EP4377177A1 - Procede de pilotage de vehicule et d'evitement d'obstacle - Google Patents
Procede de pilotage de vehicule et d'evitement d'obstacleInfo
- Publication number
- EP4377177A1 EP4377177A1 EP22744233.2A EP22744233A EP4377177A1 EP 4377177 A1 EP4377177 A1 EP 4377177A1 EP 22744233 A EP22744233 A EP 22744233A EP 4377177 A1 EP4377177 A1 EP 4377177A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- trajectory
- motor vehicle
- obstacle
- collision
- risk
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 208000027418 Wounds and injury Diseases 0.000 claims abstract description 29
- 230000006378 damage Effects 0.000 claims abstract description 29
- 208000014674 injury Diseases 0.000 claims abstract description 29
- 238000004422 calculation algorithm Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000035484 reaction time Effects 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 4
- 230000003213 activating effect Effects 0.000 abstract 1
- 230000006870 function Effects 0.000 description 21
- 230000001186 cumulative effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 3
- 238000013349 risk mitigation Methods 0.000 description 3
- 230000001960 triggered effect Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 210000004027 cell Anatomy 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 230000000116 mitigating effect Effects 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 102100034112 Alkyldihydroxyacetonephosphate synthase, peroxisomal Human genes 0.000 description 1
- 101000799143 Homo sapiens Alkyldihydroxyacetonephosphate synthase, peroxisomal Proteins 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000000848 angular dependent Auger electron spectroscopy Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 210000004899 c-terminal region Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004883 computer application Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000009849 deactivation Effects 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/09—Taking automatic action to avoid collision, e.g. braking and steering
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/095—Predicting travel path or likelihood of collision
- B60W30/0953—Predicting travel path or likelihood of collision the prediction being responsive to vehicle dynamic parameters
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/095—Predicting travel path or likelihood of collision
- B60W30/0956—Predicting travel path or likelihood of collision the prediction being responsive to traffic or environmental parameters
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/0097—Predicting future conditions
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
- B60W60/0015—Planning or execution of driving tasks specially adapted for safety
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0019—Control system elements or transfer functions
- B60W2050/0027—Minimum/maximum value selectors
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0019—Control system elements or transfer functions
- B60W2050/0028—Mathematical models, e.g. for simulation
- B60W2050/0031—Mathematical model of the vehicle
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0062—Adapting control system settings
- B60W2050/0075—Automatic parameter input, automatic initialising or calibrating means
- B60W2050/0095—Automatic control mode change
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/40—Dynamic objects, e.g. animals, windblown objects
- B60W2554/402—Type
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/80—Spatial relation or speed relative to objects
- B60W2554/804—Relative longitudinal speed
Definitions
- the present invention generally relates to vehicle safety, in particular with the aim of avoiding collisions between a vehicle and an object present in its environment.
- the present invention proposes a method for driving a motor vehicle comprising, when the motor vehicle is driven in a nominal mode (for example a manual piloting mode by a driver or an autonomous piloting mode by a computer), steps of: - determination of an initial trajectory for the motor vehicle, in particular predicted from dynamic information of the vehicle, - acquisition of data relating to the environment of the motor vehicle, - calculation of a risk of collision between the motor vehicle and a obstacle taking into account the initial trajectory determined and the data acquired, then, if the risk of collision with the obstacle exceeds a risk threshold, - calculation of a time before collision, then, if the time before collision is less than a threshold of time, - activation of an alert driving mode according to which: ⁇ a new trajectory is determined by the computer, said new trajectory making it possible to minimize the risk of collision with the obstacle causing serious injury, and ⁇ a control of the direction of the motor vehicle is
- the triggering of the emergency driving mode dansequel the vehicle is driven along an avoidance trajectory, is triggered only when it is really necessary.
- the invention proves to be particularly advantageous since it combines different technical solutions which interact in such a way as to offer a new, very safe solution for the occupants of the motor vehicle.
- it makes it possible to assign a risk of injury to each object in its environment, given the known accidentology data. It uses a method of perception based on probabilistic occupation grids. It makes it possible to manage the risk of impact and the risk of injury by practicing risk mitigation. It makes it possible to find, when possible, a collision-free trajectory.
- the time threshold is equal to the minimum among an emergency braking time and a driver reaction time;
- the computer maintains the alert driving mode activated for a predetermined minimum duration, preferably between two and four seconds; - when the alert driving mode is activated, it is planned to regularly repeat steps of acquiring data relating to the environment of the motor vehicle, of calculating a risk of collision between the motor vehicle and another obstacle taking into account the new trajectory and the data acquired, then, if the risk of collision with the other obstacle exceeds a risk threshold, calculating a time before collision with the other obstacle, then, if the time before collision is less than said time threshold, determining a second new trajectory making it possible to minimize the risk of collision with each obstacle causing serious
- the new trajectory is chosen from several test trajectories using a cost function, a value of said cost function being calculated for each test trajectory;
- - said value depends, when the test trajectory encounters an obstacle, on the speed of impact with the obstacle and on the type of obstacle;
- - Said value varies depending on whether or not the test path leaves the road taken by the motor vehicle and/or the traffic lane used by the motor vehicle and/or the traffic lanes authorized for the motor vehicle;
- the new trajectory is chosen from among several test trajectories using an MPPI type algorithm
- said data is in the form of a probabilistic occupancy grid representative of the environment of the motor vehicle and containing information on the objects present in the environment of the motor vehicle.
- Figure 1 is a schematic top view of a motor vehicle adapted to implement a method according to the invention
- Figure 2 is a representation of the "bicycle" model applied to the motor vehicle moving in a traffic lane;
- FIG. 3 is a diagram illustrating a computer system for implementing the method according to the invention.
- FIG. 4 is a schematic top view of the motor vehicle of Figure 1 moving on a road;
- FIG. 5 is a block diagram illustrating the different steps required to trigger an emergency driving mode
- FIG. 6 is a block diagram illustrating the various steps required to deactivate the emergency driving mode
- FIG. 7 is a schematic top view of the motor vehicle of Figure 1 moving on a road on which there are obstacles, at a first moment;
- FIG. 8 is a view illustrating the same situation as that illustrated in Figure 7, at a second time;
- FIG. 9 is a view illustrating the same situation as that illustrated in Figure 7, at a third time;
- FIG. 10 is a view illustrating the same situation as that illustrated in Figure 7, at a fourth instant.
- FIG 1 there is shown a motor vehicle 100 seen from above.
- the motor vehicle 100 is here a classic car, comprising a chassis which is supported by wheels and which itself supports various equipment including a powertrain, braking means, and a steering unit.
- This motor vehicle 100 is of the autonomous or semi-autonomous type, in the sense that it comprises equipment making it possible to control the vehicle in speed and in direction at least for a short period of a few seconds.
- This motor vehicle 100 is equipped with odometry sensors enabling it to locate itself in its environment so as, for example, to be able to drive itself autonomously and to assess its environment.
- the motor vehicle 100 is equipped with a camera 130 facing the front of the motor vehicle 100 to capture images of the environment located in front of the motor vehicle 100.
- the motor vehicle 100 is also equipped with at least one telemetry sensor (RADAR, LIDAR or SONAR). It is more precisely here equipped with five LIDAR sensors 121, 122, 123, 124, 125 located at the four corners of the motor vehicle and in the front central position of the motor vehicle.
- the motor vehicle 100 is also equipped with a navigation system 141, comprising for example a GNSS receiver (typically a GPS sensor), a map storage memory, and a calculation unit adapted to locate the position of the vehicle on these cards.
- a navigation system 141 comprising for example a GNSS receiver (typically a GPS sensor), a map storage memory, and a calculation unit adapted to locate the position of the vehicle on these cards.
- the motor vehicle 100 may also comprise an inertial unit 143 making it possible to determine the amount of movement of the vehicle to be two instants.
- the motor vehicle 100 is equipped with a computer 140.
- This computer 140 comprises at least one processor (CPU), at least one internal memory, analog-digital converters, and various input and/or output interfaces. [0038] Thanks to its input interfaces, the computer 140 is suitable for receiving input signals from the various sensors.
- the computer 140 is also connected to an external memory 142 which stores various data such as, for example, predetermined data which will be presented below.
- the internal memory of the computer 140 stores for its part a computer application, consisting of computer programs comprising instructions whose execution by the processor allows the implementation by the computer 140 of the method described below.
- the computer 140 is suitable for transmitting instructions to various parts of the motor vehicle.
- organs are for example a power steering actuator, a brake actuator, an enclosure located in the passenger compartment of the vehicle, a display screen located in the passenger compartment of the vehicle, an engine vibrator located in the steering wheel of the vehicle.
- a reference trajectory can be calculated if an obstacle is on the initial trajectory T0 of the vehicle so as to allow the vehicle to avoid this obstacle without the driver having to intervene ( or at least to minimize the consequences of an impact if it is not possible to avoid the obstacle), and
- the trajectory of the motor vehicle 100 is modeled here by a so-called “bicycle” model illustrated in FIG. 2.
- the motor vehicle 100 is represented by a frame and two wheels 150, 152 (like a bicycle).
- a steering angle, denoted 5, of the front wheel 150 that is to say the angle that the front wheel 150 makes with the longitudinal axis of the motor vehicle 100
- y a heading angle, denoted y, corresponding to the so-called yaw angle, between the longitudinal axis of the motor vehicle 100 and the tangent to the trajectory
- the terms U and l r respectively represent the distances between the center of gravity G of the motor vehicle 100 and the axis of the front axle and the rear axle.
- the state (and therefore the trajectory) of the motor vehicle 100 can therefore be characterized by the set x defined by the equation:
- the computer 140 receives as input data D1 representative of the environment of the motor vehicle. These data D1 are processed by a third party entity 210 of the computer 140, based in particular on the data recorded by the sensors of the vehicle (camera, LIDAR sensors, etc.).
- these data D1 are in the form of a probabilistic occupancy grid containing information on the semantics of the objects.
- the grid is formed of a plurality of cells and is centered on the vehicle or at the front of the latter.
- the characteristic dimensions of this grid depend on the size of the environment that one wishes to apprehend (it can thus vary according to the speed of movement of the motor vehicle 100).
- This representation comprises a first set of data characterizing the motor vehicle 100 (for example its location and its kinematic data) and a second set of data concerning the objects identified in the environment, in particular their location, their direction and their movement speed.
- the computer 140 also receives as input data D2 representative of severity curves resulting from accidentology, stored in a memory 220. [0065] These severity curves make it possible to associate with each detected object has a collision probability with a risk of injury.
- this technique makes it possible to determine, for each detected object, a risk of injury.
- This risk of injury is determined based on a plurality of data associated with each object.
- These data come from injury risk curves constructed from statistical accident analysis data.
- the data from these injury risk curves correspond to an illustration of the variation in the severity of the injury caused by the collision as a function of the speed of impact and the type of object (vehicle, pedestrian, bicycle , inert object, etc.). They make it possible to distinguish, for example, the probability of minor injuries (requiring less than 24 hours or no hospitalization), serious (requiring 24 hours to 30 days of hospitalization) or fatal (related to an accident within 30 days).
- the risk of injury associated with each type of object is determined by calculating a weighted sum of probabilities of death, serious injury and minor injury associated with the determined impact velocity.
- the computer 140 also receives as input data xi, u t odometry of the vehicle.
- the operation of the computer 140 to calculate the reference trajectory T 1 according to all these data can be schematized in two blocks, namely a constraint calculation block 300 and a trajectory development block 400.
- the constraint calculation block 300 makes it possible to establish, on the basis of the data D1, D2, constraints:
- controllability constraints (305). These constraints are here three in number.
- a first controllability constraint aims to limit the steering angle that the power steering actuator can impose on the steering wheel. In fact, it is desired that the steering angle d remain between two lower limits ⁇ min and upper ⁇ max so that the driver can be able to resume steering the vehicle at any time.
- a second controllability constraint aims to limit the steering speed that the power steering actuator can impose on the steering wheel. In fact, it is desired that the steering speed dô/dt remains between two lower Smin and upper Smax limits, for the same reasons as mentioned above.
- a third controllability constraint aims to limit the acceleration undergone by the motor vehicle 100. In fact, it is desired that the acceleration dV/dt remains between two lower limits Amin and upper Amax.
- the trajectory development block 400 makes it possible to determine the optimal reference trajectory T1 which minimizes the overall risk of injury, either by avoiding obstacles, or by mitigation (by minimizing the probability of collision with the risk of injury).
- test trajectories Tt k will be randomly defined (preferably more than 100, and even more preferentially more than 1000), then a cost q k associated with each test trajectory Tt k will be calculated, and a single trajectory will then be selected.
- the plurality of test trajectories Tt k is determined for a time window of the order of a few seconds (for example, of the order of 3 seconds).
- Test trajectories means the trajectories that the motor vehicle 100 could take while maneuvering in a reasonable manner, taking into account the aforementioned constraints. For example, a trajectory along which the motor vehicle 100 would move in reverse is not considered a test trajectory.
- Each of these test trajectories Tt k is determined using the bicycle model M10 described previously, over the aforementioned time window, taking into account the current position of the motor vehicle 100.
- FIG. 4 represents, by way of example, four trajectories possible tests Tti, TU, !3 ⁇ 4, TU.
- One of the main objectives for the computer 140 is then to determine, among this plurality of possible test trajectories Tt k , the one which will minimize the probability of a collision causing an injury.
- the reference trajectory T1 to be taken is determined by optimizing a cost function.
- Several types of algorithms using a cost function could be used.
- the aforementioned patent document FR2007743 describes an example thereof.
- an algorithm 401 of the MPPI (Integral Predictive Path Model) type will be preferred.
- MPPI Intelligent Predictive Path Model
- Such an algorithm is for example described in the document “G. Williams, P. Drews, B. Goldfain, J. M. Rehg and E. A. Theodorou, "Aggressive driving with model predictive path integral control,” 2016 IEEE International Conference on Robotics and Automation (ICRA), Sweden, 2016, pp. 1433-1440, doi: 10.1109/ICRA.2016.7487277”.
- Other algorithms based on this solution could also be used.
- the main idea of these MPPI algorithms is to transform the cost function of an optimal control problem into the expectation of all possible trajectories. This allows to solve the stochastic optimal problem with a probabilistic (Monte Carlo-like) approximation using direct sampling of a stochastic diffusion process.
- the MPPI algorithm determines a control sequence that minimizes the overall cost at each iteration. This cost is the integral of each individual cost at each step where the solution of the Hamilton-Jacobi-Bellman equation is approximated using the Feynman-Kac theorem and the KL divergence as described in the paper by Wlliams and para. previously cited.
- MPPI MPPI-based algorithm
- the use of the MPPI algorithm is attractive because it is a derivative-free optimization method, which allows the use of non-linear and non-convex models and cost functions, and has shown good performance in aggressive driving situations is therefore particularly well suited to emergency trajectories in the context of driving aids.
- This algorithm will preferably be implemented by a particular entity of the computer, namely by a graphics computing entity GPU.
- This algorithm 401 thus proposes a selection method, among the test trajectories Tt k , of the one which is optimal by using a cost function q k.
- This cost function q k is here equal to the sum of several components CPCIR, cvoie, CRéferen ⁇ , c ⁇ ntrôie, C variance making it possible to take into account different constraints (environment, controllability, etc.).
- the component C PC IR corresponds to the cost associated with a collision. It takes into account the risk of collision and the associated risk of injury.
- WPCIR is the weight given to this CPCIR component. This weight is for example predetermined and stored in the memory of the computer.
- brok is a Boolean which takes the value 0 if the test trajectory Tt k considered is free (without any obstacle) and the value 1 if an obstacle is on this trajectory (which is the case of the only test trajectory Tt3 in figure 4).
- OP C IR is calculated according to the speed of impact with the obstacle (in the event of an obstacle being on the test trajectory) and the semantics of this object (in particular the type of obstacle ). It is greater the higher the impact speed, and it is greater for a pedestrian type obstacle than for an inert obstacle (a branch of a tree for example).
- the component c VOi e of the cost function q k is intended to ensure that the value of the cost function is lower for a test trajectory Tt k which does not leave the traffic lane of the vehicle only for a trajectory coming out of it, in order to force the vehicle as much as possible not to go into the opposite traffic lane and not to exceed the limits of the road (in particular if there are safety barriers on both sides other side of the road).
- the first weight w VOi e has a zero value if the test trajectory Tt k remains on the authorized traffic lane(s), and a non-zero value otherwise.
- This first weight thus makes it possible to define a soft constraint allowing the vehicle to leave the authorized traffic lanes, for example by crossing a white line, if no better trajectory is possible.
- Its non-zero value is preferably between the component C Referen ⁇ and the component Cc ontroie . In this way, the first weight, when it is non-zero, has a sufficient value to have an influence on the cost function, but not too large so as not to be too constraining.
- the second weight wii mite has a zero value if the test trajectory Tt k remains on the road and a non-zero value otherwise. This second weight thus makes it possible to define a harder constraint in order to prevent the vehicle from leaving the road. Its non-zero value is preferably greater than that of the weight WPCIR. In this way, this value proves to be sufficiently constraining to never exceed the limits of the road, even in the event of mitigation.
- the motor vehicle 100 is traveling on a road comprising four traffic lanes, two in a first direction (the one in which the motor vehicle 100 is traveling) and two in an opposite direction.
- the first two traffic lanes are separated from the other two by a continuous white line.
- the road is separated from the shoulder by other white lines.
- the component c VOie of the cost function q k will have a very high value for the test trajectories Tti and Tt 4 which take the motor vehicle 100 off the road. It will have zero weight for the test trajectory Tt 3 which does not require the vehicle 100 to leave its traffic lane. And it will have an intermediate value for the test trajectory Tt 2 which requires vehicle 100 to cross the central solid white line.
- the component c Reference of the cost function q k makes it possible to preferentially select a test trajectory Tt k which is as close as possible to the initial trajectory T0 of the vehicle.
- This initial trajectory T0 is the one which was planned to be taken by the motor vehicle 100 before an emergency maneuver is triggered to avoid an obstacle located on this initial trajectory T0. It is calculated in a conventional manner, for example as a function of the dynamic data of the vehicle (speed, acceleration, steering angle, steering speed, etc.). It could be obtained otherwise. For example, it could be considered to be formed by the central trajectory of the lane taken by the vehicle.
- the term x comprises several states, including the state that the vehicle initially presents while it is still following the initial trajectory T0 and the emergency maneuver has not yet been triggered, and successive states included in a window prediction of at least one second, here equal to 3 seconds, if the vehicle was following the initial trajectory T0.
- x Gb ⁇ corresponds to the state that the vehicle will present if it follows the test trajectory Tt k considered, at a horizon of three seconds.
- the difference between these terms x and x Gb ⁇ therefore makes it possible to compare the states of the vehicle at several successive time steps included in the prediction window.
- w Referen ⁇ is the weight given to the component c Reference .
- the states x, x Gb ⁇ being column matrices, this term w Referen ⁇ could be a positive definite square matrix which respects the dimensionality of the problem, the values of which are predetermined and recorded in the memory of the computer 140.
- the component C ⁇ input and the component Cv arian ⁇ of the cost function q k are convex costs defined in the aforementioned document “G. Williams, P. Drews, B. Goldfain, JM Rehg and EA Theodorou, "Aggressive driving with model predictive path integral control,” 2016 IEEE International Conference on Robotics and Automation (ICRA), Sweden, 2016, pp. 1433-1440, doi: 10.1109/ICRA.2016.7487277”.
- the controlled component C is thus calculated as follows:
- a is between 0 and 1. It makes it possible to adjust the aggressiveness of the controller with respect to the variance of the process.
- the parameter l corresponds to the desired aggressiveness of the controller.
- the matrix ⁇ is a diagonal matrix comprising weights for the input variable u t and the Gaussian noise 3 ⁇ 4 used within the framework of the MPPI algorithm.
- the Cv arian ⁇ component is for its part calculated by means of the following equation: [0134] [Math.
- v corresponds to the variance of the Gaussian noise used in the context of the MPPI algorithm.
- the cost function q k could be equal to the sum of the aforementioned components and at least one other component, here called a component c Terminai .
- the component c Terminai is calculated as follows:
- the term xt corresponds to the state that the vehicle will present if it follows the test trajectory to a final state, corresponding to the end of the obstacle avoidance procedure.
- the term WTerminai is the weight given to the component CTerminai.
- the states x, xt being column matrices, this term W Terminai could be a row matrix comprising several predetermined non-zero values and stored in the memory of the computer 140.
- test Tt k the computer 140 is able to implement the MPPI algorithm and to select the optimal test trajectory (called reference trajectory T1).
- This reference trajectory T 1 is then stored in its memory.
- the trajectory chosen would be the one that would minimize the risk of collision and serious injury.
- the computer 140 changes from a nominal driving mode to an emergency driving mode.
- the nominal driving mode is that in which the vehicle is driven either manually by the driver, or autonomously by an entity of the computer.
- the motor vehicle 100 is driven so as to remain centered on its traffic lane and to maintain its speed equal to a setpoint speed (constant or determined according to the speed of a vehicle which would precede it on its taxiway).
- the question that arises at any time is to determine whether to keep the vehicle in autonomous driving mode or switch it to emergency driving mode in an attempt to avoid a potentially dangerous obstacle.
- FIG. 5 there is shown a first diagram illustrating a method that allows the computer 140 to determine, when the vehicle is in autonomous mode, whether or not it should switch to emergency driving mode.
- the computer determines the initial trajectory T0 to be followed taking into account the destination to be reached, for example in such a way that the vehicle remains centered on its lane.
- This initial trajectory T0 is calculated for a horizon of at most a few seconds but at least two seconds. Here, this initial trajectory T0 is calculated for the next three seconds.
- the computer determines, given the data D1 representative of the environment obtained, whether there is a risk that the motor vehicle 100 collides with any obstacle if it follows the initial trajectory T0. For this, the computer determines a probability of collision as a function of the position and the dynamics of the motor vehicle 100 and of each detected object occupying a cell of the grid of the representation considered.
- the computer seeks to verify whether two cumulative conditions are fulfilled. The first condition is that a risk of collision exists.
- the computer considers that there is a risk of collision if the probability of collision calculated for at least one of the detected objects (hereinafter referred to as “obstacle”) exceeds a predetermined risk threshold.
- the second condition is that a time before collision TTC with this obstacle is less than a determined time threshold t crit .
- the time before collision TTC can for example be equal to the time required for the motor vehicle 100 to strike the obstacle, taking into account its speed, that of the obstacle and the distance separating the vehicle from the obstacle.
- the time threshold tcrit is equal to the minimum among: an emergency braking time, and a driver reaction time.
- the emergency braking time corresponds for example to the time necessary to stop the motor vehicle, taking into account the fixed constraints.
- the driver's reaction time is for example a predetermined constant stored in the memory of the computer. This driver reaction time is here chosen to be equal to 2 seconds.
- the computer considers that no avoidance maneuver should be undertaken. Consequently, the vehicle remains piloted in autonomous driving mode and the method is reinitialized at the first step S1. [0165] Otherwise, the emergency driving mode is activated. Therefore, a reference trajectory T1 is calculated in the manner explained above, then the piloting actuators of the motor vehicle 100 are controlled so that the motor vehicle 100 follows this reference trajectory T1 and autonomously avoids the 'obstacle. This piloting mode is designed to remain activated for a predetermined period, for example equal to three seconds.
- FIG. 6 there is shown a second diagram illustrating a method which allows the computer 140 to determine, when the vehicle is in emergency driving mode, whether it should switch back to autonomous mode or remain in emergency driving.
- the computer 140 acquires the reference trajectory T1 stored in its memory and the data D1 representative of the environment. He is thus able to determine whether there is still a risk that the motor vehicle 100 will collide with any obstacle if it follows the reference trajectory T 1 .
- the computer 140 checks whether one or the other of several deactivation conditions are fulfilled. These conditions are not cumulative but independent.
- One of these conditions is that the emergency driving mode has been activated for a duration greater than a maximum threshold.
- This maximum threshold is preferably equal to six seconds.
- Another condition is that the trajectory is free of collision and that the motor vehicle 100 has been stable for a predefined duration (for example equal to one second).
- a predefined duration for example equal to one second.
- FIGS. 7 to 10 show an example in which the motor vehicle 100 must change driving mode. Initially, at a time to illustrated in Figure 7, the motor vehicle 100 is on the same path as an obstacle 900 (here another vehicle), but at a significant distance from the latter. It then remains piloted in autonomous mode in the center of its traffic lane, at a predefined setpoint speed. In parallel, the initial trajectory T0 and the time before impact TTC are regularly calculated.
- the computer checks whether a new obstacle is detected on the reference trajectory T1.
- a pedestrian 950 is detected at a time t 2 illustrated in figure 9.
- This new obstacle 950 being on the reference trajectory T1 at a distance such that the two cumulative conditions are fulfilled, the computer determines a second reference trajectory TT.
- This trajectory allows the motor vehicle 100 to avoid the two obstacles and to return to its initial traffic lane.
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
- Steering Control In Accordance With Driving Conditions (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
FR2108170A FR3125785B1 (fr) | 2021-07-27 | 2021-07-27 | Procédé de pilotage de véhicule et d’évitement d’obstacle |
PCT/EP2022/070878 WO2023006709A1 (fr) | 2021-07-27 | 2022-07-26 | Procede de pilotage de vehicule et d'evitement d'obstacle |
Publications (1)
Publication Number | Publication Date |
---|---|
EP4377177A1 true EP4377177A1 (fr) | 2024-06-05 |
Family
ID=77999132
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP22744233.2A Pending EP4377177A1 (fr) | 2021-07-27 | 2022-07-26 | Procede de pilotage de vehicule et d'evitement d'obstacle |
Country Status (5)
Country | Link |
---|---|
EP (1) | EP4377177A1 (fr) |
JP (1) | JP2024529993A (fr) |
CN (1) | CN118119541A (fr) |
FR (1) | FR3125785B1 (fr) |
WO (1) | WO2023006709A1 (fr) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116653932B (zh) * | 2023-06-09 | 2024-03-26 | 苏州畅行智驾汽车科技有限公司 | 一种车辆自动紧急转向的实现方法及相关装置 |
CN116461513B (zh) * | 2023-06-16 | 2023-09-22 | 中国第一汽车股份有限公司 | 车辆及其碰撞预警方法 |
CN117935615B (zh) * | 2024-03-25 | 2024-07-09 | 中国汽车技术研究中心有限公司 | 一种基于全身损伤度量减轻人车碰撞中行人损伤的方法 |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR2007743A3 (en) | 1968-05-03 | 1970-01-09 | Seewer Gustave | Food paste shaper |
DE102010006214A1 (de) * | 2010-01-29 | 2011-08-04 | Bayerische Motoren Werke Aktiengesellschaft, 80809 | Notbremsassistent zum automatischen Abbremsen eines Fahrzeugs zur Kollisionsvermeidung oder Kollisionsfolgenminderung |
DE102014212898A1 (de) * | 2014-07-03 | 2016-01-07 | Robert Bosch Gmbh | Verfahren zum Ermitteln einer Notfall-Trajektorie und Verfahren zum teilautomatisierten oder automatisierten Führen eines Ego-Fahrzeugs |
FR3086910B1 (fr) * | 2018-10-03 | 2020-09-25 | Psa Automobiles Sa | Securisation d'une fonction d'aide a l'evitement par bornage temporel |
-
2021
- 2021-07-27 FR FR2108170A patent/FR3125785B1/fr active Active
-
2022
- 2022-07-26 JP JP2024506153A patent/JP2024529993A/ja active Pending
- 2022-07-26 CN CN202280062599.4A patent/CN118119541A/zh active Pending
- 2022-07-26 WO PCT/EP2022/070878 patent/WO2023006709A1/fr active Application Filing
- 2022-07-26 EP EP22744233.2A patent/EP4377177A1/fr active Pending
Also Published As
Publication number | Publication date |
---|---|
FR3125785B1 (fr) | 2024-01-19 |
FR3125785A1 (fr) | 2023-02-03 |
CN118119541A (zh) | 2024-05-31 |
JP2024529993A (ja) | 2024-08-14 |
WO2023006709A1 (fr) | 2023-02-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP4377177A1 (fr) | Procede de pilotage de vehicule et d'evitement d'obstacle | |
EP3627270B1 (fr) | Dispositif électronique de détermination d'une trajectoire d'arrêt d'urgence d'un véhicule autonome, véhicule et procédé associés | |
US11555927B2 (en) | System and method for providing online multi-LiDAR dynamic occupancy mapping | |
US11587461B2 (en) | Context-sensitive adjustment of off-road glance time | |
EP3810473B1 (fr) | Procédé et système de gestion d'un changement de voie d'un véhicule autonome ou partiellement autonome | |
EP1544022B1 (fr) | Dispositif et méthode d'assistance d'un opérateur | |
EP3994042A1 (fr) | Procede de determination d'une trajectoire d'evitement d'un vehicule automobile | |
EP3568803A1 (fr) | Procede de pilotage d'un vehicule automobile autonome | |
FR2887669A3 (fr) | Procede et systeme embarque de prediction de choc entre un vehicule et un pieton | |
WO2022175034A1 (fr) | Procédé d'activation d'un système d'évitement d'obstacle pour véhicule automobile | |
FR3086075A1 (fr) | Systeme electronique de supervision d'un vehicule autonome, procede et programme d'ordinateur associes | |
WO2022018110A1 (fr) | Procédé de détermination d'une trajectoire d'un véhicule automobile | |
WO2022233739A1 (fr) | Procédé de commande d'un véhicule autonome | |
WO2022175103A1 (fr) | Procédé d'évitement d'obstacles | |
WO2018069061A1 (fr) | Procede d'elaboration d'une consigne de supervision de pilotage d'un organe de conduite d'un vehicule automobile | |
EP4251487A1 (fr) | Procédé et dispositif d'adaptation d'une trajectoire d'accélération de consigne d'un régulateur de vitesse véhicule adaptatif d'un véhicule autonome | |
FR3108878A1 (fr) | Dispositif d’aide à la manœuvre d’évitement d’une cible destiné à être incorporé dans un véhicule automobile | |
EP4223604A1 (fr) | Procédé de détection de danger dans l'environnement d'un véhicule automobile | |
EP4015332B1 (fr) | Méthode de supervision pour le contrôle d'un véhicule automobile autonome | |
EP3830741B1 (fr) | Assistance à la conduite pour le controle d'un vehicule automobile comprenant des étappes parallèles de traitement des images transformées. | |
WO2024052561A1 (fr) | Procédé de détection d'une collision prochaine, procédé d'étalonnage d'un système de détection de collision et véhicule automobile associé | |
EP4453512A1 (fr) | Procédé de modélisation d'un environnement tactique d'un véhicule automobile | |
FR3092914A1 (fr) | Procédé de détermination de la trajectoire d'un véhicule comprenant quatre roues directrices | |
EP3895147A1 (fr) | Procédé de détermination d'une valeur courante d'un paramètre d'occupation relatif à une portion d'un espace situé à proximité d'un véhicule terrestre à moteur | |
FR3106798A1 (fr) | Procédé de gestion d'un freinage autonome d'urgence. |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
17P | Request for examination filed |
Effective date: 20240213 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
RAP3 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: NISSAN MOTOR CO., LTD. Owner name: INSTITUT NATIONAL DE RECHERCHE EN INFORMATIQUE ETEN AUTOMATIQUE Owner name: AMPERE SAS |