into an end position 3 without touching the obstacles 7. For this purpose, a series of partial paths 4 are determined, solving for each partial path statistical optimization problem.
    Depending on the position of a vertex 5 of the vehicle relative to an imaginary boundary line 6 between the obstacles 7, a distinction is made between the phases A and B, in which different weightings are used for the respectively to be optimized optimization method. In the illustrated case, the vehicle 1 is in the parked state in phase B and is to be moved out of the parking space with the strongest possible rotational movements without the absolute distance to the end point 3 being of great importance. For this reason, in the optimization method, the target angle θ0 = α is set, and the weighting of the distance to the end position ep is greatly reduced from the weighting of the angle difference to the target angle = θ - θο.
    FIG. 2 b shows the vehicle 1 shortly before it has reached the end position 3. The vertex 5 has crossed the boundary line 6 at the switching point 8, and has been switched from phase B to phase A. Accordingly, in the optimization method, the target angle θo = ss has been set, and the weighting of the distance to the end position eP against the weighting of the angular difference to the target angle e0 is greatly increased.
    Fig. 3 shows schematically different scenarios of the method, namely parallel parking and parking (I), parking in and out of a garage or cross-parking (II) and oblique parking in and out (III). In each scenario, one possible relevant vertex 5 of the vehicle is marked, which can be used to determine the phase change between phase A and phase B. Other vertices are also conceivable.
    The area of phases A and B is also shown. In all three scenarios, the target angle 0s in phase A is parallel to the boundary line 6. On the other hand, target angle α in phase B in in scenario I and II is normal to the boundary line 6, but in scenario III parallel to the longitudinal extent of the obstacles 7.
    Fig. 4 shows a schematic representation of a parking scenario in which the direction of travel is changed. The vehicle 1, starting from the start point 2, first moves out of a parking space and thus moves from the phase B to the phase A. Thereafter, however, a situation occurs in which the vehicle continues to move away from the end point 3 by each forward movement. Accordingly, in the optimization process in phase A, no partial path can be determined whose cost function is less than the previously calculated cost function.
    This situation is detected in the direction change point 9, in which the vehicle changes the direction of travel and reverses. As a result, the vehicle approaches the end point 3 again. Of course, it may also be necessary to change the direction of travel several times during an entry or exit procedure, in order to always receive valid and continuously reduced results of the optimization procedure.
    Fig. 5 shows a detailed representation of the method according to the invention using pseudocode. In this embodiment, an auto-parking method is performed, and the start position of the vehicle qo is initialized as the parking position qP. Thereafter, the target angle θο is set to the value α. The value of α depends on the respective parking situation. Both in the case of the long-term parking, as well as in the case of transverse parking, the vehicle should be moved normally to the limit line 6 for the parking process as far as possible.
    Thereafter, the weight term R and the weight matrix R are set. Depending on the phase, the initial values re, θo and R are set, for example, as follows, it being understood that other weights may be provided as well:
    In the present embodiment, a Ausparkvorgang is determined, thus the method is initially in phase B. The direction D of the vehicle with 1 (forward) and the starting solution u = [U | 0, ηο] τ for the steering input uf1 / L tan (ö ) and the step width η are initialized. The vectors umin and umax limit the steering input and the step size.
    Thereafter, in a loop, the optimization process is run until the position of the vehicle is in an epsilon environment around the end point and thus the end position is reached.
    In each loop it is checked whether the position of the vertex 5 traverses the imaginary boundary line of the obstacles (xcfu ^ b) and in this case the weighting terms of the phase A from the above table are used.
    Thereafter, the actual optimization process is started, which is defined as follows: min 10 (q-1 + i) S.t. q ,; + i = f (q,; U; .D) hp (q / + 1) < 0 U-mm £ Uj. £, where the cost function to be minimized is:
    Io, (q * +1) = 7'0e0i + 1 + eP < + 1E * Pi + i
    In this method, qj denotes the current position of the vehicle to step i, the pitch vector, and D the direction. The cost penalty is minimized with respect to the variables βθ, and ep ,. The term ep, = [χ, -Xs, yrys] T denotes the distance of the vehicle to step i to the start position [xs, ys] (since the total path from the end position back to the start position is calculated). The term e ^ = 0, -00 designates the difference between the current vehicle angle and the target angle 0o. The parameters re and R are weighting parameters.
    The function hP (qj) denotes a collision detection, which detects a contact of the given dimensions of the vehicle with the obstacles on geometric way. Finally, umin and umax denote the minimum and maximum values of the optimization input consisting of steering input and step size.
    In each iteration step, the position and the vehicle angle are improved in terms of the cost function, the cost function fulfilling the purpose of allowing the start point to be reached quickly by selecting defined weighting parameters re and R in phases A and B.
    The new position qi + i is represented by an equation of motion f (qs, Uj, D), which is
    The optimization problem of the cost function loi (Qi) is always formulated only for one incremental step after the other, and repeated until the endpoint is reached. After each optimization it is checked whether either the value of the cost function is greater than in the previous optimization (lof> ki Iom) or a collision occurs (hp (qi + 1 *)> 0) and thus no partial path was found. Here are k | a weighting factor to allow sufficiently small deteriorations. If so, the direction of the subpath is reversed by setting D equal -D.
    Otherwise, the new position qi + 1 is determined by the equation of motion f (qi, u ,, D), and the procedure continues with the new position. The method is terminated when the new position is in an epsilon environment around the endpoint.
    The method according to the invention can be part of a control electronics of a vehicle or can be in the form of a computer program on a data carrier. The correspondingly controlled vehicle is equipped with sensors for detecting the environment and preferably also its own driving movements. Thus, a GPS sensor and a plurality of ultrasonic sensors or cameras may be provided to detect the own position and the positions of the obstacles. On the basis of this, the required weighting terms for the method can be determined.
    The invention is not limited to the illustrated embodiments but extends to all embodiments within the scope of the following claims.
    List of Reference Signs 1 vehicle 2 start position 3 end position 4 part path 5 corner point 6 boundary line 7 obstacle 8 changeover point 9 direction change point 10 wheel
    权利要求:
    Claims (13)
    [1]
    A method of controlling a vehicle (1) around obstacles (7) from a starting position (2) to an end position (3), the vehicle being controlled along a path, characterized in that the path comprises linear sub-paths (4) defined by a pitch η and a steering angle δ, the method comprising the steps of: a) determining a maximum steering angle range and a maximum and minimum pitch range; b) determining the current distance ep to the end position (3) and a target angle θ o and the angular difference e e of the current vehicle angle θ to the target angle; c) performing an optimization method for determining a partial path (4) by minimizing the value of a cost function associated with the partial path Io, where (i) the cost function comprises the actual distance ep to the end position (3) and the current angular difference ee to the target angle as mutually independent weighted optimization variables, and (ii ) as boundary conditions the maximum steering angle range, the maximum and minimum incremental range and a collision check are provided; d) determining the new position by adding the determined sub-path (4) to the current position; e) repetition of steps (b) to (d) until the end position (3) is achieved with sufficient accuracy.
    [2]
    Method according to claim 1, characterized in that first the complete path to the end point (3) is calculated, and thereafter the vehicle is controlled along the path.
    [3]
    A method according to claim 1, characterized in that the vehicle is controlled during the calculation of the path to the end point (3) along the calculated sub-paths (4).
    [4]
    4. Method according to one of claims 1 to 3, characterized in that, depending on the position of a point of the vehicle (1), in particular a corner point (5), relative to the obstacles (7), the method is subdivided into at least two sections first, a target angle θ o = α is selected which is substantially normal to a boundary line (6) between the obstacles (7).
    [5]
    5. Method according to one of claims 1 to 3, characterized in that, depending on the position of a point of the vehicle (1), in particular a corner point (5), relative to the obstacles (7), the method is subdivided into at least two sections first section, a target angle θ o = α is selected which is substantially parallel to the longitudinal extent of the obstacles (7).
    [6]
    6. Method according to one of claims 1 to 5, characterized in that, depending on the position of a point of the vehicle (1), in particular a corner point (5), relative to the obstacles (7), the method is subdivided into at least two sections second section, a target angle θ o = 0s is selected, which is selected substantially parallel to a boundary line (6) between the obstacles (7).
    [7]
    A method according to any one of claims 4 to 6, characterized in that the different sections are differentiated by the weighting factors of the optimization variables.
    [8]
    8. The method according to claim 7, characterized in that the method is divided into two phases A and B, wherein a) in phase A, the weighting of the current distance eP to the end position (3) over the weighting of the angular difference e0 to the target angle outweighs B) moving the vehicle rapidly towards the end position, b) in phase B, weighting the angular difference e0 to the target angle relative to the weighting of the distance eP to the final position to bring the vehicle into the correct angular position c) at a switching point (8) between phase A and phase B is switched as soon as the position of a point of the vehicle (1), in particular a corner point (5), passes through a boundary line (6) between the obstacles (7).
    [9]
    9. Method according to one of claims 1 to 7, characterized in that during the optimization process direction change points (9) are determined, in which the direction of the part path to be determined is changed, the direction change points are defined as those points in which a) determines no partial path can be, whose associated cost function is improved over the previously determined partial path, or b) no partial path can be determined, the increment is within the allowed step size range.
    [10]
    A method according to claim 8, characterized in that during the optimization method direction change points (9) are determined in which the direction of the part path to be determined is changed, the direction change points being defined as those points in which a) no partial path can be determined in phase A. whose associated cost function is improved over the previously determined partial path, or b) in phase B, no partial path that is within the allowed step size range can be determined.
    [11]
    A data carrier comprising a computer program implementing a method according to any one of claims 1 to 10.
    [12]
    12. An apparatus for carrying out a method according to one of claims 1 to 10, comprising sensors for determining the start position (2), the end position (3), the steering angle 5, the vehicle angle Θ and the coordinates of the obstacles (7) and a control unit.
    [13]
    13. Vehicle with a device according to claim 12.
    类似技术:
    公开号 | 公开日 | 专利标题
    AT514588B1|2015-02-15|Method for controlling a vehicle
    DE102015114464A9|2016-04-21|Uniform motion planner for an autonomous vehicle while avoiding a moving obstacle
    DE102015114465A1|2016-03-03|Method for path planning for an evasive steering maneuver
    EP2517190B1|2017-01-11|Automatic forward parking in perpendicular parking spaces
    EP2125472B1|2012-07-11|Semiautomatic parking machine
    EP2222532B1|2017-03-29|Method and device for planning a path when parking a vehicle
    DE102012211721A1|2013-06-13|System and method for deriving an parking curve for a vehicle
    EP3152092B1|2018-04-04|Method for operating a driver assistance system for automatically guiding a motor vehicle, and paired motor vehicle
    EP1720757B1|2010-09-08|Parking aid
    DE4415736A1|1995-11-09|Robot collision prevention using steering angle field control
    DE112017002002T5|2019-01-10|VEHICLE STEERING SYSTEM
    DE102017221398A1|2019-05-29|Method and apparatus for assisting in performing a turning maneuver of a vehicle, vehicle and computer program product
    DE102013213225A1|2015-01-08|Parking assist system and method for controlling a parking assist system for a vehicle
    DE102008027689A1|2009-12-17|Path planning method for use during parking of vehicle i.e. passenger car, involves measuring path relative to lateral parking spot, and simultaneously and maximally shifting path against driving direction depending on parking spot length
    DE102020111856A1|2020-11-12|Vehicle SCC system based on complex information and methods for controlling the same
    DE102016109047A1|2016-12-08|The vehicle steering control device
    DE102017208383B4|2022-02-24|Dynamic parking using the parking assistance system
    EP3213981B1|2019-02-20|Method for autonomous parking of a vehicle in a spot according to a velocity profil presetting, assistance system and vehicle
    DE102010049586A1|2012-04-26|Method for assisting driver for vehicle during traffic situation, involves communicating haptic feedback to driver in vehicle during driving to target position that is determined in surrounding of vehicle
    EP3323697A1|2018-05-23|Planning of a trajectory for autonomous parking of a motor vehicle in a parking space environment
    DE102006018389A1|2007-10-25|Method for following a vehicle wagon in a vehicle combination
    DE102012214847A1|2014-03-27|Method and device for guiding a vehicle within a lane
    DE102019110217B4|2021-09-16|Method for the automated control of a motor vehicle
    EP3347788A1|2018-07-18|Method and device for operating a motor vehicle traveling driverlessly within a parking space
    EP3042829B1|2019-07-24|Method for automatically maneuvering a vehicle to a predefined target position, in particular one designated as a parking space and maneuvering system for a vehicle
    同族专利:
    公开号 | 公开日
    EP3038881A1|2016-07-06|
    CN105764773A|2016-07-13|
    US9834251B2|2017-12-05|
    WO2015028316A1|2015-03-05|
    US20160200359A1|2016-07-14|
    EP3038881B1|2017-06-28|
    AT514588B1|2015-02-15|
    CN105764773B|2018-04-27|
    引用文献:
    公开号 | 申请日 | 公开日 | 申请人 | 专利标题
    DE19940007A1|1999-08-24|2001-03-08|Bosch Gmbh Robert|Method and device for supporting the parking of a motor vehicle|
    EP1332948A1|2002-01-23|2003-08-06|Toyota Jidosha Kabushiki Kaisha|Parking assist device and method for assisting parking|
    WO2004050458A1|2002-12-05|2004-06-17|Bayerische Motoren Werke Aktiengesellschaft|Method for steering a vehicle that is to be reversed into a parking space|
    DE102005006966A1|2004-03-05|2005-09-29|Continental Teves Ag & Co. Ohg|Parking aid for motor vehicles assists in steering and parking by applying torque to steering wheel, and by two or more artificial steering stops on parking path|
    WO2008055567A1|2006-11-08|2008-05-15|Volkswagen Aktiengesellschaft|Parking steering assistant with improved transverse parking function|
    DE102007009745A1|2007-02-28|2008-09-04|Continental Automotive Gmbh|Method for controlling vehicle steering during parking process, involves measuring parking place selected for parking vehicle and establishing orientation field, where orientation field determines number of support points|
    DE102008027689A1|2008-06-11|2009-12-17|Valeo Schalter Und Sensoren Gmbh|Path planning method for use during parking of vehicle i.e. passenger car, involves measuring path relative to lateral parking spot, and simultaneously and maximally shifting path against driving direction depending on parking spot length|
    EP2258606A2|2009-06-05|2010-12-08|Valeo Schalter und Sensoren GmbH|Method for determining a steering curve for steering angles of steerable wheels of a vehicle and park assistance system for a vehicle|
    DE102009040373A1|2009-09-07|2011-04-14|Valeo Schalter Und Sensoren Gmbh|Method for executing semi-autonomous parking procedure of vehicle by parking assistance system, involves detecting displacements of vehicle by objects by sensor unit after introduction of parking procedure|
    EP2316709A2|2009-10-30|2011-05-04|Audi AG|Motor vehicle, external control device and method for moving a motor vehicle out of a parking place|
    WO2012080044A1|2010-12-15|2012-06-21|Robert Bosch Gmbh|Method and system for determining a self-movement of a vehicle|
    WO2013053514A1|2011-10-13|2013-04-18|Robert Bosch Gmbh|Method for improving a parking assistant and parking system|
    DE102012211721A1|2011-12-09|2013-06-13|Hyundai Motor Company|System and method for deriving an parking curve for a vehicle|DE102018118242A1|2018-07-27|2020-01-30|Valeo Schalter Und Sensoren Gmbh|Aligning the vehicle during assisted parking|US5870303A|1987-11-20|1999-02-09|Philips Electronics North America Corporation|Method and apparatus for controlling maneuvers of a vehicle|
    EP0375055B1|1988-12-23|1995-03-22|Koninklijke Philips Electronics N.V.|Method and apparatus for controlling maneuvers of a vehicle, and vehicle comprising such apparatus|
    JP4301861B2|2002-05-20|2009-07-22|川崎重工業株式会社|Method and apparatus for maneuvering moving body|
    US8571722B2|2010-10-22|2013-10-29|Toyota Motor Engineering & Manufacturing North America, Inc.|Method for safely parking vehicle near obstacles|JP5989729B2|2014-09-12|2016-09-07|アイシン精機株式会社|Delivery support device|
    CN105469619A|2015-12-29|2016-04-06|小米科技有限责任公司|Method and device for transmitting automobile coordinate|
    US10207704B2|2016-08-19|2019-02-19|Dura Operating, Llc|Method for autonomously parking and un-parking a motor vehicle|
    US9969386B1|2017-01-10|2018-05-15|Mitsubishi Electric Research Laboratories, Inc.|Vehicle automated parking system and method|
    US10571921B2|2017-09-18|2020-02-25|Baidu Usa Llc|Path optimization based on constrained smoothing spline for autonomous driving vehicles|
    CN107792179B|2017-09-27|2019-08-23|浙江零跑科技有限公司|A kind of parking guidance method based on vehicle-mounted viewing system|
    KR102192436B1|2018-03-05|2020-12-16|주식회사 만도|Apparatus and method for determining target angle based on radar|
    JP6861272B2|2018-03-08|2021-04-21|バイドゥドットコム タイムズ テクノロジー （ベイジン） カンパニー リミテッドＢａｉｄｕ．ｃｏｍ Ｔｉｍｅｓ Ｔｅｃｈｎｏｌｏｇｙ （Ｂｅｉｊｉｎｇ） Ｃｏ．， Ｌｔｄ．|Optimizing the behavior of self-driving cars based on post-collision analysis|
    CN109895764A|2018-06-29|2019-06-18|华为技术有限公司|The method and apparatus for determining automatic parking strategy|
    EP3829958A1|2018-07-27|2021-06-09|embotech AG|Method for steering a vehicle and apparatus therefor|
    CN109376734B|2018-08-13|2020-07-31|东南大学|Square towing induction method for road rescue equipment based on license plate corner features|
    US11247700B2|2018-09-28|2022-02-15|Baidu Usa Llc|Enumeration-based three-point turn planning for autonomous driving vehicles|
    CN110329245A|2019-06-26|2019-10-15|浙江吉利控股集团有限公司|A kind of automatic parking method, apparatus, equipment and vehicle|
    DE102020103853A1|2020-02-14|2021-08-19|Franka Emika Gmbh|Graphically supported adaptation of robot control programs|
    CN111409625A|2020-04-02|2020-07-14|北京四维智联科技有限公司|Parking track determination method and device|
    CN112092810A|2020-09-24|2020-12-18|上海汽车集团股份有限公司|Vehicle parking-out method and device and electronic equipment|
    CN112884229A|2021-02-26|2021-06-01|中新国际联合研究院|Large-scale public place people flow guiding path planning method based on differential evolution algorithm|
    法律状态:
    2016-04-15| PC| Change of the owner|Owner name: ROBERT BOSCH GMBH, DE Effective date: 20160229 |
    优先权:
    申请号 | 申请日 | 专利标题
    ATA670/2013A|AT514588B1|2013-08-29|2013-08-29|Method for controlling a vehicle|ATA670/2013A| AT514588B1|2013-08-29|2013-08-29|Method for controlling a vehicle|
    CN201480047738.1A| CN105764773B|2013-08-29|2014-08-14|method for controlling a vehicle|
    PCT/EP2014/067406| WO2015028316A1|2013-08-29|2014-08-14|Method for steering a vehicle|
    EP14755625.2A| EP3038881B1|2013-08-29|2014-08-14|Method for controlling a vehicle|
    US14/912,560| US9834251B2|2013-08-29|2014-08-14|Method for steering a vehicle|
    [返回顶部]