Method for controlling an autonomous vehicle
A method controls an autonomous vehicle equipped with at least one perception unit and a first map including stored digital data representing the actual infrastructure of the environment of the autonomous vehicle. The method includes defining a first trajectory of the autonomous vehicle and a first associated kinematic profile, detecting, from data transmitted by the perception unit, a situation to be optimized on a given segment of the first trajectory located in front of the autonomous vehicle, optimizing at least one element from the first map and the first kinematic profile, optimizing the first map including determining a local map on the given segment, and/or optimizing the first kinematic profile including a determination of a second kinematic profile associated with the given segment, and controlling the displacement of the autonomous vehicle over the given segment taking into account the local map and/or the second kinematic profile.
1 . A method for controlling an autonomous vehicle equipped with at least one perception means and a first map comprising stored digital data representing an actual road infrastructure of an environment of the autonomous vehicle, the method comprising:
defining a first trajectory of the autonomous vehicle and a first associated kinematic profile;
detecting, from data transmitted by the at least one perception means, a situation to be optimized on a given segment of the first trajectory, the given segment being located in front of the autonomous vehicle, over a distance that is less than a maximum detection distance of the at least one perception means;
optimizing at least one element from the first map, the optimizing the at least one element from the first map comprising determining a local map on the given segment, the local map including a modified road infrastructure that replaces the actual road infrastructure in the given segment; and
controlling a movement of the autonomous vehicle on the given segment taking into account the local map.
2 . The control method as claimed in claim 1 , wherein determining a local map allows, by means of Bezier curves, a new curve of the given segment to be determined between an entry point and an exit point of the given segment, and the new curve has a continuity with the first trajectory at the entry point and at the exit point.
3 . The control method as claimed in claim 1 , wherein the optimizing the at least one element includes optimizing the first kinematic profile, the optimizing the first kinematic profile includes determining a second kinematic profile associated with the given segment, with at least one parameter of the second kinematic profile being different from a parameter of the first kinematic profile, wherein the determining the second kinematic profile associated with the given segment comprises computing a maximum collision-free speed threshold from data originating from the at least one perception means and the second kinematic profile comprises maximum speeds below the maximum collision-free speed threshold.
4 . The control method as claimed in claim 3 , wherein the maximum collision-free speed threshold is computed by solving an equation in which the maximum collision-free speed threshold is equal to a square root of a product of a braking value required to reach the maximum collision-free speed threshold by twice the maximum detection distance of the at least one perception means.
5 . The control method as claimed in claim 1 , wherein the detecting the situation to be optimized comprises measuring a holding time, during which the autonomous vehicle remains in a situation to be optimized and comparing the holding time with a triggering threshold associated with said situation, and the optimization is executed when the holding time is greater than the triggering threshold.
6 . The control method as claimed in claim 1 , wherein a set of predefined situations is stored in an electronic memory, and the detecting the situation to be optimized comprises comparing a perception originating from the at least one perception means with the set of predefined situations.
7 . The control method as claimed in claim 6 , wherein the set of predefined situations comprises at least one of negotiating a roundabout with two empty lanes, entering a roundabout in dense traffic conditions, two traffic lanes merging into a single lane, crossing a gridlocked junction, and overtaking a very slow vehicle on a two-way road comprising a single lane in each direction.
8 . The control method as claimed in claim 3 , wherein the second kinematic profile comprises at least one of a maximum speed at least 20% higher, a maximum acceleration at least 200% higher, and a jerk at least 1,000% higher than the first kinematic profile.
9 . A device for controlling an autonomous vehicle, the autonomous vehicle being equipped with motion actuators, the device comprising:
hardware and/or software elements configured to implement the control method as claimed in claim 1 .
10 . An autonomous vehicle, comprises:
the control device as claimed in claim 9 .
11 . A non-transitory computer-readable data storage medium storing a computer that, when executed by a computer, causes the computer to execute the control method as claimed in claim 1 .
12 . The control method as claimed in claim 1 , wherein the at least one element from the first map is a two-lane roundabout on the first map that is modified to be a one-lane roundabout on the local map.
13 . The control method as claimed in claim 1 , wherein the actual road infrastructure on the first map includes a layout of navigable portions of the road, a number of lanes of the road, speed limits of the portions of the road, markings on the road and locations of the markings, traffic signs, traffic lights, and roundabouts.