Fused sensor view for self-driving truck
AssigneeUatc, LLC
InventorsMichael Carter, Soren Juelsgaard
Life of this patent
Estimating the term…
Abstract
An autonomous control system of a self-driving semi-truck can monitor a dynamic orientation of a cargo trailer in relation to a tractor of the semi-trailer truck. Based on the dynamic orientation of the cargo trailer, the control system can dynamically generate a coordinate transform between a first reference frame of a first set of sensors mounted to the tractor, and a second reference frame of a second set of sensors mounted to the cargo trailer, and execute the dynamically generated coordinate transform on sensor data from the second set of sensors to generate a fused sensor view of a surrounding environment of the self-driving semi-truck.
Claims20
A self-driving semi-truck comprising:
- a tractor comprising a drive system;
- a first set of sensors mounted to the tractor;
- a cargo trailer comprising coupled to the tractor
- a second set of sensors mounted to the cargo trailer;
- and
- an autonomous control system comprising processing resources executing in instruction set, causing the autonomous control system to:
- monitor a dynamic orientation of the cargo trailer in relation to the tractor;
- based on the dynamic orientation of the cargo trailer, dynamically generate a coordinate transform between a first reference frame of the first set of sensors mounted to the tractor and a second reference frame of the second set of sensors mounted to the cargo trailer;
- and
- execute the dynamically generated coordinate transform on sensor data from the second set of sensors to generate a fused sensor view of a surrounding environment of the self-driving semi-truck, wherein executing the dynamically generated coordinate transform on the sensor data from the second set of sensors comprises processing the sensor data from the second set of sensors to match local coordinates of at least one of the first set of sensors.
An autonomous control system for a self-driving semi-truck, comprising:
- one or more processing resources;
- and
- a memory storing an instruction set that, when executed by the one or more processing resources, causes the one or more processing resources to:
- monitor a dynamic orientation of a cargo trailer in relation to a tractor of the semi-trailer truck;
- based on the dynamic orientation of the cargo trailer, dynamically generate a coordinate transform between a first reference frame of a first set of sensors mounted to the tractor, and a second reference frame of a second set of sensors mounted to the cargo trailer;
- and
- execute the dynamically generated coordinate transform on sensor data from the second set of sensors to generate a fused sensor view of a surrounding environment of the self-driving semi-truck, wherein executing the dynamically generated coordinate transform on the sensor data from the second set of sensors comprises processing the sensor data from the second set of sensors to match local coordinates of at least one of the first set of sensors.
A non-transitory computer readable medium storing instructions that, when executed by one or more processors of a self-driving semi-truck, cause the one or more processors to:
- monitor a dynamic orientation of a cargo trailer in relation to a tractor of the semi-trailer truck;
- based on the dynamic orientation of the cargo trailer, dynamically generate a coordinate transform between a first reference frame of a first set of sensors mounted to the tractor, and a second reference frame of a second set of sensors mounted to the cargo trailer;
- and
- execute the dynamically generated coordinate transform on sensor data from the second set of sensors to generate a fused sensor view of a surrounding environment of the self-driving semi-truck, wherein executing the dynamically generated coordinate transform on the sensor data from the second set of sensors comprises processing the sensor data from the second set of sensors to match local coordinates of at least one of the first set of sensors.
Dependencies are inferred from the claim text.