# US 2025/0093876 A1 · Robot local planner selection

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

- Number: US 2025/0093876 A1
- Document ID: US20250093876A1
- Status: Published application
- Kind: A1
- Application number: 18/467,107
- Filed: 2023-09-14
- Published: 2025-03-20
- Earliest claimed: 2023-09-14
- Assignees: Nokia Solutions and Networks Oy
- Applicants: Nokia Solutions and Networks Oy
- Inventors: Daniel ANDREWS; Jeongran Lee; Vishnu Sharma
- Web page: https://patentgrep.com/patent/US20250093876A1

## CPC

- G05D 1/0221: {involving a learning process}
- G01C 21/3407: {specially adapted for specific applications}
- G05D 1/0088: {characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours (using knowledge based models G06N5/00)}
- G05D 1/0214: {in accordance with safety or protection criteria, e.g. avoiding hazardous areas (monitoring the location of vehicles within a certain area, e.g. forbidden or allowed areas, in traffic control systems for road vehicles G08G1/13)}
- G05D 1/0274: {using mapping information stored in a memory device (navigation using map-matching G01C21/30)}
- G05D 1/622: Obstacle avoidance (predicting or avoiding probable or impending collision of road vehicles B60W30/08)
- G05D 1/644: Optimisation of travel parameters, e.g. of energy consumption, journey time or distance
- G05D 1/229: Command input data, e.g. waypoints
- G05D 2101/15: using machine learning, e.g. neural networks
- G05D 2109/10: Land vehicles
- G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G01C: MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY (measuring liquid level G01F; radio navigation, determining distance or velocity by use of propagation effects, e.g. Doppler effects, propagation time, of radio waves, analogous arrangements using other waves G01S)

## Abstract

A mobile robot includes at least one processor, and at least one memory storing instructions that, when executed by the at least one processor, cause the mobile robot to generate a set of next consecutive waypoints, determine a local planner based on the set of next consecutive waypoints, and output a velocity pair for navigating the mobile robot, based on the determined local planner.

## Claims

### Claim 1

A method for navigating a robot, the method comprising:
generating a set of next consecutive waypoints;
determining a local planner based on the set of next consecutive waypoints; and
outputting a velocity pair for navigating the robot, based on the determined local planner.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
generating a local cost map, and
wherein the determining the local planner is further based on the local cost map.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
determining a plurality of path clearance statuses based on the set of next consecutive waypoints;
filtering the plurality of path clearance statuses, and
wherein the determining the local planner is based on the filtered path clearance statuses.

### Claim 4 (depends on 1)

The method of claim 1, wherein the determining the local planner includes determining whether to use a traditional local planner or a reinforcement learning (RL) local planner.

### Claim 5 (depends on 1)

The method of claim 1, wherein the determining the local planner includes:
determining to use a traditional local planner in response to all consecutive waypoints in the set of next consecutive waypoints being clear; and
determining to use a reinforcement learning (RL) local planner in response to at least one consecutive waypoint in the set of next consecutive waypoints not being clear.

### Claim 6 (depends on 5)

The method of claim 5, further comprising:
generating an approximate path based on a global path and the set of next consecutive waypoints; and
determining whether all consecutive waypoints in the set of next consecutive waypoints are clear in response to no waypoint in the set of next consecutive waypoints being in a same position as an obstacle, based on a local cost map.

### Claim 7 (depends on 1)

The method of claim 1, wherein the generating the set of next consecutive waypoints includes:
discretizing a global path to generate discrete waypoints; and
choosing, as the set of next consecutive waypoints, a number of next discrete waypoints from a current position of the robot on the global path.

### Claim 8 (depends on 7)

The method of claim 7, wherein the choosing includes:
determining, among the discrete waypoints, a first waypoint, after a closest waypoint to the current position of the robot; and wherein
the choosing chooses the number of next discrete waypoints starting from the first waypoint.

### Claim 9

A mobile robot comprising:
at least one processor; and
at least one memory storing instructions that, when executed by the at least one processor, cause the mobile robot to
generate a set of next consecutive waypoints,
determine a local planner based on the set of next consecutive waypoints, and
output a velocity pair for navigating the mobile robot, based on the determined local planner.

### Claim 10 (depends on 9)

The mobile robot of claim 9, wherein the at least one memory stores instructions that, when executed by the at least one processor, cause the mobile robot to:
generate a local cost map; and
determine the local planner further based on the local cost map.

### Claim 11 (depends on 9)

The mobile robot of claim 9, wherein the at least one memory stores instructions that, when executed by the at least one processor, cause the mobile robot to:
determine a plurality of path clearance statuses based on the set of next consecutive waypoints;
filter the plurality of path clearance statuses; and
determine the local planner based on the filtered path clearance statuses.

### Claim 12 (depends on 9)

The mobile robot of claim 9, wherein the at least one memory stores instructions that, when executed by the at least one processor, cause the mobile robot to determine whether to use a traditional local planner or a reinforcement learning (RL) local planner.

### Claim 13 (depends on 9)

The mobile robot of claim 9, wherein the at least one memory stores instructions that, when executed by the at least one processor, cause the mobile robot to:
determine to use a traditional local planner in response to all consecutive waypoints in the set of next consecutive waypoints being clear; and
determine to use a reinforcement learning (RL) local planner in response to at least one consecutive waypoint in the set of next consecutive waypoints not being clear.

### Claim 14 (depends on 13)

The mobile robot of claim 13, wherein the at least one memory stores instructions that, when executed by the at least one processor, cause the mobile robot to:
generate an approximate path based on a global path and the next consecutive waypoints; and
determine whether all consecutive waypoints in the set of next consecutive waypoints are clear in response to no waypoint in the set of next consecutive waypoints being in a same position as an obstacle, based on a local cost map.

### Claim 15 (depends on 9)

The mobile robot of claim 9, wherein the at least one memory stores instructions that, when executed by the at least one processor, cause the mobile robot to:
discretize a global path to generate discrete waypoints; and
choose, as the set of next consecutive waypoints, a number of next discrete waypoints from a current position of the robot on the global path.

### Claim 16 (depends on 15)

The mobile robot of claim 15, wherein the at least one memory stores instructions that, when executed by the at least one processor, cause the apparatus to:
determine, among the discrete waypoints, a first waypoint, after a closest waypoint to the current position of the robot; and
choose the number of next discrete waypoints starting from the first waypoint.

### Claim 17

A non-transitory computer readable storage medium storing computer executable instructions that, when executed at a mobile robot, cause the mobile robot to perform a method for navigating the mobile robot, the method comprising:
generating a set of next consecutive waypoints;
determining a local planner based on the set of next consecutive waypoints; and
outputting a velocity pair for navigating the robot, based on the determined local planner.

### Claim 18 (depends on 15)

The non-transitory computer readable storage medium of claim 15, the method further comprising:
generating a local cost map, and
wherein the determining the local planner is further based on the local cost map.

### Claim 19 (depends on 15)

The non-transitory computer readable storage medium of claim 15, wherein the determining the local planner includes determining whether to use a traditional local planner or a reinforcement learning (RL) local planner.

### Claim 20 (depends on 15)

The non-transitory computer readable storage medium of claim 15, wherein the determining the local planner includes:
determining to use a traditional local planner in response to all consecutive waypoints in the set of next consecutive waypoints being clear; and
determining to use a reinforcement learning (RL) local planner in response to at least one consecutive waypoint in the set of next consecutive waypoints not being clear.

### Claim 21

A mobile robot comprising:
at least one processor; and
at least one memory storing instructions that, when executed by the at least one processor, cause the mobile robot to navigate based on a received velocity pair, the received velocity pair based on a local planner for the mobile robot, the local planner being determined based on a set of next consecutive waypoints for the mobile robot.
