Gap measurement for vehicle convoying
A variety of methods, controllers and algorithms are described for identifying the back of a particular vehicle (e.g., a platoon partner) in a set of distance measurement scenes and/or for tracking the back of such a vehicle. The described techniques can be used in conjunction with a variety of different distance measuring technologies including radar, LIDAR, camera based distance measuring units and others. The described approaches are well suited for use in vehicle platooning and/or vehicle convoying systems including tractor-trailer truck platooning applications. In another aspect, technique are described for fusing sensor data obtained from different vehicles for use in the at least partial automatic control of a particular vehicle. The described techniques are well suited for use in conjunction with a variety of different vehicle control applications including platooning, convoying and other connected driving applications including tractor-trailer truck platooning applications.
1 . A method for tracking a specific vehicle during platooning operations, comprising:
generating a histogram representing radar point candidates from a specific partner vehicle detected by a radar unit over multiple radar sample periods;
defining a multi-dimensional bounding box around an estimated position of the partner vehicle, wherein the multi-dimensional bounding box includes position and velocity dimensions;
identifying partner vehicle radar point candidates within the multi-dimensional bounding box;
applying a clustering algorithm to the histogram to identify clusters of radar point candidates;
identifying a back position of the partner vehicle based on the identified clusters; and
storing the histogram as a radar signature of the partner vehicle for subsequent identification verification.
2 . The method of claim 1 , further comprising:
comparing a new histogram generated after radar contact with the partner vehicle has been interrupted, to the stored radar signature, to verify that radar contact with the partner vehicle has been reestablished.
3 . The method of claim 1 , further comprising:
transmitting the stored radar signature to another vehicle to facilitate identification of the partner vehicle by the other vehicle for future platooning operations.
4 . The method of claim 1 , wherein the clustering algorithm is a modified mean shift algorithm.
5 . The method of claim 1 , further comprising:
adjusting parameters of the multi-dimensional bounding box based on accumulated radar data.
6 . The method of claim 1 , further comprising:
determining an effective vehicle length of the partner vehicle based on the back position of the partner vehicle relative to a reported GPS position of the partner vehicle.
7 . The method of claim 1 , further comprising:
using a Kalman filter to estimate a state of the partner vehicle, wherein the state includes position and velocity information.
8 . A system for tracking a specific vehicle during platooning operations, comprising:
a radar unit for obtaining radar scenes including detected object points;
a position estimator configured to estimate a position of a partner vehicle; and
a processor configured to:
generate a histogram representing radar point candidates from the partner vehicle over multiple radar scene samples;
define a multi-dimensional bounding box around the estimated position of the partner vehicle, wherein the multi-dimensional bounding box includes position and velocity dimensions;
identify partner vehicle radar point candidates within the multi-dimensional bounding box;
apply a clustering algorithm to the histogram to identify clusters of radar point candidates;
identify a back position of the partner vehicle based on the identified clusters; and
store the histogram as a radar signature of the partner vehicle for subsequent identification verification.
9 . The system of claim 8 , wherein the processor is further configured to:
compare a new histogram generated after radar contact with the partner vehicle has been interrupted, to the stored radar signature, to verify that radar contact with the partner vehicle has been reestablished.
10 . The system of claim 8 , wherein the processor is further configured to:
transmit the stored radar signature to another vehicle to facilitate identification of the partner vehicle by the other vehicle for future platooning operations.
11 . The system of claim 8 , wherein the clustering algorithm is a modified mean shift algorithm.
12 . The system of claim 8 , wherein the processor is further configured to:
adjust parameters of the multi-dimensional bounding box based on accumulated radar data.
13 . The system of claim 8 , wherein the processor is further configured to:
determine an effective vehicle length of the partner vehicle based on the back position of the partner vehicle relative to a reported GPS position of the partner vehicle.
14 . The system of claim 8 , wherein the processor is further configured to:
apply a Kalman filter to maintain and update a state estimate of the partner vehicle, wherein the state estimate includes position and velocity parameters.