IP Library Granted Patent US 12660735
Granted Patent B2
US 12660735 · App. 18/617,794 · Granted Jun 23, 2026

Automated systems and methods for agricultural crop monitoring and sampling

Inventors: David J. Cappelleri (West Lafayette, IN); Nitya N. Agrawal (Centreville, VA); Aarya Deb (West Lafayette, IN); Brian Huang (Scotch Plains, NJ); Kitae Kim (West Lafayette, IN)
Assignee: Purdue Research Foundation
A01B79/005B25J11/0055B25J15/0019G01C21/1652G01C21/1656G01S17/89
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12660735
App. No.
18/617,794
Granted
Jun 23, 2026
Kind
B2
Abstract

A robotic system navigates a terrain adjacent one or more agricultural crops. The system includes a movable body operable to navigate the ground terrain, a tracking camera configured to generate visual-inertial odometry (VIO) data, a first LiDAR sensor configured to capture a first set of LiDAR data, a second LiDAR sensor configured to capture a second set of LiDAR data, and a controller. The controller is configured to generate terrain navigation instructions utilizing a Monte Carlo Localization algorithm, wherein the Monte Carlo Localization algorithm includes the VIO data from the tracking camera and the first set of LiDAR data.

Claims (56)

1 . A robotic system operable to navigate a terrain adjacent one or more agricultural crops, comprising:

a) a movable body operable to navigate a ground terrain adjacent one or more agricultural crops;

b) a tracking camera configured to generate visual-inertial odometry (VIO) data while the movable body navigates the ground terrain;

c) a first LiDAR sensor configured to capture a first set of LiDAR data;

d) a second LiDAR sensor configured to capture a second set of LiDAR data;

e) a controller configured to:

i) generate terrain navigation instructions utilizing a Monte Carlo Localization algorithm, wherein the Monte Carlo Localization algorithm includes the VIO data from the tracking camera and the first set of LiDAR data; and

ii) generate a crop monitoring dataset including at least one of a crop stalk height or a crop stalk radius using at least one of first LiDAR data from the first LiDAR sensor and the second set of LiDAR data from the second LiDAR sensor;

wherein the Monte Carlo Localization algorithm of the controller incorporates an Extended Kalman Filter (EKF) to generate the terrain navigation instructions;

wherein the movable body is coupled with a plurality of wheels configured to navigate the ground terrain, wherein the plurality of wheels defines a wheel odometry while the movable body navigates the ground terrain adjacent one or more agricultural crops, wherein the EKF is configured to combine the wheel odometry and the VIO data.

2 . The robotic system of claim 1 , further comprising:

a) a gripping member selectively operable to grasp one or more of the agricultural crops; and

b) an end effector selectively operable to cut and remove a portion from one or more of the agricultural crops.

3 . The robotic system of claim 2 , wherein the controller is further configured to initiate a crop sampling procedure by selectively controlling the gripping member and end effector, wherein the crop sampling procedure includes cutting and removing the portion from one or more of the agricultural crops.

4 . The robotic system of claim 3 , wherein the end effector includes a nichrome wire, wherein the controller is operable to heat the nichrome wire to cut the portion of the one or more of the agricultural crops during the crop sampling procedure.

5 . The robotic system of claim 1 , further comprising a robotic arm moveable about six degrees of freedom.

6 . The robotic system of claim 5 , further comprising:

a) a gripping member selectively operable to grasp one or more of the agricultural crops; and

b) an end effector selectively operable to cut and remove a portion from one or more of the agricultural crops;

wherein the gripping member and the end effector are coupled with the robotic arm.

7 . The robotic system of claim 6 , further comprising an RGB-D camera mounted on the robotic arm, wherein the RGB-D camera is configured to provide vision-based guidance instructions to the robotic arm, wherein the vision-based guidance instructions includes at least one of a position and a distance of the robotic arm related to the portion of the one or more of the agricultural crops during the crop sampling procedure.

8 . The robotic system of claim 1 , wherein the first LiDAR sensor is a two-dimensional LiDAR sensor, wherein the second LiDAR sensor is a three-dimensional LiDAR sensor.

9 . The robotic system of claim 1 , wherein generating a crop monitoring dataset includes initiating a neural network algorithm to detect a portion of one or more of the agricultural crops.

10 . A robotic system operable to navigate a terrain adjacent one or more agricultural crops, comprising:

a) a movable body operable to navigate a ground terrain adjacent one or more agricultural crops;

b) a tracking camera configured to generate visual-inertial odometry (VIO) data while the movable body navigates the ground terrain;

c) a first LiDAR sensor configured to capture a first set of LiDAR data;

d) a second LiDAR sensor configured to capture a second set of LiDAR data;

e) a gripping member selectively operable to grasp one or more of the agricultural crops;

f) an end effector selectively operable to cut and remove a portion from one or more of the agricultural crops; and

g) a controller configured to:

i) generate terrain navigation instructions utilizing a Monte Carlo Localization algorithm, wherein the Monte Carlo Localization algorithm includes the VIO data from the tracking camera and the first set of LiDAR data; and

ii) initiate a crop sampling procedure by selectively controlling the gripping member and end effector, wherein the crop sampling procedure includes cutting and removing the portion from one or more of the agricultural crops;

wherein the Monte Carlo Localization algorithm of the controller incorporates an Extended Kalman Filter (EKF) to generate the terrain navigation instructions;

wherein the movable body is coupled with a plurality of wheels configured to navigate the ground terrain, wherein the plurality of wheels defines a wheel odometry while the movable body navigates the ground terrain adjacent one or more agricultural crops, wherein the EKF is configured to combine the wheel odometry and the VIO data.

11 . The robotic system of claim 10 , further comprising a robotic arm moveable about six degrees of freedom.

12 . The robotic system of claim 11 , wherein the gripping member and the end effector are coupled with the robotic arm.

13 . The robotic system of claim 12 , further comprising an RGB-D camera mounted on the robotic arm, wherein the RGB-D camera is configured to provide vision-based guidance instructions to the robotic arm, wherein the vision-based guidance instructions includes at least one of a position and a distance of the robotic arm related to the portion of the one or more of the agricultural crops during the crop sampling procedure.

14 . The robotic system of claim 11 , wherein the first LiDAR sensor is a two-dimensional LiDAR sensor, wherein the second LiDAR sensor is a three-dimensional LiDAR sensor.

15 . A robotic system operable to navigate a terrain adjacent one or more agricultural crops, comprising:

a) a movable body operable to navigate a ground terrain adjacent one or more agricultural crops;

b) a first LiDAR sensor configured to capture a first set of LiDAR data, wherein the first set of LiDAR data includes a first three-dimensional LiDAR dataset;

c) a second LiDAR sensor configured to capture a second set of LiDAR data, wherein the second set of LiDAR data includes a second three-dimensional LiDAR dataset;

d) a robotic arm movable about six degrees of freedom, including:

i) a gripping member selectively operable to grasp one or more of the agricultural crops; and

ii) an end effector selectively operable to cut and remove a portion from one or more of the agricultural crops; and

e) a controller configured to:

i) generate terrain navigation instructions utilizing a Monte Carlo Localization algorithm, wherein the Monte Carlo Localization algorithm includes the VIO data from the tracking camera and the first set of LiDAR data; and

ii) initiate a crop sampling procedure by selectively controlling the gripping member and end effector, wherein the crop sampling procedure includes cutting and removing the portion from one or more of the agricultural crops;

wherein the Monte Carlo Localization algorithm of the controller incorporates an Extended Kalman Filter (EKF) to generate the terrain navigation instructions;

wherein the movable body is coupled with a plurality of wheels configured to navigate the ground terrain, wherein the plurality of wheels defines a wheel odometry while the movable body navigates the ground terrain adjacent one or more agricultural crops, wherein the EKF is configured to combine the wheel odometry and the VIO data.

16 . The robotic system of claim 15 , further comprising a robotic arm moveable about six degrees of freedom.

17 . The robotic system of claim 16 , further comprising:

a) a gripping member selectively operable to grasp one or more of the agricultural crops; and

b) an end effector selectively operable to cut and remove a portion from one or more of the agricultural crops;

wherein the gripping member and the end effector are coupled with the robotic arm.