Unified motion planning algorithm for autonomous driving vehicle in obstacle avoidance maneuver

Patent metadata

Field	Value
Publication number	US-9457807-B2
Application number	US-201414297493-A
Country	US
Kind code	B2
Filing date	Jun 5, 2014
Priority date	Jun 5, 2014
Publication date	Oct 4, 2016
Grant date	Oct 4, 2016

Abstract

A method for automated lane centering and/or lane changing purposes for a vehicle traveling on a roadway that employs roadway points from a map database to determine a reference vehicle path and sensors on the vehicle for detecting static and moving objects to adjust the reference path. The method includes reducing the curvature of the reference path to generate a reduced curvature reference path that reduces the turning requirements of the vehicle and setting the speed of the vehicle from posted roadway speeds from the map database. The method also includes providing multiple candidate vehicle paths and vehicle speeds to avoid the static and moving objects in front of the vehicle.

First claim

What is claimed is:

1. A method for generating a desired path for a vehicle to follow along a roadway, said vehicle including a map database and a lane detection system, said method comprising:
providing roadway measurement values from the map database to a controller including a processor and a memory, where the roadway measurement values identify locations on the roadway;
adjusting positions of the roadway measurement values relative to the roadway, in the memory, so that adjacent roadway measurement values are substantially an equal distance apart;
determining, using the controller, a reference path using the roadway measurement values for the vehicle to follow along the roadway;
determining, using the controller, a reference speed of the vehicle from a posted roadway speed from the map database;
determining, using the controller, that an object creates a potential collision problem with the vehicle on the reference path and at the reference speed;
adjusting, using the controller, the reference path and/or the reference speed to avoid the object;
determining a short segment path that will bring the vehicle back to the reference path, including modeling a local closed-loop trajectory as a fifth-order polynomial path model and a third-order polynomial speed model; and
providing signals from the controller to a vehicle brake system, a throttle and a steering system to cause the vehicle to follow the reference path and the reference speed.

2. The method according to claim 1 further comprising reducing a curvature of the reference path to generate a reduced curvature reference path that reduces turning requirements of the vehicle.

3. The method according to claim 2 wherein reducing the curvature of the reference path includes minimizing a cost function where the roadway measurement values are selectively adjusted at high curvature locations along the reference path.

4. The method according to claim 3 wherein minimizing the cost function includes minimizing the cost function as:

argmin

P
∈
P

⁢

ω
smooth

·

Σ

pi
∈
P

⁢

p
i

-

p

i
-
1



p
i

-

p

i
-
1



·

p
i

-

p

i
+
1



p
i

-

p

i
+
1



+

ω
length

·

Σ

pi
∈
P

⁢



p
i

-

p

i
-
1



,

where p i is the ith sample point and ω smooth is a weight for a path smoothness term:

Σ

p
,

∈
P

⁢

p
i

-

p

i
-

Assignees

• Gm Global Tech Operations Llc
• Univ Carnegie Mellon

Inventors

• Lee Jin-Woo
• Mudalige Upali Priyantha
• Gu Tianyu
• Dolan John M

Classifications

• B60W30/10

  Path keeping {(cruise control for automatically following a preceding vehicle B60W30/165)} · CPC title

• B60W2720/10

  Longitudinal speed · CPC title

• B60W2556/50

  of positioning data, e.g. GPS [Global Positioning System] data · CPC title

• B60W30/09 Primary

  Taking automatic action to avoid collision, e.g. braking and steering · CPC title

• B60W10/20

  including control of steering systems · CPC title