Back to results
US 12,479,405 B2Granted
System and method for surface adaptive braking
AssigneeVolvo Truck Corporation
InventorChidambaram Subramanian
Life of this patent
Estimating the term…
Abstract
Systems, methods, and computer-readable storage media for using neural networks to ensure the braking capabilities of articulated vehicles are adapted to prevent jackknifing. A system can receive operational parameters associated with both a vehicle and a trailer being towed by the vehicle. The system can also identify a current surface condition and predict, using a neural network, road conditions for a portion of the road which the vehicle is approaching. When distinctions between current and predicted, future conditions are defined, and the system can cause modification of the operational parameters of the vehicle and/or the trailer.
Claims20
A method comprising:
- receiving, at a processor within a vehicle, from a plurality of tire sensors associated with tires of the vehicle, first road condition data, wherein:
- the vehicle is towing a trailer;
- the vehicle has first operational parameters which are associated with braking of the vehicle;
- the trailer has second operational parameters which are associated with braking of the trailer;
- determining, via the processor and based on the first road condition data, a current surface condition;
- receiving, at the processor from a plurality of other vehicles, second road condition data;
- executing, via the processor, a machine learning algorithm, wherein:
- inputs to the machine learning algorithm comprise the first road condition data and the second road condition data;
- and
- outputs of the machine learning algorithm comprise an approaching surface condition;
- and
- modifying, via the processor, at least one of the first operational parameters and the second operational parameters based on:
- a distinction between the current surface condition and the approaching surface condition;
- and
- distinct slip ratios of the vehicle and the trailer based on the current surface condition.
12 more elements
An articulated vehicle, comprising:
- a trailer;
- a truck configured to pull the trailer;
- a plurality of tire sensors;
- a processor;
- a non-transitory computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising:
- receiving first operational parameters associated with braking of the truck;
- receiving second operational parameters associated with braking of the trailer;
- receiving, from the plurality of tire sensors, first road condition data;
- determining, via the processor and based on the first road condition data, a current surface condition;
- receiving, from a plurality of other vehicles, second road condition data;
- executing a machine learning algorithm, wherein:
- inputs to the machine learning algorithm comprise the first road condition data and the second road condition data;
- and
- outputs of the machine learning algorithm comprise an approaching surface condition;
- and
- generating an operating mode of the vehicle, the operating mode being based the current surface condition, the approaching surface condition, the first operational parameters, and the second operational parameters, the operating mode being one of a plurality of modes selected from a list comprising:
- a normal mode, where no changes to at least one operational parameter of the first operational parameters and the second operational parameters are needed based on a distinction between the current surface condition and the approaching surface condition;
- a warning mode with a severity, where at least one operational parameter of the first operational parameters and the second operational parameters is to be modified based on a distinction between the current surface condition and the approaching surface condition;
- and
- a poor surface mode, where at least one operational parameter of the first operational parameters and the second operational parameters is to be modified based on the current surface condition, the first operational parameters, and the second operational parameters;
- and
- modifying at least one of the first operational parameters and the second operational parameters based on:
- a distinction between the current surface condition and the approaching surface condition;
- and
- distinct slip ratios of the truck and the trailer based on the current surface condition.
22 more elements
A non-transitory computer-readable storage medium stored within a vehicle, the non-transitory computer-readable storage medium having instructions stored which, when executed by a processor, cause the processor to perform operations comprising:
- receiving, at the processor within the vehicle, from a plurality of tire sensors associated with tires of the vehicle, first road condition data, wherein:
- the vehicle is towing a trailer;
- the vehicle has first operational parameters which are associated with braking of the vehicle;
- and
- the trailer has second operational parameters which are associated with braking of the trailer;
- determining, via the processor and based on the first road condition data, a current surface condition;
- receiving, at the processor from a plurality of other vehicles, second road condition data;
- executing, via the processor, a machine learning algorithm, wherein:
- inputs to the machine learning algorithm comprise the first road condition data and the second road condition data;
- and
- outputs of the machine learning algorithm comprise an approaching surface condition;
- and
- modifying, via the processor, at least one of the first operational parameters and the second operational parameters based on:
- a distinction between the current surface condition and the approaching surface condition;
- and
- distinct slip ratios of the vehicle and the trailer based on the current surface condition.
13 more elements
Dependencies are inferred from the claim text.