patent.fyi
Applications  /  US 2026/0356363
United States Patent Application Publication

US 2026/0356363 A1

Published
Nov 12, 2026
Filed
Apr 6, 2026
Earliest date on the face
May 7, 2025
Classification
B60W 30/165
First published here
Nov 20, 2026

Generated automatically. Not reviewed by a person. Not legal advice or an opinion.

Section 1 · machine-generated

What if?

Questions about how individual parts of claim 1 might be changed. A question may describe something different from what the claim language recites, or a version of it; no view is offered on which.

1.1Hardwired vehicle control logic

What ifWhat if fixed-function logic gates performed the vehicle-control calculations without an instruction-executing processor?
Claim language“a processor”

A custom digital circuit uses adders and comparators to score tracked vehicles and compare their trajectories with route coordinates. A hardwired state machine selects a trajectory and feeds its coordinates to a fixed-point steering circuit.

1.2Road edge confidence trigger

What ifWhat if the controller activated the fallback when confidence in the detected road edges stayed low for 0.8 seconds?
Claim language“a lane marking is missing for at least a threshold distance”

A lidar estimates the left and right road edges from curb profiles and changes in surface height. The controller activates fallback tracking when either edge estimate stays below a confidence score of 0.4 for 0.8 seconds.

1.3Live drivable surface corridor

What ifWhat if current sensor measurements and the planned route heading defined the region of interest without stored lane records?
Claim language“historical traffic lane information”

The controller projects the next 40 meters of the planned route onto a local grid of drivable surface cells derived from camera and lidar measurements. It clips a corridor extending 2 meters to either side of the projected route to the connected drivable surface ahead.

1.4Static road boundary guidance

What ifWhat if the controller fitted a travel path between static road boundaries without selecting a lead vehicle?
Claim language“a lead vehicle that satisfies a predetermined condition”

Lidar returns locate curbs and paved shoulders on both sides of the roadway. The controller fits a smooth curve through the midpoints between the boundaries and uses it on single-lane segments with adequate clearance for the vehicle.

1.5Road geometry path generation

What ifWhat if the controller generated a path from road geometry and used the lead vehicle only to estimate available clearance?
Claim language“set the monitored path of the lead vehicle as a reference path”

A path planner fits a smooth curve from the current vehicle pose to a route waypoint using the edges of the drivable surface as constraints. The lead vehicle's tracked footprint supplies a moving obstacle for clearance checks along the generated curve.

Section 2 · machine-generated

Variations

Further arrangements of the same subject matter, described here as of the publication date at the foot of this page.

Other field of use

Lead vehicle guidance in freight yards

An autonomous yard tractor checks its assigned route for segments where painted guides are absent over a configured distance. The controller uses stored lane geometry to bound the search region where a record exists and uses surveyed drivable pavement along the assigned route elsewhere. It selects a moving yard tractor whose reported destination matches the next waypoint on the assigned route. After confirming that the observed track follows the assigned route, the controller uses that track for steering and regulates speed to maintain a following gap.

Component substitution

Radar tracking for lead vehicle guidance

A front-mounted imaging radar replaces camera-based lead vehicle tracking and supplies range, azimuth, and radial velocity measurements, while a lane camera detects marking gaps on the planned route. The controller sets a search region from stored lane geometry where available and from mapped drivable road boundaries elsewhere. It compensates for ego motion, clusters radar returns into vehicle tracks, and selects a candidate whose track has the lowest estimated position uncertainty. Once the observed track matches the planned route, the controller interpolates its measured positions into a reference path for steering and uses radar range and range rate for gap control.

Parameter or scale variation

Short marking gaps at low speed

On planned route segments with a speed limit of 20 km/h or less, a camera-based detector triggers when a lane marking is absent for at least 8 m. The controller searches up to 25 m ahead inside stored lane boundaries where available and inside sensor-detected road edges elsewhere. At 10 Hz it updates vehicle tracks and selects a target with at least eight associated detections in the last ten updates. After the target track matches the planned route, the controller resamples its observed positions at 0.5 m intervals for steering and maintains a time gap of at least 2 seconds.

Combination with existing systems

Lead guidance with emergency braking

A lane camera detects marking gaps on the planned route, and the controller uses historical lane boundaries where available and sensed road edges elsewhere to define the search region. A vehicle tracker selects a lead vehicle whose recent acceleration stays within configured bounds and supplies its observed path to the steering controller after the path matches the route. An independent automatic emergency braking system uses forward range and closing speed to assess collision risk along the commanded trajectory. A brake command arbiter gives emergency braking priority over the normal following controller when both request longitudinal control.

Lead guidance through temporary work zones

A camera detects a marking gap on the planned route, and the controller retrieves historical lane geometry if the segment has a stored record. A work-zone perception system fits boundaries to rows of cones and barriers, and the controller searches the portion of the temporary corridor that connects the planned entry and exit, using stored lane geometry to locate those connections when available. It selects a vehicle whose track crosses successive gates placed along the corridor in route order. Once the observed track matches the planned passage through the work zone, the controller uses it for steering and checks the ego vehicle's swept path against the detected boundaries.

Automated or data-driven variant

Learned scoring for lead vehicle selection

A processor detects a marking gap on the planned route and defines the search region with historical lane geometry where available and a current drivable-area estimate elsewhere. A gradient-boosted decision tree scores each vehicle track from its position uncertainty, missed detections, acceleration history, and association with mapped road segments. Training labels record whether each candidate continues through the next planned waypoint, and the controller selects the highest-scoring candidate above a calibrated threshold. A separate route check confirms that the observed track follows the planned route before the controller uses it as the steering reference.

Specific version of a part

Embedded multicore control processor

An embedded processor runs camera and radar track fusion on one core and vehicle control on another. The control core reads timestamped track data and updates actuator requests at 50 hertz.

Distance accumulation for marking gaps

The controller projects camera detections of lane markings onto the planned route in 1-meter intervals. It flags a gap when 30 consecutive observed intervals lack a detection for the same lane boundary.

Radar and camera lead selection

The controller associates radar range and range-rate measurements with camera detections classified as vehicles inside the region of interest. It selects the nearest confirmed vehicle whose heading is within 10 degrees of the vehicle's own heading and whose track persists for at least 0.5 seconds.

Route matched lead trajectory

The controller stores the lead vehicle's tracked positions in road coordinates and checks whether the positions progress along the planned route in order. When every sample in the most recent 20 meters lies within 1 meter of the route centerline, the controller interpolates those samples to form the reference path.

Section 3 · quoted from USPTO records

Other work

Passages reproduced word for word from two earlier-published U.S. patent documents, placed beside the language of claim 1. No characterization is offered. Each passage is marked A or B for the document it comes from; ¶ numbers are the paragraph numbers in the USPTO’s published full text of that document.

Document AUS 2014/0032108 A1
Published
Jan 30, 2014
Filed
Jul 30, 2012
Class
G06K 9/62
Document BUS 2017/0225567 A1
Published
Aug 10, 2017
Filed
Oct 30, 2015
Class
B60K 35/00
Claim 1
Document A
Document B
1.1a processor; and
The lane tracking system 12 is comprised of at least a processor and a memory module, where the processor is configured with software designed to select an anchor lane for tracking, which may be used by a semi-autonomous driving system for lateral control of the vehicle 10.
A · US 2014/0032108 A1 · ¶ 21
1.2a memory storing at least one instruction that is configured to be executed by the processor to cause the apparatus to: determine whether at least one road segment, in which a lane marking is missing for at least a threshold distance, is detected in a planned travel route of the autonomous vehicle;
At decision diamond 90, it is determined whether lane boundary information in front of the vehicle 10 is available from the vision system 20 (from the camera 22). The availability of front visual lane boundary information means that a lane boundary (curb or lane stripe) has been detected visually, such that the position and curvature of the lane boundary can be reliably estimated for some distance ahead of the vehicle 10.
A · US 2014/0032108 A1 · ¶ 28
1.3a memory storing at least one instruction that is configured to be executed by the processor to cause the apparatus to: set, based on detecting the at least one road segment and based on whether historical traffic lane information comprises lane information of the at least one road segment, a region of interest;
1.4a memory storing at least one instruction that is configured to be executed by the processor to cause the apparatus to: select, among one or more objects recognized in the region of interest, a lead vehicle that satisfies a predetermined condition;
1.5a memory storing at least one instruction that is configured to be executed by the processor to cause the apparatus to: based on a monitored path of the lead vehicle matching the planned travel route of the autonomous vehicle, set the monitored path of the lead vehicle as a reference path of the autonomous vehicle; and
The lane tracking system 12 receives data from the navigation & digital map system 14, the vehicle dynamics system 16, the vision system 20 and the object detection sensor 30, and finds the anchor lane that is consistent with lane boundary markers, navigation route, leading vehicle trajectory, and other data.
A · US 2014/0032108 A1 · ¶ 21
1.6a memory storing at least one instruction that is configured to be executed by the processor to cause the apparatus to: control, based on the reference path, an autonomous driving operation of the autonomous vehicle.
The autonomous driving enabled vehicle also determines a future position obtained from the current position and the vehicle speed through map matching of the vehicle speed pulses and the moving speed of the vehicle and received GPS signals with navigation map data. The autonomous driving enabled vehicle utilizes sensor information and the position information of the vehicle to carry out autonomous driving (Patent Literatures 1 to 9, for example).
B · US 2017/0225567 A1 · ¶ 2

An empty cell means only that no passage was reproduced there.

Statements in these documents
A lane tracking system is needed which uses all available data to select an anchor lane and exhibits improved lane tracking performance in lane merge and exit scenarios.
A · US 2014/0032108 A1 · ¶ 6
This invention relates generally to enhanced lane tracking capability of an automobile and, more particularly, to a method for selecting an anchor lane using navigation and digital map information, leading vehicle trajectories, and other data, to improve lane tracking performance at lane merge and split locations.
A · US 2014/0032108 A1 · ¶ 2
Furthermore, in a case where a driver of a vehicle moving under autonomous driving has become aware of an accident or congestion, if the driver suddenly cancels the autonomous driving and performs a heavy braking operation or abrupt steering operation, vehicles around the vehicle are also in danger.
B · US 2017/0225567 A1 · ¶ 12
The present invention allows prevention of accidents caused by autonomous driving enabled vehicles.
B · US 2017/0225567 A1 · ¶ 16
Cite aspatent.fyi, US 2026/0356363 A1, claim 1, first published 2026-11-20T00:27:46-05:00, https://patent.fyi/US20260356363/, SHA-256 97a2af3c50a1fcebee94fa269e40b482399827596b5b04d9879a6833ba5e4692
First published
Permanent addresshttps://patent.fyi/US20260356363/
Content fingerprint (SHA-256)97a2af3c50a1fcebee94fa269e40b482399827596b5b04d9879a6833ba5e4692
Methodv2026-11-18.2 · automated, not reviewed by a person
Correctionscorrections@patent.fyi