IP Library › Granted Patent US 9,630,324
Granted Patent B2
US 9,630,324 · App. 14/619,035 · Granted Apr 25, 2017

Enhanced system and method for control of robotic devices

Inventors: Adam Cohen (Oakland, CA); James L. Barber (Spokane Valley, WA); Michael A. Singer (Belmont, CA); Daniel Chavez (Berkeley, CA); Farid W Saddik (Santa Clara, CA); James Creasy (Berkeley, CA); Alan Gushurst (Pleasanton, CA)
Assignee: SKUR, Inc.
B25J13/006B25J9/1661B25J9/1689B25J9/1697H04L67/12Y10S901/47
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 9,630,324
App. No.
14/619,035
Filed
Feb 10, 2015
Granted
Apr 25, 2017
Kind
B2
Examiner
WONG, YUEN H
Art Unit
3667
USPC
700/253
Abstract

A system for robotic device control and data acquisition, comprising a robotic device control system adapted to receive sensor-based data comprising physical object information, the sensor-based data being received from a plurality of sources, each source comprising at least a physical sensor in communication with the robotic device control system computer via a communications network, an enhanced robotic device control application adapted to receive sensor-based data from the robotic device control system computer and manipulate the sensor-based data to produce enhanced data, and a method for robotic device control and data acquisition.

Claims (27)

1. A system for robotic device control and data acquisition, comprising:

a plurality of network-connected hardware sensors;

a network-connected robotic device control system computer comprising a processor, a database, a memory, and program code, wherein the program code, when executed by the processor, causes the processor to:

receive, from the plurality of network-connected hardware sensors, via the network, a plurality of sensor-based data point clouds, each point cloud comprising a plurality of sensor-based data points associated to a physical object via the network;

an enhanced network-connected robotic device control application computer comprising another processor, a database, a memory, and another program code, wherein the another program code when executed by the another processor, cause the another processor to:

receive, via the network, the plurality of sensor-based data point clouds from the robotic device control system computer, and

for at least a portion of the plurality of sensor-based data point clouds of each point cloud, add one or more properties, the one or more properties comprising information whether a data point is in, on, or outside the physical object;

a network-connected database computer comprising a further processor, a database, a memory, and further program code, wherein the further program code when executed by the further processor, cause the further processor to:

store the plurality of sensor-based data point clouds received from the robotic device control system and the enhanced robotic device control application computer,

wherein at least the plurality of sensor-based data point clouds are stored according to a sparse-point model,

wherein upon only a subset of the plurality of sensor-based data points from a first point cloud corresponding to the physical object are available, the plurality of sensor-based data point clouds from a second point cloud are combined with the plurality of sensor-based data point clouds from the first point cloud to form an enhanced data point cloud to achieve a best possible point cloud for maximum completion of the enhanced data point cloud associated to the physical object,

wherein superfluous sensor-based data points of the plurality of sensor-based data points are removed as noise from the sparse point cloud model,

wherein sensor-based data points with no properties are removed from the sparse point cloud model,

wherein at least a portion of the second point cloud comprises one or more sensor-based data points not available in the first point cloud, and

wherein the enhanced robotic device control application computer converts at least the sensor-based data for each point cloud between the sparse point cloud model and a vectorized object model in a two-way reversible manner to optimize data processing for data originated from the plurality of network-connected hardware sensors associated to the physical object.

2. The system of claim 1 , wherein the physical object is a civil engineering structure.

3. The system of claim 1 , wherein a database comprises at least a relational database.

4. A method for robotic device control and data acquisition, comprising steps of:

receiving, at a robotic device control system including a plurality of network-connected hardware sensors via a network, a plurality of point clouds, each point cloud comprising sensor-based data;

for each point cloud, processing, at the robotic device control system, a plurality of sensor-based data;

for at least a portion of the plurality of sensor-based data, adding, by an enhanced robotic device control application computer, one or more properties, the one or more properties comprising information whether a data point is in, on, or outside an associated physical object;

storing, in a database computer, the sensor-based data for each point cloud in a sparse-point model;

upon only a subset of sensor-based data points from a first point cloud corresponding to the physical object are available, combining, by the enhanced robotic device control application computer, sensor-based data points from a second point cloud with sensor-based data points from the first point cloud to form an enhanced data point cloud to achieve a best possible point cloud for maximum completion of the enhanced data point cloud associated to the physical object, wherein at least a portion of the second point cloud comprises sensor-based data points not available in the first point cloud; and

converting at least the sensor-based data for each point cloud, using the enhanced robotic device control application computer, between a vectorized model and the sparse-point model in a two-way reversible manner to optimize data processing for data originated from the plurality of network-connected hardware sensors associated to the physical object.

5. The method of claim 4 , further comprising step of producing a plurality of mission record flat files based at least in part on received sensor-based data, the flat files comprising a plurality of data pertaining to the plurality of sensor-based data.

6. The method of claim 5 , further comprising step of building a memory structure of data comprising at least a portion of the plurality of sensor-based data, the memory structure being based at least in part on a mission record flat file.

7. The method of claim 6 , further comprising step of building the memory structure based at least in part on a size of at least a memory flat file.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 8, 2016
From: COHEN, ADAM; BARBER, JAMES L.; SINGER, MICHAEL A.; CHAVEZ, DANIEL; SADDIK, FARID W; CREASY, JAMES; GUSHURST, ALAN
To: SKUR, INC.
Reel/Frame 037681/0440 →
Continuity (2)
Provisional Application 61972201 · Mar 28, 2014
Related Publication 20150273693A1 · Oct 1, 2015