Mitsubishi Electric Research Laboratories, Inc.

Disney Enterprises, Inc.

Mitsubishi Electric Research Labs.

Mitsubishi Electric Corporation

Jeroen Van Baar

Ramesh Raskar

Wojciech Matusik

Hanspeter Pfister

Paul A Beardsley

Collin E Oosterbaan

Markus H Gross

Thomas H Willwacher

Mouhacine Benosman

Matthias Zwicker

Radu Ioan Corcodel

Siddarth Jain

Dohyung Seo

Petros T Boufounos

Hassan Mansour

Jay E Thornton

Oncel C Tuzel

Paul H Dietz

Alan Sullivan

Rasmus Tamstorf

Steven Poulakos

Reazul Hasan Russel

Srinivasa G Rao

Rakshith Sharma Srinivasa

A system for parameter tuning for robotic manipulators is provided. The system includes an interface configured to receive a task specification, a plurality of physical parameters, and a plurality of control parameters, wherein the interface is configured to communicate with a real-world robot via a robot controller. The system further includes a memory to store computer-executable programs including a robot simulation module, a robot controller, and an auto-tuning module a processor, in connection with the memory. In this case, the processor is configured to acquire, in communication with the real-world robot, state values of the real-world robot, state values of the robot simulation module, simultaneously update, by use of a predetermined optimization algorithm with the auto-tuning module, an estimate of one or more of the physical, and said control parameters, and store the updated parameters.

Simulation-in-the-loop tuning of robot parameters for system modeling and control

A system for trajectories imitation for robotic manipulators is provided. The system includes an interface configured to receive a plurality of task descriptions, wherein the interface is configured to communicate with a real-world robot, a memory to store computer-executable programs including a robot simulator, a training module and a transfer module, and a processor, in connection with the memory. The processor is configured to perform training using the training module, for the task descriptions on the robot simulator, to produce a plurality of source policy with subgoals for the task descriptions. The processor performs training using the training module, for the task descriptions on the real-world robot, to produce a plurality of target policy with subgoals for the task descriptions, and update the parameters of the transfer module from corresponding trajectories with the subgoals for the robot simulator and real-world robot.

Transfer between tasks in different domains

A controller is provided for interactive classification and recognition of an object in a scene using tactile feedback. The controller includes an interface configured to transmit and receive the control, sensor signals from a robot arm, gripper signals from a gripper attached to the robot arm, tactile signals from sensors attached to the gripper and at least one vision sensor, a memory module to store robot control programs, and a classifier and recognition model, and a processor to generate control signals based on the control program and a grasp pose on the object, configured to control the robot arm to grasp the object with the gripper. Further, the processor is configured to compute a tactile feature representation from the tactile sensor signals and to repeat gripping the object and computing a tactile feature representation with the set of grasp poses, after which the processor, processes the ensemble of tactile features to learn a model which is utilized to classify or recognize the object as known or unknown.

Interactive tactile perception method for classification and recognition of object instances

A controller for controlling a system having uncertainties in its dynamics subject to constraints on an operation of the system is provided. The controller is configured to acquire historical data of the operation of the system, and determine, for the system in a current state, a current control action transitioning a state of the system from the current state to a next state. The current control action is determined according to a robust and constraint Markov decision process (RCMDP) that uses the historical data to optimize a performance cost of the operation of the system subject to an optimization of a safety cost enforcing the constraints on the operation, wherein a state transition for each of state and action pairs in the performance cost and the safety cost is represented by a plurality of state transitions capturing the uncertainties of the dynamics of the system.

Apparatus and method for controlling a system having uncertainties in its dynamics

A multi-modal dense correspondence image processing system submit the multi-modal images to a neural network to produce multi-modal features for each pixel of each of the multi-modal image. Each multi-modal image includes an image of a first modality and a corresponding image of a second modality different from the first modality. The neural network includes a first subnetwork trained to extract first features from pixels of the first modality, a second subnetwork trained to extract second features from pixels of the second modality, and a combiner configured to combine the first features and the second features to produce multi-modal features of a multi-modal image. The system compares the multi-modal features of a pair of multi-modal images to estimate a dense correspondence between pixels of the multi-modal images of the pair and outputs the dense correspondence between pixels of the multi-modal images in the pair.

Multi-modal dense correspondence imaging system

A radar imaging system to reconstruct a radar reflectivity image of a scene including an object moving with the scene, includes an optical sensor to track the object over a period of time including multiple time steps to produce, for each of the multiple time steps, a deformation of a nominal shape of the object, and an electromagnetic sensor to acquire snapshots of the scene over the multiple time steps to produce a set of radar reflectivity image of the object with deformed shapes defined by the corresponding deformations of the nominal shape of the object. The system also includes a processor configured to determine, for each of the multiple time steps using the deformation determined for the corresponding time step, a transformation between the radar reflectivity image of the object acquired by the electromagnetic sensor at the corresponding time step and a radar reflectivity image of the object in the prototypical pose, and to combine the radar reflectivity images of the object with deformed shapes transformed with the corresponding transformations to produce the radar reflectivity image of the object in the prototypical pose.

System and method for multimodal, motion-aware radar imaging

A method registers a deformable image to a fixed image by first acquiring the deformable image and the fixed image. Multi-resolution multi-level image pyramids are generated for the deformable and fixed images. Levels of the multi-resolution multi-level image pyramids are processed in a coarse to fine order, and for each deformable and fixed image at each level partitioning the deformable and fixed image into overlapping blocks, and labeling each block with a label by solving, iteratively and in parallel, until a termination condition is reached, a binary maximum flow problem, within &#x3b1;-expansion, for each block and performing boundary fusion for the blocks, and then registering each block according to the labels to form the fixed image.

Method for deformable image registration

A method registers a source image with a target image, wherein the images are deformable, by first measuring dissimilarity between the source image and the target image. The dissimilarity minimized using a discrete energy function. At multiple scales, multi-scale Markov random field registration is applied to the source and target images to determine a deformation vector field. Then, the target image is warped according to the deformation field vector to obtain a warped target mage registered to the source image.

Method for registering deformable images using random Markov fields

A method denoises a noisy image by, for each pixel in the noisy image, first constructing a key from a patch, wherein the patch includes locally neighboring pixels around the pixel. A function is selected from a function library using the key. Then, the function is applied to the patch to generate a corresponding noise free pixel for the pixel.

Image denoising using a library of functions

Where images are displayed such that unintended light is also included and that light cannot be fully subtracted from the displayed image, an image processor compensates by compensating for the remaining light using perceptual models. In some cases, the perceptual model includes a plurality of user sensitivities and computation is performed, at least in part, based on expected user sensitivity to light pollution in portions of the images. The perceptual model might include a contrast sensitivity function, threshold-vs-intensity, saliency prediction and visual masking. The model might include artist indications of view attention. A light pollution likelihood map might be used to reduce the amount of computation needed, using a likelihood measure to determine an amount of computation to perform.

Perceptually-based compensation of unintended light pollution of images for projection display systems

A method generates input text with a pointing device at a distance from a writing surface. Motion information of a mobile coordinate frame of the pointing device is sensed relative to a stationary coordinate frame of the writing surface using a motion sensor configured to track motion of the pointing device. The input text is then determined from the motion information. A projection of a track of the motion of the pointing device on the writing surface can also be determined from the motion information, and the track can be displayed on the writing surface as the input text.

Motion-based text input

A method adjusts a pose of a projector with respect to a display surface. A homography His determined between a display surface and a projector. The homography His decomposed into rotation and translation parameters expressing a pose Mof the projector. An ideal pose Mof the projector corresponding to an ideal homography His determined. A pose adjustment Mis determined according to M=M(M). The pose adjustment Mis decomposed into rotation and translation adjustment parameters. Then, the projector is adjusted mechanically to the ideal pose Maccording to the rotation and translation adjustment parameters.

System and method for mechanically adjusting projector pose with six degrees of freedom for image alignment

A wireless location and identification system includes a controller and a tag. The controller has a projector configured to generate a unique temporal sequence of light intensities for each pixel in an output image of the projector and a wireless transceiver configured to emit an output signal and receive an input signal. The tag includes a photo-sensor configured to sense the unique temporal sequence of light intensities of a particular pixel, a transducer configured to receive the output signal from the transceiver, and a means for modulating, according to the unique temporal sequence of light intensities, the input signal for the transceiver in response to receiving the output signal and sensing the unique temporal sequence of light intensities of the particular pixel to indicate a location of the tag to the controller.

Interactive wireless tag location and identification system

A rigidly-coupled projector-camera system is augmented with laser pointers. The projector-camera system and lasers can be used to determine homography between the projector and a display surface, so that a projection of any desired geometry can be made on the display surface.

Projector-camera system with laser pointers

A system projects multiple output images on a display surface. The system includes multiple projectors. Each projector includes a processing unit. The processing unit includes a microprocessor, a memory and an I/O interface connected by busses. A projector sub-system coupled to the processing unit is for displaying output images on the display surface. A camera sub-system coupled to the processing unit is for acquiring input images reflecting a geometry of the display surface. The camera sub-system is in a fixed physical relationship to the projector sub-system. A network sub-system coupled to the processing unit is for communicating messages between the projectors. Internal sensors coupled to the processing unit are for determining an orientation of the projector sub-system and the camera sub-system with respect to the display surface.

Growing community of inventors

Arlington, MA, United States of America

Jeroen Van Baar