Method for determining a trajectory of a motor vehicle
A method for determining a trajectory of a motor vehicle includes identifying a plurality of objects present in the surroundings of the motor vehicle. For each object, the method includes: a) determining a speed of impact between the object of interest and the motor vehicle, b) determining a risk of injury in the event of a collision with the motor vehicle at the determined impact speed, c) determining the probability of a collision resulting in an injury between the object of interest and the motor vehicle, depending on the determined risk of injury. The method subsequently includes determining a plurality of possible trajectories for the motor vehicle, and determining the trajectory to be followed by the motor vehicle by optimising a cost function which depends on the determined collision probabilities and which minimises the risk of collision resulting in an injury between each object and the motor vehicle.
1 . A method for determining a trajectory of a motor vehicle, comprises:
identifying, via a computer in the motor vehicle, objects present in an environment of the motor vehicle, the identifying including for each identified object:
a) determining a distance between the motor vehicle and the object using a range-finding sensor disposed on the motor vehicle,
b) determining a speed of impact between the object and the motor vehicle,
c) determining a risk of injury in an event of collision between the object concerned and the motor vehicle at the determined speed of impact, and
d) determining a probability of collision resulting in an injury as a function of the determined risk of injury, then
determining a trajectory to be taken by the motor vehicle by optimizing a cost function which depends on determined probabilities of collision resulting in an injury and which makes it possible to minimize the risk of collision resulting in an injury between each object and the motor vehicle;
transmitting the trajectory to be taken to a processing circuitry configured to perform autonomous driving; and
autonomously modifying a current trajectory of the motor vehicle into the trajectory to be taken with the processing circuitry,
wherein said probability of collision resulting in an injury is a function of a distance separating the motor vehicle and said object, said probability of collision resulting in an injury being calculated as a function of a probability of occupancy of a cell of a grid by said object, said grid comprising a plurality of cells representing the environment of the motor vehicle,
wherein the risk of injury associated with each object is determined as a function of a plurality of data which correspond respectively to probabilities of the injury being more or less serious, each probability depending on a nature of the identified object, and
wherein said plurality of data comprises a probability of death, a probability of serious injury and a probability of slight injury, and wherein the risk of injury associated with each object is determined by calculating a weighted sum of the probabilities of death, of serious injuries and of slight injuries associated with the determined speed of impact.
2 . The method as claimed in claim 1 , wherein the cost function depends on kinematic data of the motor vehicle, on a distance between the motor vehicle and each object, and on the probability of collision resulting in an injury determined for each object.
3 . The method as claimed in claim 1 , wherein the optimizing of the cost function is performed so as to observe at least one constraint relating to dynamic characteristics of the motor vehicle.
4 . The method as claimed in claim 1 , wherein the determining the trajectory to be taken by the motor vehicle is based on a minimizing of the cost function, said cost function being higher when the risk of injury caused in the event of collision is great.
5 . A method comprising:
the method as claimed in claim 1 ; and
displaying the trajectory to be taken on a screen inside the motor vehicle for a driver.
6 . The method as claimed in claim 5 , further comprising:
alerting the driver of the motor vehicle implemented by the computer as a function of the risk of collision or of injury caused by a collision between the object and the motor vehicle.
7 . The method as claimed in claim 6 , wherein the alerting is performed when the cost function is above a predetermined threshold.
8 . The method as claimed in claim 7 , wherein the alerting comprises emission of an audible or haptic or visual alert.
9 . The method as claimed in claim 1 , wherein the risk of injury is determined for the speed of impact relative to an impacted object type with a risk-of-injury curve.
10 . A method for determining a trajectory of a motor vehicle, comprises:
identifying, via a computer in the motor vehicle, objects present in an environment of the motor vehicle, the identifying including for each identified object:
a) determining a distance between the motor vehicle and the object using a range-finding sensor disposed on the motor vehicle,
b) determining a speed of impact between the object and the motor vehicle,
c) determining a risk of injury in an event of collision between the object concerned and the motor vehicle at the determined speed of impact, and
d) determining a probability of collision resulting in an injury as a function of the determined risk of injury, then
determining a trajectory to be taken by the motor vehicle by optimizing a cost function which depends on determined probabilities of collision resulting in an injury and which makes it possible to minimize the risk of collision resulting in an injury between each object and the motor vehicle;
transmitting the trajectory to be taken to a processing circuitry configured to perform autonomous driving;
autonomously modifying, by the processing circuitry, a current trajectory of the motor vehicle into the trajectory to be taken,
wherein said probability of collision resulting in an injury is a function of a distance separating the motor vehicle and said object, said probability of collision resulting in an injury being calculated as a function of a probability of occupancy of a cell of a grid by said object, said grid comprising a plurality of cells representing the environment of the motor vehicle,
wherein the risk of injury associated with each object is determined as a function of a plurality of data which correspond respectively to probabilities of the injury being more or less serious, each probability depending on a nature of the identified object, and
wherein said plurality of data comprises a probability of death, a probability of serious injury and a probability of slight injury, and wherein the risk of injury associated with each object is determined by calculating a weighted sum of the probabilities of death, of serious injuries and of slight injuries associated with the determined speed of impact.
11 . The method of claim 10 , wherein the risk of injury associated with each object is determined as a function of a plurality of data which correspond respectively to probabilities of the injury being more or less serious, each probability depending on a nature of the identified object.
12 . The method of claim 11 , wherein said plurality of data comprises a probability of death, a probability of serious injury and a probability of slight injury, and wherein the risk of injury associated with each object is determined by calculating a weighted sum of the probabilities of death, of serious injuries and of slight injuries associated with the determined speed of impact.
13 . The method of claim 10 , wherein the cost function depends on kinematic data of the motor vehicle, on a distance between the motor vehicle and each object, and on the probability of collision resulting in an injury determined for each object.
14 . The method of claim 10 , wherein the optimizing of the cost function is performed so as to observe at least one constraint relating to dynamic characteristics of the motor vehicle.
15 . The method of claim 10 , wherein the determining the trajectory to be taken by the motor vehicle is based on a minimizing of the cost function, said cost function being higher when the risk of injury caused in the event of a collision is great.
16 . The method of claim 10 , wherein the risk of injury is determined for the speed of impact relative to an impacted object type with a risk-of-injury curve.