Disney Enterprises, Inc.

Novalogic, Inc.

Kyle G Freeman

Michael Richard Honeck

Jeremie A Papon

Jeremy Andrew Mika

Michael Fusco

Cory J Rouse

Shelley O Short

Clifford W Wong

Jon Hayes Snoddy

Raymond J Scanlon

Daniel C Pike

Jerry W Rees

Lance Duane Updyke

Carol Ann O'Sullivan

Chonhyon Park

Max L Gilbert

Jan Ondrej

An interactive autonomous robot is configured for deployment within a social environment. The disclosed robot includes a show subsystem configured to select between different in-character behaviors depending on robot status, thereby allowing the robot to appear in-character despite technical failures. The disclosed robot further includes a safety subsystem configured to intervene with in-character behavior when necessary to enforce safety protocols. The disclosed robot is also configured with a social subsystem that interprets social behaviors of humans and then initiates specific behavior sequences in response.

Interactive autonomous robot configured with in-character safety response protocols

Interactive autonomous robot configured for deployment within a social environment

A self-guiding automaton includes sensors, a hardware processor, and a memory storing a self-guidance software code. The hardware processor executes the self-guidance software code to detect a location and/or travel path of one or more human being(s) in a pedestrian environment using the sensors, and identify a self-guided path forward in the pedestrian environment based on the location and/or travel path of each human being(s). The self-guidance software code also determines a social cue for communicating the self-guided path forward to the human being(s), detects any change in the location and/or travel path of each human being(s) using the sensors, determines a pedestrian safety score of the self-guided path forward based on the location and/or travel path and any change in the location and/or travel path of each human being(s), and moves the automaton along the self-guided path forward if the pedestrian safety score satisfies a safety threshold.

Communicative self-guiding automation

Embodiments provide for perceptual data association from at least a first and a second sensor disposed at different positions in an environment, in respective series of local scene graphs that identify characteristics of objects in the environment that are updated asynchronously and merging the series of local scene graphs to form a coherent image of the environment from multiple perspectives.

Perceptual data association

Embodiments provide for perceptual data association received from at least a first and a second sensor disposed at different positions in an environment, in respective time series of local scene graphs that identify several characteristics of at least one object in the environment that are updated different rates; merging, at an output rate, characteristics for each given object from the several time series of local scene graphs that are updated at the output rate; merging, at the output rate, characteristics for each given object from the time series of local scene graphs that are updated at rates other than the output rate; and outputting, at the output rate, a time series of global scene graphs including the merged characteristics.

Systems and methods for tracking subjects within a three-dimensional physical environment are presented herein. A ranging sensor is mounted at a sensor location in the environment. The ranging sensor generates sensor output. The sensor output includes detected ranges of surfaces present in the environment as a function of orientations of the ranging sensor. Characteristics of the surface are determined using the detected ranges and orientations as polar coordinates of the surfaces.

Tracking subjects using ranging sensors

A method for localizing robots and other objects when ranging devices are partially obstructed. The method includes retrieving a digital map of the space and then identifying potential locations for the object in the space. The method involves generating a prediction of expected ranges between the object and surfaces in the space at each of the potential locations. The method includes operating a ranging device to measure ranges to the surfaces in the space and comparing, for each of the predictions, the measured ranges with the expected ranges to identify the most accurate prediction. The comparing includes weighting ranges that are too small neutrally as these are strikes on obstructions, weighting ranges that provide matches positively, and weighting ranges that are too large negatively, and the comparing then involves summing the weighted ranges to identify a most accurate one of the predictions and associated current location for the object.

Map localizing with partially obstructed ranging devices for autonomous robots and vehicles

A trained classifier to be used with a navigation algorithm for use with mobile robots to compute safe and efficient trajectories. An offline learning process is used to train a classifier for the navigation algorithm (or motion planner), and the classifier functions, after training is complete, to accurately detect intentions of humans within a space shared with the robot to block the robot from traveling along its current trajectory. At runtime, the trained classifier can be used with regression based on past trajectories of humans (or other tracked, mobile entities) to predict where the humans will move in the future and whether the humans are likely to be blockers. The planning algorithm or motion planner generates trajectories based on predictions of human behavior that allow the robot to navigate amongst crowds of people more safely and efficiently.

Trained human-intention classifier for safe and efficient robot navigation

A technique for the realistic simulation of visual scenes uses voxels generated from positional and elevational data combined with a stored color map to generate vertex and triangle data that is used by an accelerator card to render a visual scene on a display device. In this manner, the invention provides rendering efficiency and speed for highly detailed visual scenes while preventing overdraw.

Method for rendering realistic terrain simulation

Color video data is compressed by storing only the most frequently occurring colors in a block of pixel data. A minimum number of colors for the block is determined determining when colors in a block are the same or comparatively close to colors in the corresponding block of the previous video frame or are comparatively close to colors in the next previous adjacent block such that no additional color data needs to be stored, and by consolidating comparatively close colors withing the block. Two comparatively close colors are consolidated by substituting the more frequently occurring color for the less frequently occurring color in the block. Colors are comparatively close when the difference in their color values is less than a color threshold value. The color threshold value can be set by the user. If the minimum number of colors determined for the block is greater than four, then the color thresholds are adjusted and a new minimum number of colors is then determined. The pixel data of the block are stored in accordance with the minimum number of colors determined for that block. Greater compression is achieved when a lower minimum number of colors is determined for the block. Further compression can be achieved by incorporating a reference to a buffer containing common colors, and using a flag stored in the video stream to indicate when the data included in a byte of color data is an index value pointing to a color stored in the buffer rather than actual color data.

Video compression and playback process

A technique and system for the realistic simulation of visual scenes reduces the three-dimensional computation to two additions and further reduces the need for three-dimensional computations by displaying several screen pixels per three-dimensional computation. The approach when implemented in hardware or software significantly speeds up scene generation time while improving the resolution and realism of the rendered scene.

System and method for realistic terrain simulation

Color video data is compressed by storing only the most frequently occurring colors in a block of pixel data. A minimum number of colors for the block is determined by consolidating comparatively close colors. Two comparatively close colors are consolidated by substituting the more frequently occurring color for the less frequently occurring color in the block. Colors are comparatively close when the difference in their color values is less than a color threshold value. The color threshold value can be set by the user. If the minimum number of colors determined for the block is greater than four, then the color thresholds are adjusted and a new minimum number of colors is then determined. The pixel data of the block are stored in accordance with the minimum number of colors determined for that block. Greater compression is achieved when a lower minimum number of colors is determined for the block.

Real-time video and animation playback process

A technique and system for the real-time computation of visual scenes reduces the three-dimensional computation to two additions and further reduces the need for three-dimensional computations by displaying several screen pixels per three-dimensional computation. The approach when implemented in hardware or software significantly speeds up scene generation time. From a two-dimensional array of elevations a series of cross-sections perpendicular to the observer are constructed. For each elevation within the cross-section, a series of screen pixels is drawn. The next array element in the cross-section is found by adding a value to both indexes in the two-dimensional array.

Growing community of inventors

Agoura, CA, United States of America

Kyle G Freeman