Omron Corporation

Scientific Technologies Corporation

Omron Scientific Technologies, Inc.

Omron Scientic Technologies, Inc.

John Drinkard

Ambrish Tyagi

Yoshiharu Tani

Christopher Alan Dums

Fred Schleifer

Koichi Kinoshita

Gaurav Misra

Takeshi Shoji

Akihiro Suzumura

Javier Cardona

Sean Bailey

Alejandro Ruiz Sanchez

Andres Rodriguez Campo

Karthik Mahesh Varadarajan

Galen Knode

Kautilya Chenna

Ed Oltman

Javier Onses Cardona

Christopher Dums

Disclosed techniques for graph generation for online path planning offer multiple advantages, such as providing for high-quality motion during online operation of the robot, while reducing the computational burden of graph generation. Achieving these competing goals involves reducing the dimensionality of the graph generation problem by performing unconstrained sampling that defines partial robot poses that set values for fewer than all configuration parameters of the robot. The remaining configuration parameters for each sample are then determined in dependence on a distance function that relates the partial pose to one or more reference robot poses that are associated with one or more tasks to be performed by the robot and are provided as inputs to the graph generation. Reference robot poses may be determined automatically based on computer analysis of the robot application or may be user-input values.

Method and apparatus for improved sampling-based graph generation for online path planning by a robot

Disclosed techniques embody advantageous approaches to online task and motion planning for robots, based on the decomposition of robot tasks into subtasks having attached attributes that, among other things, indicate whether dynamic trajectory modification is permitted during subtask execution. The decomposition and attribute tagging allows for hybrid motion control during task execution, for example, with some subtasks allowing for reactive motion planning for collision avoidance, and other subtasks disallowing reactive motion. Collision avoidance for non-reactive subtasks involves, for example, coordinating volume reservations within an involved robot work cell, to prevent other robots from interfering with a robot engaged in a subtask designated as non-reactive. Determination of which subtasks are non-reactive relies on information included in an input task specification and may be based on user analysis or automated analysis of the involved robot application.

Method and apparatus for online task planning and robot motion control

A map updating technique offers the performance advantages gained by robots using a good-quality static map for autonomous navigation within an environment, while providing the convenience of automatic updating. In particular, one or more robots log data while performing autonomous navigation in the environment according to the static map, and a computer appliance, such as a centralized server, collects the logged data as historic logged data, and performs a map update process using the historic logged data. Such operations provide for periodic or as needed updating of the static map, based on observational data from the robot(s) that capture changes in the environment, without need for taking the robot(s) offline for the computation.

Method and apparatus for updating an environment map used by robots for self-localization

The present invention comprises an apparatus and method for monitoring a zone, which is a contiguous or non-contiguous, two-dimensional (2D) area or three-dimensional (3D) volume. Among its several advantages, the apparatus includes a plurality of sensors that monitor portions of the zone and report intrusion status to a control unit that provides monitoring boundary information to each of the sensors based on user input and further 'maps' or otherwise associates each sensor to control unit outputs in accordance with user-defined behaviors. Still further, as a meaningful aid for configuring monitoring boundaries used by the sensors for objection intrusion detection, in one or more embodiments of the apparatus and method, at least a subset of sensors use a common coordinate frame of reference, based on a common origin located within overlapping sensor fields of view.

Method and apparatus for monitoring zones

According to one aspect of the teachings herein, a method and apparatus detect mechanical misalignments in a machine vision system during run-time operation of the machine vision system, and compensate image processing based on the detected misalignments, unless the detected misalignments are excessive. Excessive misalignments may be detected by determining a worst-case error based on them. If the worst-case error exceeds a defined limit, the machine vision system transitions to a fault state. The fault state may include disrupting operation of a hazardous machine or performing one or more other fault-state operations. Among the detected misalignments are internal misalignments within individual cameras used for imaging, and relative misalignments between cameras. The method and apparatus may further perform run-time verifications of focus and transition the machine vision system to a fault state responsive to detecting insufficient focal quality.

Method and apparatus for detecting and mitigating mechanical misalignments in an optical system

The teachings herein provide a method and apparatus for detecting erroneous pixel addressing in an imaging sensor. The method and apparatus advantageously leverage the characteristic 'fixed pattern noise' of the sensor to detect addressing errors. Broadly, pixel addressing errors are detected based on comparing the pattern noise seen in data read outs from a targeted address of the sensor with characteristic fixed pattern noise known for the sensor.

Method and apparatus for fault detection for imager decoder

According to one aspect of the teachings presented herein, a machine vision system includes one or more sensor units that are each advantageously configured to use different pairings among a set of spaced-apart image sensors, to provide redundant object detection for a primary monitoring zone, while simultaneously providing for the detection of objects that may shadow the primary monitoring zone. Further, a plurality of 'mitigations' and enhancements provide safety-of-design and robust operation. Such mitigations and enhancements include, for example, bad-pixel detection and mapping, cluster-based pixel processing for improved object detection, test-image injection for fault detection, dual-channel, redundant processing for safety-critical object detection, temporal filtering to reduce false detections, and the use of high dynamic range (HDR) images, for improved operation over variable ambient lighting conditions.

Method and apparatus for projective volume monitoring

According to one aspect of the teachings presented herein, a projective volume monitoring apparatus is configured to detect objects intruding into a monitoring zone. The projective volume monitoring apparatus is configured to detect the intrusion of objects of a minimum object size relative to a protection boundary, based on an advantageous processing technique that represents range pixels obtained from stereo correlation processing in spherical coordinates and maps those range pixels to a two-dimensional histogram that is defined over the projective coordinate space associated with capturing the stereo images used in correlation processing. The histogram quantizes the horizontal and vertical solid angle ranges of the projective coordinate space into a grid of cells. The apparatus flags range pixels that are within the protection boundary and accumulates them into corresponding cells of the histogram, and then performs clustering on the histogram cells to detect object intrusions.

In one aspect of the teachings herein, a 3D imaging apparatus uses a 'texture tool' or facilitates the use of such a tool by an operator, to add artificial texture to a scene being imaged, for 3D imaging of surfaces or background regions in the scene that otherwise lack sufficient texture for determining sufficiently dense 3D range data. In at least one embodiment, the 3D imaging apparatus provides for iterative or interactive imaging, such as by dynamically indicating that one or more regions of the scene require artificial texturing via the texture tool for accurate 3D imaging, and then indicating whether or not the addition of artificial texture cured the texture deficiency and/or whether any other regions within the image require additional texture.

Method and apparatus for generating texture in a three-dimensional scene

Zone selection logic in an area monitoring device increases the number of unique monitoring zone selections that can be selected using a limited number of discrete zone selection inputs, without compromising the safety critical operation of zone selection. The device monitors the logical state of each input in a set of individual inputs and recognizes each unique logical combination of zone selection inputs as a different zone selection. For example, each of two or more configured monitoring zones is associated with a different combinatorial zone selection pattern of asserted zone selection input signals. Correspondingly, a control circuit within the area monitoring device is configured to monitor the discrete zone selection inputs and activate a given one of the configured monitoring zones based on recognizing the associated combinatorial zone selection pattern of asserted zone selection signals.

Method and apparatus for zone selection in area monitoring devices

According to a method and apparatus taught herein an active object detection system performs reliable object detection based on light pulse emissions and corresponding and time-of-flight based distance determination, while advantageously rejecting clutter. While not limiting, the method and apparatus taught herein may be particularly advantageous for safety-critical object detection applications, such as where the active object detection system, e.g., a laser scanner, monitors for objects of at least a specified size within a predetermined monitoring radius or contour.

Clutter rejection in active object detection systems

A presence sensing system provides one or more visible indicators useful for indicating a relative location of objects sensed within the scanning field of view. For example, the system may have an indicator array or an integrated display assembly in which individual indicators or indicator positions correspond to defined portions of the system's field of view. In this manner, the presence sensing system can indicate where one or more sensed objects lie within its field of view. The system may monitor or otherwise scan an angular field of view and may have an indicator array comprising a plurality of individual indicators, each one corresponding to a portion of the monitored area. With this configuration, the system selectively illuminates or otherwise activates those indicators in the array corresponding to the relative angles of detected objects within its field of view.

Presence sensing system and method

A data reduction circuit serves as a post-processor for digitized waveform data, providing reduced data sets for subsequent processing. Preferably, the data reduction circuit receives one or more potentially long sequences of digital waveform data and provides as output sets of sequence numbers corresponding to transitions in the digitized waveforms. In this manner, a processor concerned with the location of waveform transitions is relieved from the burden of processing the sequences just to identify the transition points. In some embodiments, the data reduction circuit cooperates with a waveform digitizer that produces digitized sequences of comparator waveforms in a laser-based distance measuring circuit. Transition points in the digitized waveform correspond to return reflections of emitted laser pulses and may be used to identify laser pulse flight time. Thus, reporting only sequence numbers for the waveform transition points greatly reduces the amount of data transferred to a distance-calculating processor.

System and method for waveform processing

A circuit generates a test signal useful in verifying the actual delay values of individual delay stages in a digital delay line. In general, the cumulative delay of the delay line defines a window in time having its zero point anchored to the beginning of the delay line. Successive delay stages correspond to successive time bins within the overall time window. The test signal shifts at a known, linear rate in time with respect to a reference signal, which is used to initiate a test cycle. The reference signal synchronizes sampling of the test signal to the beginning of the time window. Samples of the test signal are taken at sample points determined by the actual time delays in the successive delay stages. The observed distribution of test signal edges across the time window may be used to determine the actual delay intervals of the delay line.

System and method for delay line testing

A clockless time-of-flight interval timer includes a tapped delay line register comprising N buffers that each contribute a substantially identical incremental time delay. A latched version of a START pulse associated with an output of transmitted energy from a laser is propagated through the tapped delay line. A DATA signal representing a detected pulse returned from a target is coupled to a block of four comparators each having a different signal threshold. The output of each comparator block is provided as input to one of four channel registers, each register comprising N D-type flipflops separately but synchronously triggerable by tapped incrementally delayed outputs from the N buffers. Channel register outputs are multiplexed and decoded and interfaced with a microprocessor. The microprocessor determines first signal time over threshold (FOT) information and total time over threshold (TOT) information from the channel registers. The FOT provides a measure of time-of-flight, which measure can be corrected using TOT information and a look-up table containing timing walk incremental delay corrections for individual ones of the N buffers. TOT information can be used as an indicator of signal strength and thus may be used to correct for systematic errors in measured delay, which arise from fluctuation in signal strength.

Growing community of inventors

Foster City, CA, United States of America

John Drinkard