SYSTEMS AND METHODS FOR CONTROLLING A VEHICLE USING HIGH PRECISION AND HIGH RECALL DETECTION

1 . A method of controlling an autonomous vehicle, comprising:

receiving data from a set of sensors, wherein the data represents objects or obstacles in an environment of the autonomous vehicle; and

using a processor:

determining attributes of each of the objects or obstacles based on the received data from the set of sensors;

integrating the attributes of the each of the objects or obstacles;

identifying objects or obstacles based on the integrated attributes;

determining a candidate trajectory for the autonomous vehicle to avoid the objects or obstacles; and

controlling the autonomous vehicle according to the candidate trajectory.

2 . The method of claim 1 , further comprising:

generating high precision detection data based on the received data;

identifying from the high precision detection data a first set of objects or obstacles that are classifiable by at least one known classifier;

tracking movement of one or more objects in the first set of objects or obstacles over time and maintaining identity of the tracked one or more objects in the first set of objects or obstacles;

generating high recall detection data based on the received data;

identifying from the high recall detection data a second set of objects or obstacles without using any classifier;

filtering out objects, from the second set of objects or obstacles, that correspond to the tracked one or more objects in the first set of objects or obstacles to obtain a filtered set of objects or obstacles; and

determining a candidate trajectory for the autonomous vehicle to avoid at least the tracked one or more objects in the first set of objects or obstacles and the filtered set of objects or obstacles.

3 . The method of claim 1 , wherein the attributes comprise kinematic information, geometric information, or object classification information.

4 . The method of claim 2 , comprising generating the high precision detection data and the high recall detection data based on different subsets of data received from different sets of sensors.

5 . The method of claim 2 , wherein the step of filtering comprises filtering out a set of points corresponding to the tracked one or more objects in the first set of objects or obstacles from at least one point cloud of the second set of objects or obstacles.

6 . The method of claim 2 , comprising generating the high precision detection data from the data received from image and point cloud detectors.

7 . The method of claim 2 , comprising generating the high recall detection data from point cloud clustering by LIDAR, stereo depth vision by RADAR, and/or monocular depth vision using learned low-level features by RADAR.

8 . The method of claim 7 , wherein the learned low-level features comprise distance.

9 . The method of claim 2 , wherein the step of tracking comprises tracking movement of the one or more objects in the first set of objects or obstacles over a period of time when the one or more objects are detectable by the set of sensors.

10 . The method of claim 9 , wherein the period is from about 100 ms to about 500 ms.

11 . The method of claim 1 , wherein the set of sensors comprise a two-dimensional object detector, a three-dimensional object detector, and/or an obstacle detector.

12 . The method of claim 1 , wherein the set of sensors comprise RADAR, LIDAR, camera, sonar, laser, or ultrasound.

13 . A system for controlling an autonomous vehicle, comprising:

a set of sensors, configured to receive data that represents objects or obstacles in an environment of the autonomous vehicle; and

a processor, configured to:

determine attributes of each of the objects or obstacles based on the received data from the set of sensors;

integrate the attributes of the each of the objects or obstacles;

identify objects or obstacles based on the integrated attributes;

determine a candidate trajectory for the autonomous vehicle to avoid the objects or obstacles; and

control the autonomous vehicle according to the candidate trajectory.

14 . The system of claim 13 , wherein the processor is further configured to:

generate high precision detection data based on the received data;

identify, from the high precision detection data, a first set of objects or obstacles that are classifiable by at least one known classifier;

track movement of one or more objects in the first set of objects or obstacles over time and maintain identity of the tracked one or more objects in the first set of objects or obstacles;

generate high recall detection data based on the received data;

identify from the high recall detection data a second set of objects or obstacles without using any classifier;

filtering out objects, from the second set of objects or obstacles, that correspond to the tracked one or more objects in the first set of objects or obstacles to obtain a filtered set of objects or obstacles; and

determine a candidate trajectory for the autonomous vehicle to avoid at least the tracked one or more objects in the first set of objects or obstacles and the filtered set of objects or obstacles.

15 . The system of claim 13 , wherein the attributes comprise kinematic information, geometric information, or object classification information.

16 . The system of claim 14 , wherein the processor is configured to generate the high precision detection data and the high recall detection data based on different subsets of data received from different sets of sensors.

17 . The system of claim 14 , wherein the processor is configured to filter out a set of points corresponding to the tracked one or more objects in the first set of objects or obstacles from at least one point cloud of the second set of objects or obstacles.

18 . The system of claim 14 , wherein the processor is configured to generate the high precision detection data from the data received from image and point cloud detectors.

19 . The system of claim 14 , wherein the processor is configured to generate the high recall detection data from point cloud clustering by LIDAR, stereo depth vision by RADAR, and/or monocular depth vision using learned low-level features by RADAR.

20 . The system of claim 19 , wherein the learned low-level features comprise distance.

21 . The system of claim 14 , wherein the processor is configured to track movement of the one or more objects in the first set of objects or obstacles over a period of time when the one or more objects are detectable by the set of sensors.

22 . The system of claim 14 , wherein the set of sensors comprise a two-dimensional object detector, a three-dimensional object detector, and/or an obstacle detector.