Dynamic wheel configuration adjustment based on environmental conditions
Systems and techniques for determining adverse traction conditions currently and/or likely to be being experienced by a vehicle and mitigating such conditions are described. Using sensor data, a vehicle computing device may determine an adverse traction conditions and various attributes of the condition. The vehicle computing device may adjust individual wheel configurations to address this condition, for example, by increasing or decreasing cross-corner wheels, rapidly and repeatedly increasing and decreasing particular wheels, and/or steering wheel individual to increase traction overall and/or reduce the speed of the vehicle (e.g., without using brakes). When normal traction conditions are recognized, the vehicle computing system may return the wheel suspension and steering configurations back to normal.
1 . A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing instructions executable by the one or more processors, wherein the instructions, when executed, cause the system to perform operations comprising:
receiving sensor data associated with an environment from a plurality of sensor systems of a vehicle traversing an environment;
determining, based at least in part on the sensor data, an adverse traction condition associated with a surface in the environment on which the vehicle is predicted to traverse;
predicting, based at least in part on the adverse traction condition and a planned vehicle trajectory:
a first traction condition for a first wheel of a plurality of wheels configured at the vehicle, and
a second traction condition for a second wheel of the plurality of wheels, wherein the second traction condition is distinct from the first traction condition;
determining, based at least in part on a first traction condition, that the first wheel is associated with reduced traction;
based at least in part on determining the first wheel is associated with reduced traction:
reducing a first load at the first wheel;
reducing a second load at a third wheel of the plurality of wheels that is a cross-corner wheel relative to the first wheel;
increasing a third load at the second wheel; and
increasing a fourth load at a fourth wheel of the plurality of wheels; and
controlling the vehicle in the environment based at least in part on the planned vehicle trajectory.
2 . The system of claim 1 , wherein the operations further comprise repeatedly modifying the first load at the first wheel and the second load at the third wheel.
3 . The system of claim 2 , wherein the operations further comprise:
determining a first plurality of wheel tractions corresponding to a first plurality of loads at the first wheel while repeatedly modifying the first load at the first wheel; and
configuring the first wheel at a fifth load based at least in part on the first plurality of wheel tractions.
4 . The system of claim 3 , wherein the operations further comprise configuring the third wheel at a sixth load based at least in part on the fifth load.
5 . The system of claim 1 , wherein the first wheel is configured proximate to a leading edge of the vehicle.
6 . One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors, perform operations comprising:
receiving data captured by a sensor associated with a vehicle operating in an environment;
determining, based at least in part on the data, an adverse traction condition associated with a surface in the environment;
predicting, based at least in part on the data and the adverse traction condition:
a first traction condition for a first wheel of a plurality of wheels configured at the vehicle, and
a second traction condition for a second wheel of the plurality of wheels, wherein the second traction condition is distinct from the first traction condition;
implementing a first suspension configuration of the first wheel based at least in part on the first traction condition;
implementing a second suspension configuration of the second wheel based at least in part on the second traction condition, wherein the first suspension configuration is distinct from the second suspension configuration, wherein the first wheel is a cross corner wheel relative to the second wheel; and
controlling the vehicle in the environment based at least in part on the first suspension configuration and the second suspension configuration.
7 . The one or more non-transitory computer-readable media of claim 6 , wherein controlling the vehicle in the environment comprises autonomously controlling the vehicle based at least in part on a trajectory comprising a representation of the surface.
8 . The one or more non-transitory computer-readable media of claim 6 , wherein:
implementing the first suspension configuration comprises reducing a first load of the first wheel; and
implementing the second suspension configuration comprises increasing a second load of the second wheel.
9 . The one or more non-transitory computer-readable media of claim 6 , wherein:
the data comprises wheel sensor data for the first wheel; and
determining the adverse traction condition comprises determining the first traction condition based at least in part on the wheel sensor data for the first wheel.
10 . The one or more non-transitory computer-readable media of claim 6 , wherein the operations further comprise:
receiving second data captured by the sensor;
determining, based at least in part on the second data, that the first wheel is associated with increased traction; and
based at least in part on determining that the first wheel is associated with increased traction, implementing a third suspension configuration of the first wheel and a fourth suspension configuration of the second wheel.
11 . The one or more non-transitory computer-readable media of claim 10 , wherein:
implementing the first suspension configuration comprises reducing a first load of the first wheel;
implementing the second suspension configuration comprises increasing a second load of the second wheel;
implementing the third suspension configuration comprises increasing the first load of the first wheel; and
implementing the second suspension configuration comprises reducing the second load of the second wheel.
12 . The one or more non-transitory computer-readable media of claim 6 , wherein the first suspension configuration comprises repeatedly modifying a first load of the first wheel.
13 . The one or more non-transitory computer-readable media of claim 12 , wherein the second suspension configuration comprises repeatedly modifying a second load of a third wheel of the plurality of wheels in phase with the repeatedly modifying of the first load.
14 . The one or more non-transitory computer-readable media of claim 13 , wherein the first traction condition is associated with reduced traction.
15 . A method comprising:
receiving data captured by a sensor associated with a vehicle operating in an environment;
determining, based at least in part on the data, an adverse traction condition;
predicting, based at least in part on the adverse traction condition and a planned vehicle trajectory:
a first traction condition for a first wheel of a plurality of wheels configured at the vehicle, and
a second traction condition for a second wheel of a plurality of wheels, wherein the second traction condition is distinct from the first traction condition;
implementing a first wheel configuration of the first wheel based at least in part on the first traction condition;
implementing a second wheel configuration of the second wheel based at least in part on the second traction condition, wherein the first wheel configuration is distinct from the second wheel configuration, wherein the first wheel is a cross corner wheel relative to the second wheel; and
controlling the vehicle in the environment based at least in part on the first wheel configuration and the second wheel configuration.
16 . The method of claim 15 , wherein:
the first wheel configuration comprises steering the first wheel in a first direction; and
the second wheel configuration comprises steering the second wheel in a second direction distinct from the first direction.
17 . The method of claim 15 , wherein:
the first wheel configuration comprises steering the first wheel toward a third wheel configured at a same axle of the vehicle as the first wheel; and
the method further comprises steering the third wheel towards the first wheel.
18 . The method of claim 15 , wherein:
the first wheel configuration comprises steering the first wheel away from a third wheel configured at a same axle of the vehicle as the first wheel; and
the method further comprises steering the third wheel away from the first wheel.
19 . The method of claim 15 , further comprising determining the first wheel configuration based at least in part on a plurality of traction measurements associated with a plurality of loads applied to the first wheel.
20 . The method of claim 15 , wherein the adverse traction condition comprises an aquaplane condition.