Mitsubishi Electric Research Laboratories, Inc.

Honda Motor Co., Ltd.

Mitsubishi Electric Research Labs.

Rethink Robotics Gmbh

Mitsubishi Electric Corporation

Yuri A Ivanov

Jay E Thornton

Christopher Richard Wren

John C Barnwell, Iii

Fatih M Porikli

Alex Paul Pentland

Abraham Goldsmith

Rodney Brooks

Christopher R Wren

Thomas R Serre

James Barabas

Rizwan Choudhry

Alexander Sorokin

Ishwinder Kaur Banga

Andrea E G Bradshaw

Systems and methods for providing precise robotic operations without the need for special or task-specific components utilize, in one implementation, a spatial adjustment system, physically separate from the robotic manipulator, supports the target workpiece and works in concert with the robotic manipulator to perform tasks with high spatial precision.

Robotic placement and manipulation with enhanced accuracy

A display system includes a display device having multiple possible poses, including a neutral pose. A physical constraint maintains the display device in the neutral pose absent an application of an external force. A sensor measures a magnitude and direction of a displacement of the display device to a displaced pose due to the application of the external force. Then, the rendering engine renders an image on the display device according to the magnitude and direction of the displacement even while the display device remains constant in the displaced pose.

Method and system for displaying images on moveable display devices

A path of a particle beam is determined through a 3D planning treatment volume (PTV), wherein the PTV includes a set of slices in a depth order, and each slice includes a set of locations. For each slice, the set of locations are grouped into a set of lines along a selected direction, wherein each line is a straight line and includes a starting location and an ending location, and each line is connected to one or two other lines, and the connecting connects two lines to either the starting location or the ending location of the lines to form a tour, and the tours are connected through the slices in the depth order to form the path of the particle beam.

Method for determining paths of particle beams through 3D tissue volumes

A network in an environment includes passive sensors with associated sensor identification numbers. A set of active badges with associated badge identification numbers, wherein each badge is associated with an object, and wherein a particular sensor broadcasts a packet in response to detecting a particular object, wherein the packet includes the sensor identification number and a time, and only if the particular object is associated with a particular badge then the badge appends the badge identification number to the packet and broadcasts the appended packet, and the particular sensor receives and rebroadcasts the appended packet for further processing to passively and actively monitor the environment.

Active badge localization using passive sensors

Embodiments of the invention disclose a system and a method for determining a nearest neighbor to an input data point on a non-Euclidean manifold. The data points on the non-Euclidean manifold are clustered, projected into Euclidean sub-space nearest to the cluster and mapped from the Euclidean sub-space into a Hamming space such that neighboring data points of the Hamming space corresponds to neighboring data points on the non-Euclidean manifold. The method maps the input data point to the Hamming space corresponding to a particular Euclidean sub-space, wherein the particular Euclidean sub-space is the nearest to the input data point, and selects a data point corresponding to a nearest data point to the input data point in the Hamming space as the nearest neighbor for the input data point on the non-Euclidean manifold.

Nearest neighbor methods for non-Euclidean manifolds

A method and system tracks models and predict object movement in an environment. Sequences of temporally and spatially adjacent events sensed by the set of sensors are linked to form a set of tracklets. Each tracklet has an associated starting and terminating location. The tracklets are used to construct a directed graph including starting nodes, terminating nodes, and, intermediate nodes connected by edges. The intermediate nodes can be split nodes where tracklets diverge onto different tracks, and join nodes where multiple tracklets converge onto a single path. Probabilities are assigned to the edges to model and predict movement of the objects in the environment.

System and method for modeling movement of objects using probabilistic graphs obtained from surveillance data

A method determines an error in aligning a patient with a radiation beam. A planning volume V is acquired during treatment planning, and a treatment volume I is acquired during treatment. For each point r in the planning volume and treatment volume to be aligned by a coordinate transformation T, a weighted error DWE is minimized using an objective function F(r, T) applied to the planning volume and the treatment volume weighted by a weighting function W(r) as where W(r) is a function of a target weight W, a tissue at risk weight W, and a delivered dose weight W.

Plan-based medical image registration for radiotherapy

Embodiment of the invention describes a system and a method for positioning an object from a first pose to a second pose. The method displays concurrently a first image and a second image on a display device, wherein the first image and the second image represent respectively the first pose and the second pose of the object. The method updates, in response to a change in a pose of the display device, the second image such that an alignment of the first image and the second image on the display device depends on the change in the pose of the display device, and positions the object from the first pose to the second pose based on the change in the pose of the display device.

Positioning an object based on aligned images of the object

A method and an apparatus determines a geometry of a scene by projecting one or more output image into the scene, in which a time to project the output image is t. Input images are acquired of the scene, in which a time to acquire each input image is t, and in which t&#x3e;tand in which the input image includes a distinguishable stripe of pixels with an edge due to t&#x3e;t. An amount of distortion of the edge is measured from a straight line to determine a geometry of the scene.

System and method for determining geometries of scenes

A method detects an object left-behind in a scene by updating a set of background models using a sequence of images acquired of the scene by a camera. Each background model is updated at a different temporal scales ranging from short term to long term. A foreground mask is determined from each background model after the updating for a particular image of the sequence. A motion image is updated from the set of foreground masks. In the motion, image, each pixel has an associated evidence value. The evidence values are compared with a evidence threshold to detect and signal an object left behind in the scene.

Method for detecting objects left-behind in a scene

Techniques are disclosed for multi-modal identification that utilize a classifier combination framework. One embodiment of the present invention provides a multi-modal identification system that includes a collection of classifiers that classify feature streams derived from audio and/or video sources. A classifier combination scheme is used to combine the classifier outputs having varying degrees of confidence, but in a robust way by using a confidence-based weighting scheme that operates on a 'per-class' basis, rather than (or in addition to) the traditional 'per-classifier' basis. The system can be distributed across several machines running independent feature classifiers on the subscription basis.

Confidence weighted classifier combination for multi-modal identification

A method constructs a strong classifier from weak classifiers by combining the weak classifiers to form a set of combinations of the weak classifiers. Each combination of weak classifiers is boosted to determine a weighted score for each combination of weak classifiers, and combinations of weak classifiers having a weighted score greater than a predetermined threshold are selected to form the strong classifier.

Weighted ensemble boosting method for classifier combination and feature selection

A system and a method are disclosed for automatically controlling the position of a mirror to stabilize the view in the mirror in spite of changes in viewing position. Initially, a mirror position is set by a user so that the user can comfortably view the reflection of a desired area. A tracking system estimates the user's viewing position. As a user's viewing position changes, the system reorients the mirror such that the reflection in the mirror is stabilized.

Automatic mirror stabilization

A system and a method are disclosed for identifying pixels belonging to moving objects in a series of images by using a signed difference operation. A first signed difference is determined between a first image and a second image. A second signed difference is determined between a second image and a third image. Pixels that change from a positive sign in the first signed difference to a negative sign in the second signed difference belong to the moving object in the second image.

Adaptive tracking for gesture interfaces

The location of an object in a physical scene is identified with a stereo camera. A virtual surface is identified in the physical scene, and an approximate disparity set is constructed for the virtual surface. A main and a reference image of the scene are acquired by the stereo camera. The reference image is warped according to the disparity set, and subtracted from the main image to determine a set of depth residual values. Pixels having a substantially non-zero residual are identified with a surface of the object not coincident with the virtual surface.

Growing community of inventors

Arlington, MA, United States of America

Yuri A Ivanov