# US 2021/0278850 A1 · Robot obstacle collision prediction and avoidance

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

- Number: US 2021/0278850 A1
- Document ID: US20210278850A1
- Status: Published application
- Kind: A1
- Application number: 16/809,810
- Filed: 2020-03-05
- Published: 2021-09-09
- Earliest claimed: 2020-03-05
- Assignees: Locus Robotics Corp.
- Applicants: Locus Robotics Corp.
- Inventors: Thomas Moore
- Web page: https://patentgrep.com/patent/US20210278850A1

## CPC

- 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 1/024: {in combination with a laser (lasers per se H01S)}
- B60R 21/013: including means for detecting collisions, impending collisions or roll-over
- G01S 17/89: for mapping or imaging
- G01S 17/931: of land vehicles
- G05D 1/0274: {using mapping information stored in a memory device (navigation using map-matching G01C21/30)}
- G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- B60R: VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES

## Abstract

A method for predicting a collision between a mobile robot and an obstacle in an environment includes obtaining laser scan data for the mobile robot at a current location in the environment. The method also includes predicting a future location of the mobile robot in the environment and producing predicted laser scan data corresponding to the future location of the mobile robot in the environment. The method further includes assessing the predicted laser scan data relative to the mobile robot at the current location to determine whether a collision with an obstacle is predicted.

## Claims

### Claim 1

A method for predicting a collision between a mobile robot and an obstacle in an environment, comprising:
obtaining laser scan data for the mobile robot at a current location in the environment;
predicting a future location of the mobile robot in the environment;
producing predicted laser scan data corresponding to the future location of the mobile robot in the environment; and
assessing the predicted laser scan data relative to the mobile robot at the current location to determine whether a collision with an obstacle is predicted.

### Claim 2 (depends on 1)

The method of claim 1 wherein the laser scan data for the mobile robot at a current location includes raw data output from a laser scanner on the mobile robot.

### Claim 3 (depends on 2)

The method of claim 2 wherein the raw data output from the laser scanner for the mobile robot at the current location includes laser scan points indicating points of reflection off of obstacles in the environment.

### Claim 4 (depends on 3)

The method of claim 3 wherein the step of predicting the future location of the mobile robot in the environment includes estimating the future location of the mobile robot moving along an arc path after N seconds of travel from the current location using a commanded velocity of the mobile robot.

### Claim 5 (depends on 4)

The method of claim 4 wherein N is a number between 1 and 2.

### Claim 6 (depends on 3)

The method of claim 3 wherein the predicted laser scan data includes predicted laser scan points indicating predicted points of reflection off of obstacles in the environment from the future location of the mobile robot.

### Claim 7 (depends on 6)

The method of claim 6 further including representing the mobile robot as a polygon.

### Claim 8 (depends on 7)

The method of claim 7 the polygon representing the mobile robot is an R-sided, convex polygon.

### Claim 9 (depends on 7)

The method of claim 7 wherein the step of assessing the predicted laser scan data relative to the mobile robot at the current location includes connecting each of the laser scan points with a corresponding predicted laser scan point with an arc, thereby forming a plurality of arcs.

### Claim 10 (depends on 9)

The method of claim 9 wherein each arc of the plurality of arcs comprises a plurality of line segments, L.

### Claim 11 (depends on 9)

The method of claim 9 wherein the step of assessing the predicted laser scan data relative to the mobile robot at the current location includes determining if any of the plurality of arcs intersect with a point on the polygon representing the mobile robot, which is indicative of a potential collision between the mobile robot and an obstacle.

### Claim 12 (depends on 11)

The method of claim 11 further including adjusting the commanded velocity of the mobile robot using a scaling factor based at least in part on a depth of incursion into the polygon for at least one intersecting arc.

### Claim 13 (depends on 12)

The method of claim 12 wherein the depth of incursion into the polygon for each intersecting arc is determined based on the length of an arc length approximation for the intersecting arc.

### Claim 14 (depends on 13)

The method of claim 13 wherein for each intersecting arc, a ratio of a straight line distance from the current laser scan point on the obstacle to the point of intersection on the polygon relative to the arc length approximation is determined and the minimum ratio is used as the scaling factor.

### Claim 15

An autonomous mobile robot configured to predict a collision with an obstacle in an environment, comprising:
a mobile robot base;
a laser scanner mounted on the mobile robot base; and
a computer on the mobile robot base, including a processor and a memory, the computer being operatively coupled to the laser scanner; the processor configured to execute instructions stored in memory to:
obtain laser scan data for the mobile robot at a current location in the environment;
predict a future location of the mobile robot in the environment;
produce predicted laser scan data corresponding to the future location of the mobile robot in the environment; and
assess the predicted laser scan data relative to the mobile robot at the current location to determine whether a collision with an obstacle is predicted.

### Claim 16 (depends on 15)

The autonomous mobile robot of claim 15 wherein the laser scan data for the mobile robot at a current location includes raw data output from a laser scanner on the mobile robot.

### Claim 17 (depends on 16)

The autonomous mobile robot of claim 16 wherein the raw data output from the laser scanner for the mobile robot at the current location includes laser scan points indicating points of reflection off of obstacles in the environment.

### Claim 18 (depends on 17)

The autonomous mobile robot of claim 17 wherein the instruction stored in memory to predict the future location of the mobile robot in the environment incudes estimating the future location of the mobile robot moving along an arc path after N seconds of travel from the current location using a commanded velocity of the mobile robot.

### Claim 19 (depends on 18)

The autonomous mobile robot of claim 18 wherein N is a number between 1 and 2.

### Claim 20 (depends on 17)

The autonomous mobile robot of claim 17 wherein the predicted laser scan data includes predicted laser scan points indicating predicted points of reflection off of obstacles in the environment from the future location of the mobile robot.

### Claim 21 (depends on 20)

The autonomous mobile robot of claim 20 wherein the processor is further configured to execute instructions stored in memory to represent the mobile robot as a polygon.

### Claim 22 (depends on 21)

The autonomous mobile robot of claim 21 the polygon representing the mobile robot is an R-sided, convex polygon.

### Claim 23 (depends on 21)

The autonomous mobile robot of claim 21 wherein when the processor executes instructions stored in memory to assess the predicted laser scan data relative to the mobile robot at the current location, the processor is further configured to connect each of the laser scan points with a corresponding predicted laser scan point with an arc, thereby forming a plurality of arcs.

### Claim 24 (depends on 23)

The autonomous mobile robot of claim 23 wherein each arc of the plurality of arcs comprises a plurality of line segments, L.

### Claim 25 (depends on 23)

The autonomous mobile robot of claim 23 wherein when the processor executes instructions stored in memory to assess the predicted laser scan data relative to the mobile robot at the current location, the processor is further configured to determine if any of the plurality of arcs intersect with a point on the polygon representing the mobile robot, which is indicative of a potential collision between the mobile robot and an obstacle.

### Claim 26 (depends on 25)

The autonomous mobile robot of claim 25 wherein the processor is further configured to execute instructions stored in memory to adjust a commanded velocity of the mobile robot using a scaling factor based at least in part on a depth of incursion into the polygon for at least one intersecting arc.

### Claim 27 (depends on 26)

The autonomous mobile robot of claim 26 wherein the depth of incursion into the polygon for each intersecting arc is determined based on the length of an arc length approximation for the intersecting arc.

### Claim 28 (depends on 27)

The method of claim 27 wherein the processor is further configured to execute instructions stored in memory to calculate a ratio for each intersecting arc, wherein the ratio is of a straight line distance from the current laser scan point on the obstacle to the point of intersection on the polygon relative to the arc length approximation and the minimum ratio is used as the scaling factor.
