Systems and Methods for Obstacle Avoidance

• US 20120046820A1
• Filed: 08/18/2011
• Published: 02/23/2012
• Est. Priority Date: 10/21/2005
• Status: Active Grant

• Current Assignee: Deere & Company, iRobot Corporation
• Original Assignee: iRobot Corporation
• Inventors: ALLARD, James, WIENHOLD, Kathleen A., NORRIS, William Robert, CATALFANO, Anthony Francis
• Granted Patent: US 8,874,300 B2
• Time in Patent Office: Days
• US Class Current: 701/25
• CPC Class Codes: B60T 7/22 initiated by contact of vehicle, e.g. bumper, with an external object, e.g. another vehicle , or by means of contactless obstacle detectors mounted on the vehicle
• CPC Class Codes: B60W 30/09 Taking automatic action to avoid collision, e.g. braking and steering
• CPC Class Codes: B60W 30/095 Predicting travel path or likelihood of collision
• CPC Class Codes: B60W 60/0051 from occupants to vehicle
• CPC Class Codes: B60W 60/0053 from vehicle to occupant
• CPC Class Codes: B62D 1/286 Systems for interrupting non-mechanical steering due to driver intervention
• CPC Class Codes: G05B 19/414 Structure of the control system, e.g. common controller or multiprocessor systems, interface to servo, programmable interface controller
• CPC Class Codes: G05D 1/0061 for transition from automatic pilot to manual pilot and vice versa
• 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 1/0246 using a video camera in combination with image processing means
• 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 1/0259 using magnetic or electromagnetic means
• 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 1/028 using a RF signal
• CPC Class Codes: H04L 67/12 specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
• CPC Class Codes: Y10S 901/01 Mobile robot
• CPC Class Codes: Y10S 901/47 : Optical

Abstract

Embodiments of the invention provide systems and methods for obstacle avoidance. In some embodiments, a robotically controlled vehicle capable of operating in one or more modes may be provided. Examples of such modes include teleoperation, waypoint navigation, follow, and manual mode. The vehicle may include an obstacle detection and avoidance system capable of being implemented with one or more of the vehicle modes. A control system may be provided to operate and control the vehicle in the one or more modes. The control system may include a robotic control unit and a vehicle control unit.

Claims

1. A method for directing a robotic vehicle to follow an object, the method comprising:

identifying an object for the robotic vehicle to follow;

estimating a robotic vehicle position relative to a previous position and a movement of the object;

estimating a range position of the object;

receiving a position of the object;

determining whether the object is located within the estimated range position;

calculating a trajectory set based in part on the object position, wherein the trajectory set comprises a plurality of trajectories;

assigning a preference value for each of the trajectories; and

providing the trajectory set to a drive arbiter.

2. The method of claim 1, wherein identifying an object for the robotic vehicle to follow comprises:

receiving an identification of an object to follow, the identification comprising an object location; and

detecting the object to follow.

3. The method of claim 1, wherein identifying an object for the robotic vehicle to follow comprises:

receiving data from a laser scanner, wherein the data comprises an identification of a plurality of objects within a detection zone; and

selecting the closest identified object to follow.

4. The method of claim 1, wherein the trajectory set comprises a trajectory having a middle vector and a plurality of trajectories having a trajectory vector, the middle vector and trajectory vector for each trajectory are separated from each other by a pre-determined angle.

5. The method of claim 4, wherein assigning a preference value for each of the trajectories comprises:

assigning a preferred value for the trajectory having the middle vector; and

assigning a least preferred value for the trajectory having the trajectory vector furthest from the middle vector.

6. The method of claim 1, further comprising:

receiving obstacle data, the obstacle data comprising the location of obstacles;

providing the obstacle data to the drive arbiter; and

selecting a trajectory based at least in part on the obstacle data.

7. A method for controlling a robotic vehicle using an obstacle map, the method comprising:

obtaining a plurality of points, wherein each point represents at least part of an obstacle and a position of the obstacle at a particular time;

associating a time stamp with each point;

mapping the points to a cell, wherein the cell is partitioned into grids;

separating the plurality of points into old, current, and new points based at least in part on the associated time stamp;

determining the center of at least one of the old points and the current points;

determining the center of the new points;

obtaining a position difference between the center of the new points and the center of at least one of the old points and the current points;

determining a velocity of an object based at least in part on the position difference; and

using the object velocity to control the robotic vehicle.

8. The method of claim 7, further comprising:

receiving a scan rate associated with obtaining the plurality of points;

determining a heading and radius of the object based at least in part on the position difference and scan rate; and

using the heading and radius to control the robotic vehicle.

9. The method of claim 7, further comprising:

generating a trajectory set comprising a plurality of trajectories, each trajectory comprising commands for robotic vehicle movement;

producing an obstacle report having obstacle characteristics, the obstacle report comprising a density of objects associated with a robotic vehicle path; and

using the obstacle report to assign a preference to each trajectory.

10. A method for generating a three-dimensional obstacle map for use in a robotically controlled vehicle, the method comprising;

using a laser scanner to execute a first scan of a scan range;

obtaining two-dimensional obstacle data points representing obstacles located in the scan range;

associating scan data with the obstacle data points, the scan data comprising at least one of scan range data representing the scan range, scanner angle data representing the angle of the laser scanner, vehicle velocity data, or a laser scanner synch pulse;

sending the scan data and obstacle data points to a robotic control unit;

time stamping the obstacle data points; and

generating a three-dimensional obstacle map based at least in part on the time stamped obstacle data points and scan data.

11. The method of claim 10, wherein sending the scan data and obstacle data points to a robotic control unit comprising sending the scan data and obstacle data points to a obstacle map robotic control unit;

and

wherein the obstacle map robotic control unit time stamps the obstacle data points.

12. The method of claim 11, further comprising:

providing a supervisory robotic control unit to generate the obstacle map.

13. The method of claim 10, wherein the obstacle map is used to control the robotic control vehicle.

14. A method for converting three-dimensional obstacle data into two-dimensional obstacle data for controlling a robotic vehicle, the method comprising:

obtaining a plurality of three-dimensional time stamped obstacle data from a laser scanner, the obstacle data representing the location of an obstacle;

receiving time stamped velocity data of the robotic vehicle;

comparing the obstacle data to pre-set criteria to separate the obstacle data into relevant obstacle data and irrelevant obstacle data, wherein the irrelevant obstacle data is outside the pre-set criteria;

discarding the irrelevant obstacle data;

correlating the relevant obstacle data to a two-dimensional point cloud representing an index of a point array; and

generating a two-dimensional obstacle map based at least in part on the point array.

15. The method of claim 14, further comprising:

discarding obstacle data having time stamps older than a pre-set threshold

16. The method of claim 14, further comprising:

filtering the point cloud to remove relevant obstacle data having a position beyond a pre-set length from the robotic control vehicle; and

overwriting obstacle map data having a time stamp outside a pre-set threshold with additional obstacle map data.