Method and system for controlling a remote vehicle

• US 8,577,538 B2
• Filed: 07/16/2007
• Issued: 11/05/2013
• Est. Priority Date: 07/14/2006
• Status: Active Grant

• Current Assignee: iRobot Corporation
• Original Assignee: iRobot Corporation
• Inventors: Lenser, Scott Raymond, Jones, Christopher Vernon, Yamauchi, Brian Masao
• Primary Examiner(s): Trammell, James
• Assistant Examiner(s): Edwards, Jerrah
• Application Number:
  US11/826,541
• Publication Number:
  US 20080027591A1
• Time in Patent Office: 2,304 Days
• Field of Search: 700/259, 701/2, 701/28, 701/300, 701/301
• US Class Current: 701/28
• CPC Class Codes: G05D 1/0027 involving a plurality of vehicles, e.g. fleet or convoy travelling fleet control of land vehicles from a control room G05D1/0297; traffic control systems for road vehicles G08G1/00; for marine craft G08G3/00; for aircraft G08G5/00
• CPC Class Codes: G05D 1/0038 by providing the operator with simple or augmented images from one or more cameras located onboard the vehicle, e.g. tele-operation images analyzed by a computer and used for automatic navigation G05D1/0246
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• CPC Class Codes: G05D 1/024 in combination with a laser lasers per se H01S
• CPC Class Codes: G05D 1/0251 extracting 3D information from a plurality of images taken from different locations, e.g. stereo vision stereoscopic image analysis H04N13/00; depth recovery from images G06T7/593
• CPC Class Codes: G05D 1/0255 using acoustic signals, e.g. ultra-sonic singals sonar systems designed for anti-collision purposes G01S15/93
• CPC Class Codes: 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
• CPC Class Codes: G05D 1/027 comprising intertial navigation means, e.g. azimuth detector inertial navigation G01C21/16; inertial navigation combined with non-inertial navigation instruments G01C21/165
• CPC Class Codes: G05D 1/0272 comprising means for registering the travel distance, e.g. revolutions of wheels measuring distance traversed on the ground by vehicles, e.g. using odometers G01C22/00
• CPC Class Codes: G05D 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30
• CPC Class Codes: G05D 1/0278 using satellite positioning signals, e.g. GPS
• CPC Class Codes: G05D 1/0297 by controlling means in a control room
• CPC Class Codes: G06F 3/0412 Digitisers structurally integrated in a display
• CPC Class Codes: H04L 67/125 involving control of end-device applications over a network

Abstract

A system for controlling more than one remote vehicle. The system comprises an operator control unit allowing an operator to receive information from the remote vehicles and send commands to the remote vehicles via a touch-screen interface, the remote vehicles being capable of performing autonomous behaviors using information received from at least one sensor on each remote vehicle. The operator control unit sends commands to the remote vehicles to perform autonomous behaviors in a cooperative effort, such that high-level mission commands entered by the operator cause the remote vehicles to perform more than one autonomous behavior sequentially or concurrently. The system may perform a method for generating obstacle detection information from image data received from one of a time-of-flight sensor and a stereo vision camera sensor.

Claims

1. A method of maintaining an occupancy grid map having cells, the method comprising:

receiving image data from a sensor of a remote vehicle, the sensor being one of a time-of-flight sensor and a stereo vision camera sensor, the image data including one or more columns of pixels;

for each pixel of the image data from the sensor;

determining, at a processor operatively connected to the sensor, a direction for the pixel based on a field of view of the sensor; and

combining, at the processor, the direction with depth information of the image data for a potential obstacle in the pixel;

using, at the processor, the combined direction and depth information to plot points, sequentially, for each column of pixels of the image data, each point representing a distance of the potential obstacle from the remote vehicle and a direction of the potential obstacle;

creating, at the processor, one or more best-fit lines from a predetermined number of sequential plotted points;

determining, at the processor, a respective slope of each best-fit line, and determining the existence of the potential obstacle if the slope of the best-fit line is above a threshold slope;

generating, at the processor, a one-dimensional set of values, derived from the best-fit lines, representing the distance to any obstacle detected by the sensor, each value being indexed by its angle with respect to the field of view of the sensor;

updating, at the processor, the occupancy grid map based on the one-dimensional set of values by incrementing a cell of the occupancy grid map, if an obstacle was detected within that cell; and

adding, at the processor, a location of the remote vehicle to the occupancy grid map.

2. The method of claim 1 wherein, a value of the one dimensional set of values is set equal to infinity when an object is not detected in a portion of the image data corresponding to an index of the value.

3. The method of claim 1, further comprising downsampling the one-dimensional set of values to a predetermined number of values.

4. The method of claim 1, wherein creating the occupancy grid map from the one-dimensional set of values further comprises decrementing a cell of the occupancy grid map if no obstacle was detected within that cell.

5. The method of claim 1, wherein more recent depth information is weighted to represent its greater importance in creating the occupancy grid map.

6. The method of claim 5, wherein the time-of-flight sensor is a SwissRanger sensor or a flash LIDAR sensor.

7. A method for generating obstacle detection information, the method comprising:

receiving image data from a sensor of a remote vehicle, the sensor being one of a time-of-flight sensor and a stereo vision camera sensor, the image data including one or more columns of pixels;

for each pixel of the image data from the sensor;

determining, at a processor operatively connected to the sensor, a direction for the pixel based on a field of view of the sensor; and

combining, at the processor, the direction with a depth information of the image data for a potential obstacle in the pixel;

using, at the processor, the combined direction and depth information to plot points, sequentially, for each column of pixels of the image data, each point representing a distance of the potential obstacle from the remote vehicle and a direction of the potential obstacle;

creating, at the processor, one or more best-fit lines from a predetermined number of sequential plotted points;

determining, at the processor, a respective slope of each best-fit line, and determining the existence of the potential obstacle if the slope of the best-fit line is above a threshold slope; and

generating, at the processor, a one-dimensional set of values, derived from the best-fit lines, representing the distance to any obstacle detected by the sensor, each value being indexed by its angle with respect to the field of view of the sensor.

8. The method of claim 7, further comprising downsampling the one-dimensional set of values to a predetermined number of values.