Handling maneuver limits for autonomous driving systems
A method includes identifying mass distribution data of an autonomous vehicle (AV). The mass distribution data is associated with a first load proximate a first distal end of a first axle of the AV and a second load proximate a second distal end of the first axle of the AV. The method further includes determining, based on the mass distribution data, one or more handling maneuver limits for the AV. The method further includes causing the AV to travel a route based on the one or more handling maneuver limits.
1. A method comprising:
identifying mass distribution data of an autonomous vehicle (AV), wherein the mass distribution data comprises a first load value at a first distal end of a first axle of the AV and a second load value at a second distal end of the first axle of the AV;
selecting, based on the mass distribution data and road map data, a route from a starting location to a destination location;
determining an output corresponding to the AV travelling the route, wherein the output corresponding to the AV traveling the route comprises a maximum first parameter value and a maximum second parameter value;
determining, based on the first load value at the first distal end of the first axle and the second load value at the second distal end of the first axle, one or more handling maneuver limits for the AV to travel the route;
determining, based on the one or more handling maneuver limits, an updated output corresponding to the AV travelling the route, wherein the updated output corresponding to the AV traveling the route comprises an updated first parameter value and an updated second parameter value; and
causing the AV to travel the route based on the updated first parameter value and the updated second parameter value associated with the one or more handling maneuver limits.
2. The method of claim 1 , wherein the one or more handling maneuver limits are further determined based on one or more of:
a vertical center of gravity (COG) of a trailer of the AV;
a lateral COG of the trailer of the AV; or
a longitudinal COG of the trailer of the AV.
3. The method of claim 1 , wherein at least one of:
the first load value is a first mass value associated with the first distal end of the first axle and the second load value is a second mass value associated with the second distal end of the first axle; or
the one or more handling maneuver limits are further determined based on a ratio of the first load value to the second load value.
4. The method of claim 1 , wherein the one or more handling maneuver limits are further determined based on one or more of:
moment of inertia data of the AV; or
roll stiffness data of the AV.
5. The method of claim 1 , wherein the determining of the one or more handling maneuver limits comprises receiving, from a physics model, corresponding output of the one or more handling maneuver limits responsive to providing at least the first load value at the first distal end of the first axle and the second load value at the second distal end of the first axle of the mass distribution data to the physics model, wherein the physics model describes dynamical response of the AV to forces on the AV, the forces being associated with one or more of corresponding type of acceleration, jerk, turning, or corresponding type of braking.
6. The method of claim 5 , wherein the forces are further associated with one or more of a corresponding type of road bank or wind.
7. The method of claim 1 , wherein the determining of the one or more handling maneuver limits comprises selecting the one or more handling maneuver limits from a look-up table based on the mass distribution data.
8. The method of claim 1 , wherein the determining of the one or more handling maneuver limits is based on historical sensor data of one or more AVs and historical handling maneuvers of the one or more AVs.
9. The method of claim 1 further comprising selecting the route based at least in part on one or more of the mass distribution data or the one or more handling maneuver limits for the AV.
10. The method of claim 1 , wherein the one or more handling maneuver limits comprises:
type of braking of the AV;
acceleration limits of the AV;
jerk limits of the AV;
yaw rate limits of the AV;
type of evasive maneuvers of the AV;
lane selection of the AV; or
turning limits of the AV.
11. The method of claim 1 , wherein the causing of the AV to travel the route comprises generating a plan to travel the route based on the one or more handling maneuver limits.
12. The method of claim 1 , wherein the causing of the AV to travel the route comprises generating short time horizon route data for travelling a segment of the route based on the one or more handling maneuver limits.
13. The method of claim 1 , wherein the mass distribution data is of a trailer of the AV.
14. The method of claim 1 , wherein:
the output corresponding to the AV traveling the route comprises the maximum first parameter value and the maximum second parameter value without taking into account the mass distribution data of the AV; and
the updated output corresponding to the AV traveling the route comprises the updated first parameter value and the updated second parameter value taking into account the mass distribution data of the AV.
15. The method of claim 1 , wherein:
the maximum first parameter value and the updated first parameter value correspond to lateral acceleration values; and
the maximum second parameter value and the updated second parameter value correspond to longitudinal acceleration values.
16. The method of claim 15 , wherein:
the lateral acceleration values correspond to one or more of acceleration to a side, turning, cornering, evasive maneuver, or changing lanes; and
the longitudinal acceleration values correspond to one or more of acceleration within a lane, acceleration towards a front of the AV, or adjusting speed without turning.
17. A system comprising:
a memory device; and
a processing device, coupled to the memory device, wherein the processing device is to:
identify mass distribution data of an autonomous vehicle (AV), wherein the mass distribution data comprises a first load value at a first distal end of a first axle of the AV and a second load value at a second distal end of the first axle of the AV;
select, based on the mass distribution data and road map data, a route from a starting location to a destination location;
determine an output corresponding the AV travelling the route, wherein the output corresponding to the AV traveling the route comprises a maximum first parameter value and a maximum second parameter value;
determine, based on the first load value at the first distal end of the first axle and the second load value at the second distal end of the first axle, one or more handling maneuver limits for the AV to travel the route;
determining, based on the one or more handling maneuver limits, an updated output corresponding to the AV travelling the route, wherein the updated output corresponding to the AV traveling the route comprises an updated first parameter value and an updated second parameter value; and
cause the AV to travel the route based on the updated first parameter value and the updated second parameter value associated with the one or more handling maneuver limits.
18. The system of claim 17 , wherein the one or more handling maneuver limits are further determined based on one or more of:
a vertical center of gravity (COG) of a trailer of the AV;
a lateral COG of the trailer of the AV;
a longitudinal COG of the trailer of the AV;
a ratio of the first load value to the second load value;
moment of inertia data of the AV; or
roll stiffness data of the AV.
19. The system of claim 17 , wherein to determine the one or more handling maneuver limits, the processing device is to receive, from a physics model, corresponding output of the one or more handling maneuver limits responsive to providing at least the first load value at the first distal end of the first axle and the second load value at the second distal end of the first axle of the mass distribution data to the physics model, wherein the physics model describes dynamical response of the AV to forces on the AV, the forces being associated with one or more of corresponding type of acceleration, jerk, turning, or corresponding type of braking.
20. A non-transitory computer-readable storage medium having instructions stored thereon that, when executed by a processing device, cause the processing device to:
identify mass distribution data of an autonomous vehicle (AV), wherein the mass distribution data comprises a first load value at a first distal end of a first axle of the AV and a second load value at a second distal end of the first axle of the AV;
selecting, based on the mass distribution data and road map data, a route from a starting location to a destination location;
determining output corresponding to the AV travelling the route, wherein the output corresponding to the AV traveling the route comprises a maximum first parameter value and a maximum second parameter value;
determine, based on the first load value at the first distal end of the first axle and the second load value at the second distal end of the first axle, one or more handling maneuver limits for the AV to travel the route;
determining, based on the one or more handling maneuver limits, an updated output corresponding to the AV travelling the route, wherein the updated output corresponding to the AV traveling the route comprises an updated first parameter value and an updated second parameter value; and
cause the AV to travel the route based on the updated first parameter value and the updated second parameter value associated with the one or more handling maneuver limits.
21. The non-transitory computer-readable storage medium of claim 20 , wherein to determine the one or more handling maneuver limits, the processing device is to select the one or more handling maneuver limits from a look-up table based on the mass distribution data.
22. The non-transitory computer-readable storage medium of claim 20 , wherein the processing device is to determine the one or more handling maneuver limits based on historical sensor data of one or more AVs and historical handling maneuvers of the one or more AVs.
23. The non-transitory computer-readable storage medium of claim 20 , wherein the processing device is to select the route based at least in part on one or more of the mass distribution data or the one or more handling maneuver limits for the AV.