# US 2025/0157066 A1 · Enhanced slam-based parking assist with reusable training outcome for near-identical parking slots

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0157066 A1
- Document ID: US20250157066A1
- Status: Published application
- Kind: A1
- Application number: 18/521,099
- Filed: 2023-11-28
- Published: 2025-05-15
- Earliest claimed: 2023-11-13
- Assignees: GM Global Technology Operations LLC
- Applicants: GM Global Technology Operations LLC
- Inventors: Yuan Zhang; Wenyuan Qi
- Web page: https://patentgrep.com/patent/US20250157066A1

## CPC

- G06T 7/579: from motion
- B60W 30/06: Automatic manoeuvring for parking
- B60W 50/14: Means for informing the driver, warning the driver or prompting a driver intervention
- B62D 15/028: {Guided parking by providing commands to the driver, e.g. acoustically or optically}
- B62D 15/0285: {Parking performed automatically}
- G06V 20/586: {of parking space}
- B60W 2050/146: {Display means}
- B60W 2420/403: Image sensing, e.g. optical camera
- G06T 2207/20081: Training; Learning
- G06T 2207/30264: Parking
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- B60W: CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B62D: MOTOR VEHICLES; TRAILERS (steering, or guiding on a desired track, of agricultural machines or implements A01B69/00; wheels, castors, axles, increasing wheel adhesion B60B; vehicle tyres, tyre inflation or tyre changing B60C; connections between vehicles of a train or the like B60D; vehicles for use on rail and road, amphibious or convertible vehicles B60F; suspension arrangements B60G; heating, cooling, ventilating or other air treating devices B60H; windows, windscreens, non-fixed roofs, doors or similar devices, protective coverings for vehicles not in use B60J; propulsion plant arrangements, auxiliary drives, transmissions, controls, instrumentation or dashboards B60K; electric equipment or propulsion of electrically-propelled vehicles B60L; power supply for electrically-propelled vehicles B60M; passenger accommodation not otherwise provided for B60N; adaptations for load transportation or to carry special loads or objects B60P; arrangement of signalling or lighting devices, the mounting or supporting thereof or circuits therefor, for vehicles in general B60Q; vehicles, vehicle fittings or vehicle parts not otherwise provided for B60R; servicing, cleaning, repairing, supporting, lifting, or manoeuvring, not otherwise provided for, B60S; brake arrangements, brake control systems or parts thereof B60T; air-cushion vehicles B60V; motor-cycles, accessories therefor B62J, B62K; testing of vehicles G01M)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A method for SLAM-based parking assist includes determining that a host vehicle is entering a corridor adjacent a target parking slot and determining a potential reusability of at least one of a plurality of previously determined training outcome of a training process for the target parking slot. The training outcome includes training identifying data of a potential parking slot. The method further includes receiving identifying data of the target parking slot, identifying which of the plurality of training outcomes is reusable based on the identifying data of the target parking slot to select an identified training outcome, comparing the identifying data of the target parking slot with the identifying data of the potential parking slot of the identified training outcome, and loading the identifying data of the target parking slot into a SLAM-based parking assist.

## Claims

### Claim 1

A method for SLAM-based parking assist, comprising:
determining that a host vehicle is entering a corridor adjacent a target parking slot;
in response to determining that the host vehicle entered the corridor adjacent the target parking slot, determining a potential reusability of a plurality of training outcomes of a training process for the target parking slot, wherein each of the plurality of training outcomes includes training identifying data of a potential parking slot;
in response to determining a potential reusability of the plurality of training outcomes of the training process for the target parking slot, receiving identifying data of the target parking slot;
identifying which of the plurality of training outcomes is reusable based on the identifying data of the target parking slot to select an identified training outcome;
comparing the identifying data of the target parking slot with the identifying data of the potential parking slot of the identified training outcome to determine whether differences between the identifying data of the target parking slot and the identifying data of the potential parking slot of the identified training outcome are within predetermined thresholds; and
in response to determining that the differences between the identifying data of the target parking slot and the identifying data of the potential parking slot of the identified training outcome are within predetermined thresholds, loading the identifying data of the target parking slot into a SLAM-based parking assist.

### Claim 2 (depends on 1)

The method of claim 1, further comprising providing visual guidance to a vehicle occupant to complete parking using the SLAM-based parking assist and the identifying data of the target parking slot.

### Claim 3 (depends on 1)

The method of claim 1, further comprising controlling a motion of the host vehicle to reach a target parking position in the target parking slot.

### Claim 4 (depends on 1)

The method of claim 1, wherein the SLAM-based parking assist employs a SLAM feature set to localize and map the host vehicle, and the method further comprising:
detecting a new variety of a SLAM feature dataset; and
adjusting the identified training outcome using the new variety of the SLAM feature dataset.

### Claim 5 (depends on 1)

The method of claim 1, wherein the identifying data of the target parking slot includes geometrical attributes of the target parking slot, the identifying data of the potential parking slot of the identified training outcome includes geometrical attributes of the potential parking slot of the identified training outcome.

### Claim 6 (depends on 5)

The method of claim 5, wherein the geometrical attributes of the target parking slot include a corridor width of the corridor adjacent the target parking slot, a chassis ramp height of a ramp interconnecting the corridor and the target parking slot, a slot internal width of the target parking slot, and a slot external width of the target parking slot.

### Claim 7 (depends on 5)

The method of claim 5, further comprising determining that differences between the geometrical attributes of the target parking slot and the geometrical attributes of the potential parking slot of the identified training outcome are within predetermined geometrical thresholds.

### Claim 8

A system for SLAM-based parking assist, comprising:
a plurality of sensors;
a controller in communication with the plurality of sensors, wherein the controller is programmed to:
determine that a host vehicle is entering a corridor adjacent a target parking slot;
in response to determining that the host vehicle entered the corridor adjacent the target parking slot, determine a potential reusability of a plurality of training outcomes of a training process for the target parking slot, wherein each of the plurality training outcomes includes training identifying data of a potential parking slot;
in response to determining a potential reusability of the plurality training outcomes of the training process for the target parking slot, receive identifying data of the target parking slot;
identify which of the plurality of training outcomes is reusable based on the identifying data of the target parking slot to select an identified training outcome;
compare the identifying data of the target parking slot with the identifying data of the potential parking slot of the identified training outcome to determine whether differences between the identifying data of the target parking slot and the identifying data of the potential parking slot of the identified training outcome are within predetermined thresholds; and
in response to determining that the differences between the identifying data of the target parking slot and the identifying data of the potential parking slot of the identified training outcome are within predetermined thresholds, load the identifying data of the target parking slot into a SLAM-based parking assist.

### Claim 9 (depends on 8)

The system of claim 8, wherein the controller is programmed to command a user interface to provide visual guidance to a vehicle occupant to complete parking using the SLAM-based parking assist and the identifying data of the target parking slot.

### Claim 10 (depends on 8)

The system of claim 8, wherein the controller is programmed to control a motion of the host vehicle to reach a target parking position in the target parking slot.

### Claim 11 (depends on 8)

The system of claim 8, wherein the SLAM-based parking assist employs a SLAM feature set to localize and map the host vehicle, and wherein the controller is programmed to:
detect a new variety of a SLAM feature dataset; and
adjust the identified training outcome using the new variety of the SLAM feature dataset.

### Claim 12 (depends on 8)

The system of claim 8, wherein the identifying data of the target parking slot includes geometrical attributes of the target parking slot, the identifying data of the potential parking slot of the identified training outcome includes geometrical attributes of the potential parking slot of the identified training outcome.

### Claim 13 (depends on 12)

The system of claim 12, wherein the geometrical attributes of the target parking slot include a corridor width of the corridor adjacent the target parking slot, a chassis ramp height of a ramp interconnecting the corridor and the target parking slot, a slot internal width of the target parking slot, and a slot external width of the target parking slot.

### Claim 14 (depends on 13)

The system of claim 13, wherein the controller is programmed to determine that differences between the geometrical attributes of the target parking slot and the geometrical attributes of the potential parking slot of the identified training outcome are within predetermined geometrical thresholds.

### Claim 15

A tangible, non-transitory, machine-readable medium, comprising machine-readable instructions, that when executed by a processor, cause the processor to:
determine that a host vehicle is entering a corridor adjacent a target parking slot;
in response to determining that the host vehicle entered the corridor adjacent the target parking slot, determine a potential reusability of a plurality of training outcomes of a training process for the target parking slot, wherein each of the plurality of training outcomes includes training identifying data of a potential parking slot;
in response to determining a potential reusability of the plurality of training outcomes of the training process for the target parking slot, receive identifying data of the target parking slot;
identify which of the plurality of training outcomes is reusable based on the identifying data of the target parking slot to select an identified training outcome;
compare the identifying data of the target parking slot with the identifying data of the potential parking slot of the identified training outcome to determine whether differences between the identifying data of the target parking slot and the identifying data of the potential parking slot of the identified training outcome are within predetermined thresholds; and
in response to determining that the differences between the identifying data of the target parking slot and the identifying data of the potential parking slot of the identified training outcome are within predetermined thresholds, load the identifying data of the target parking slot into a SLAM-based park assist.

### Claim 16 (depends on 15)

The tangible, non-transitory, machine-readable medium of claim 15, wherein the tangible, non-transitory, machine-readable medium further comprising machine-readable instructions, that when executed by the processor, causes the processor to command a user interface to provide visual guidance to a vehicle occupant to complete parking using the SLAM-based parking assist and the identifying data of the target parking slot.

### Claim 17 (depends on 15)

The tangible, non-transitory, machine-readable medium of claim 15, wherein the tangible, non-transitory, machine-readable medium further comprising machine-readable instructions, that when executed by the processor, causes the processor to control a motion of the host vehicle to reach a target parking position in the target parking slot.

### Claim 18 (depends on 15)

The tangible, non-transitory, machine-readable medium of claim 15, wherein the SLAM-based park assist employs a SLAM feature set to localize and map the host vehicle, and the tangible, non-transitory, machine-readable medium further comprising machine-readable instructions, that when executed by the processor, causes the processor to:
detect a new variety of a SLAM feature dataset; and
adjust the identified training outcome using the new variety of the SLAM feature dataset.

### Claim 19 (depends on 15)

The tangible, non-transitory, machine-readable medium of claim 15, wherein the identifying data of the target parking slot includes geometrical attributes of the target parking slot, the identifying data of the potential parking slot of the identified training outcome includes geometrical attributes of the potential parking slot of the identified training outcome.

### Claim 20 (depends on 19)

The tangible, non-transitory, machine-readable medium of claim 19, wherein the tangible, non-transitory, machine-readable medium further comprising machine-readable instructions, that when executed by the processor, causes the processor to determine that differences between the geometrical attributes of the target parking slot and the geometrical attributes of the potential parking slot of the identified training outcome are within predetermined geometrical thresholds.
