# US 2020/0004251 A1 · Planning driven perception system for autonomous driving vehicles

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

- Number: US 2020/0004251 A1
- Document ID: US20200004251A1
- Status: Published application
- Kind: A1
- Application number: 16/025,653
- Filed: 2018-07-02
- Published: 2020-01-02
- Earliest claimed: 2018-07-02
- Assignees: Baidu USA LLC
- Applicants: Baidu USA LLC
- Inventors: Fan ZHU; Qi KONG
- Web page: https://patentgrep.com/patent/US20200004251A1

## CPC

- B60W 50/06: Improving the dynamic response of the control system, e.g. improving the speed of regulation or avoiding hunting or overshoot
- G05D 1/0212: {with means for defining a desired trajectory (involving a plurality of land vehicles G05D1/0287)}
- B60W 60/001: {Planning or execution of driving tasks}
- G01S 13/865: {Combination of radar systems with lidar systems}
- G01S 13/931: of land vehicles
- G01S 17/931: of land vehicles
- G05D 1/0231: {using optical position detecting means (position-fixing by using electromagnetic waves other than radio waves, e.g. optical position detecting means G01S5/16)}
- G05D 1/0257: {using a radar (radar systems designed for anti-collision purposes between land vehicles or between land vehicle and fixed obstacles G01S13/931)}
- G05D 1/0278: {using satellite positioning signals, e.g. GPS}
- B60W 2050/065: {by reducing the computational load on the digital processor of the control computer}
- B60W 2552/53: Road markings, e.g. lane marker or crosswalk
- G01S 2013/9318: {Controlling the steering}
- G01S 2013/9323: {Alternative operation using light waves}
- G01S 2013/93271: {in the front of the vehicles}
- 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
- G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- 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 perception perceives a driving environment surrounding an ADV based on sensor data obtained from a variety of sensors. Based on the perception data received from the perception module, a planning module is to plan a trajectory for a current driving cycle to drive the ADV. In addition, the planning module determines a driving intent and one or more regions of interest (ROIs) surrounding the ADV based on the trajectory. The driving intent and the ROIs information is then provided to the perception module as a feedback. The perception module can then processing the sensor data from selective sensors to generate the perception data for a next driving cycle. The selected sensors may be determined and selected based on the driving intent and the ROIs, such that the sensor data of the unrelated sensors may be ignored to reduce the computation cost of the perception module.

## Claims

### Claim 1

A computer-implemented method for operating an autonomous driving vehicle, the method comprising:
receiving, by a planning module, first perception data from a perception module, the first reception data describing a driving environment surrounding an autonomous driving vehicle (ADV);
planning, by the planning module, a trajectory for a current driving cycle based on the first perception data to drive the ADV from a first location to a second location;
determining a driving intent and one or more regions of interest (ROIs) surrounding the ADV based on the trajectory;
transmitting the driving intent and the ROIs to the perception module via an application programming interface (API);
generating, by the perception module, second perception data for a next driving cycle based on the driving intent and the ROIs; and
selectively processing sensor data from certain sensors associated with the ADV based on the driving intent and the ROIs.

### Claim 2 (depends on 1)

The method of claim 1, wherein the driving intent is one of following lane, changing lane, at intersection, nudging to left, nudging to right, merging lane, or moving backwardly.

### Claim 3 (depends on 1)

The method of claim 1, wherein one or more regions of interest comprise a front region, a back region, a left region, a right region, a front-left region, a front-right region, a back-left region, or a back-right region.

### Claim 4 (depends on 1)

The method of claim 1, wherein determining a driving intent and one or more regions of interest comprises:
for each of the regions of interest, calculating a distance range of the ROI from a current location of the ADV; and
calculating a scanning angle range of the ROI, wherein the ROI is defined by an area calculated based on the distance range and the scanning angle range.

### Claim 5 (depends on 4)

The method of claim 4, wherein the distance range is calculated based on a current speed of the ADV in view of a speed limit of a lane.

### Claim 6 (depends on 5)

The method of claim 5, wherein the distance range is calculated based on a speed value calculated based on the current speed of the ADV and the speed limit, multiplied by a predetermined period of time.

### Claim 7 (depends on 6)

The method of claim 6, wherein the speed value is calculated based on a larger value of the current speed of the ADV and a predetermined percentage of the speed limit.

### Claim 8 (depends on 6)

The method of claim 6, wherein the speed value is calculated based on a difference between the current speed of the ADV and a predetermined percentage of the speed limit.

### Claim 9 (depends on 4)

The method of claim 4, wherein the distance range is calculated based on a distance between the current location of the ADV and a lane boundary of a current lane within which the ADV is driving.

### Claim 10 (depends on 9)

The method of claim 9, wherein the distance range is calculated further based on a lane width of an adjacent lane.

### Claim 11

A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations, the operations comprising:
receiving, by a planning module, first perception data from a perception module, the first reception data describing a driving environment surrounding an autonomous driving vehicle (ADV);
planning, by the planning module, a trajectory for a current driving cycle based on the first perception data to drive the ADV from a first location to a second location;
determining a driving intent and one or more regions of interest (ROIs) surrounding the ADV based on the trajectory;
transmitting the driving intent and the ROIs to the perception module via an application programming interface (API);
generating, by the perception module, second perception data for a next driving cycle based on the driving intent and the ROIs; and
selectively processing sensor data from certain sensors associated with the ADV based on the driving intent and the ROIs.

### Claim 12 (depends on 11)

The machine-readable medium of claim 11, wherein the driving intent is one of following lane, changing lane, at intersection, nudging to left, nudging to right, merging lane, or moving backwardly.

### Claim 13 (depends on 11)

The machine-readable medium of claim 11, wherein one or more regions of interest comprise a front region, a back region, a left region, a right region, a front-left region, a front-right region, a back-left region, or a back-right region.

### Claim 14 (depends on 11)

The machine-readable medium of claim 11, wherein determining a driving intent and one or more regions of interest comprises:
for each of the regions of interest, calculating a distance range of the ROI from a current location of the ADV; and
calculating a scanning angle range of the ROI, wherein the ROI is defined by an area calculated based on the distance range and the scanning angle range.

### Claim 15 (depends on 14)

The machine-readable medium of claim 14, wherein the distance range is calculated based on a current speed of the ADV in view of a speed limit of a lane.

### Claim 16 (depends on 15)

The machine-readable medium of claim 15, wherein the distance range is calculated based on a speed value calculated based on the current speed of the ADV and the speed limit, multiplied by a predetermined period of time.

### Claim 17 (depends on 16)

The machine-readable medium of claim 16, wherein the speed value is calculated based on a larger value of the current speed of the ADV and a predetermined percentage of the speed limit.

### Claim 18 (depends on 16)

The machine-readable medium of claim 16, wherein the speed value is calculated based on a difference between the current speed of the ADV and a predetermined percentage of the speed limit.

### Claim 19 (depends on 14)

The machine-readable medium of claim 14, wherein the distance range is calculated based on a distance between the current location of the ADV and a lane boundary of a current lane within which the ADV is driving.

### Claim 20 (depends on 19)

The machine-readable medium of claim 19, wherein the distance range is calculated further based on a lane width of an adjacent lane.

### Claim 21

A data processing system, comprising:
a processor; and
a memory coupled to the processor to store instructions, which when executed by the processor, cause the processor to perform operations, the operations including:
receiving, by a planning module, first perception data from a perception module, the first reception data describing a driving environment surrounding an autonomous driving vehicle (ADV),
planning, by the planning module, a trajectory for a current driving cycle based on the first perception data to drive the ADV from a first location to a second location,
determining a driving intent and one or more regions of interest (ROIs) surrounding the ADV based on the trajectory,
transmitting the driving intent and the ROIs to the perception module via an application programming interface (API),
generating, by the perception module, second perception data for a next driving cycle based on the driving intent and the ROIs; and
selectively processing sensor data from certain sensors associated with the ADV based on the driving intent and the ROIs.
