Sri International

Xerox Corporation

Beijing Jingdong Shangke Information Technology Co., Ltd.

Jd.com American Technologies Corporation

Sarnoff Corporation

Other

Beijing Jingdong Century Trading Co., Ltd.

Hui Ting Cheng

Harpreet Singh Sawhney

Ajay Divakaran

Omar Javed

Zhigang Fan

Jiangjian Xiao

Jingen Liu

Ying-wei Lin

Jayakrishnan Kumar Eledath

Qian Yu

Amir Tamrakar

Ishani Chakraborty

Jiejie Zhu

Shen-Ge Wang

Mayank Bansal

Feng Han

Bogdan Calin Mihai Matei

Sang-Hack Jung

Rakesh Kumar

John C Handley

Dennis Lee Matthies

Arkady Kopansky

Saad Masood Khan

Saad Ali

Salil Prabhakar

Chris Broaddus

Raja Bala

Beilei Xu

Stuart Alan Schweid

Keith James Hanna

Robert John Rolleston

Michael Anthony Isnardi

Jeffrey Lubin

Elliott A Eklund

Elizabeth E Shriberg

Vincent Paragano

Xiang Li

Aydin Arpa

Zhiwei Zhu

Steven S Weiner

Yanlin Guo

Behjat Siddiquie

Wei Xi

Chengzhi Qi

Zihang Wei

Changjiang Yan

Peng Chang

David Chisolm

Walter Paul

Nicholas John Vander Valk

Marusia Musacchio

Zhengmao Liu

Darren Butler

Mohamed Elhoseiny

A method and device for controlling a robot, and a robot. The device detects whether there is an article being put into or taken out from a storage container of a robot, and if it is detected that an article is put into or taken out from the storage container, an information list is updated according to the article being put into or taken out, the information list recording relevant information about articles in the storage container.

Method and device for controlling a robot, and robot

A method and system for monitoring an e-commerce platform. The system includes a computing device and a visual sensor. The computing device includes a processor and a storage device storing computer executable code. The computer executable code, when executed at the processor, is configured to: extract image keypoints from an image of the object captured by the visual sensor; retrieve a template of the object, where the template includes template keypoints of at least one template side surface of the object; pick two template keypoints from the template side surface and determine two image keypoints respectively matching the two picked template keypoints; build a bounding box of the object based on the two determined image keypoints; and refine the bounding box.

System and method for fast object detection in robot picking

A system for automatic product enrollment, includes: multiple visual sensors configured to capture images of a product; multiple scales configured to measure weight distribution of the product; and a computing device in communication with the visual sensors and the scales. The computing device is configured to: determine identification of the product and construct a 3D model of the product using the captured images; retrieve warehouse information of the product based on the identification; and enroll the warehouse information, the 3D model, and the weight distribution of the product into a product database. An automatic product enrollment method using the system.

System and method for automatic product enrollment

Zero-shot content detection includes building/training a semantic space by embedding word-based document descriptions of a plurality of documents into a multi-dimensional space using a semantic embedding technique; detecting a plurality of features in the multimodal content by applying feature detection algorithms to the multimodal content; determining respective word-based concept descriptions for concepts identified in the multimodal content using the detected features; embedding the respective word-based concept descriptions into the semantic space; and in response to a content detection action, (i) embedding/mapping words representative of the content detection action into the semantic space, (ii) automatically determining, without the use of training examples, concepts in the semantic space relevant to the content detection action based on the embedded words, and (iii) identifying portions of the multimodal content responsive to the content detection action based on the concepts in the semantic space determined to be relevant to the content detection action.

Zero-shot event detection using semantic embedding

A robot system for processing an object to be packaged as a product, a packaging method, and a method of processing the same are provided. The object has multiple surfaces, and multiple e-package information tags are provided on the surfaces of the object for storing information of the product. Each surface is provided with one of the e-package information tags. The information of the product includes information of a location, an orientation and physical features of the object. In operation, the robot system controls a sensing device to detect and capture one of the e-package information tags on the object to obtain a captured image, and processes the captured image to obtain the information of the product. Based on the information of the product, the robot system controls a robotic grasping device to perform a robotic manipulation for handling the object.

Robot system for processing an object and method of packaging and processing the same

A system for mapping and localization includes first and second robotic devices and fiducial tags placed at predetermined positions of an environment. The quality of the first robotic device is better than the second robotic device. The first robotic device prepares a high resolution multilayer map, and the second robotic device uses the multilayer map for fast and accurate localization. The first robotic device has a visual sensor and a light detection and ranging (LIDAR) device, and is configured to prepare the multilayer map by: constructing a feature point cloud layer of the environment using images captured by the visual sensor; building a tag layer comprising identifications and locations of the tags; constructing an occupancy map using LIDAR scans; and forming the multilayer map having the feature point cloud layer, the tag layer, and the occupancy map layer, which share the same coordinate system.

System and method for multimodal mapping and localization

Embodiments of the present disclosure disclose a method and an apparatus for controlling a mobile robot. A specific embodiment of the method comprises: generating pedestrian assessment information based on perception information of the mobile robot, wherein the pedestrian assessment information includes a pedestrian intent type and a pedestrian event type of the nearby pedestrian; then, generating pedestrian behavior information based on the perception information and the pedestrian assessment information, wherein the pedestrian behavior information includes a predicted position information sequence and a predicted behavior type sequence of the nearby pedestrian in a preset future time period; next, generating information for control use based on the perception information, the pedestrian assessment information and the pedestrian behavior information; finally, and controlling the mobile robot based on the information for control use. This embodiment improves a social acceptance of the mobile robot.

Method and apparatus for controlling a mobile robot

A computing system for recognizing salient events depicted in a video utilizes learning algorithms to detect audio and visual features of the video. The computing system identifies one or more salient events depicted in the video based on the audio and visual features.

Recognizing salient video events through learning-based multimodal analysis of visual features and audio-based analytics

Embodiments of the present disclosure disclose a fulfillment system, sorting methods and sorting apparatuses applied to the fulfillment system. A preferred embodiment of the method comprises: sending by a control server, target transportation indication information corresponding to a target order to a target vehicle, wherein the target transportation indication information includes the target order and a target storage compartment identifier, the target, storage compartment identifier being configured for indicating a target storage compartment in a target storage receptacle connected with the target vehicle; and then collecting, by the target vehicle, an item/items corresponding to the target order to the target storage compartment in response to receiving the target transportation indication information, thereby collecting the item(s) corresponding to each order to a specific storage compartment, which need not an additional sorting step, thereby reducing fulfillment costs.

Fulfillment system, and sorting methods and apparatuses applied to the fulfillment system

Embodiments of the present disclosure disclose a robot for sorting. A specific embodiment of the robot for sorting may comprise: at least one layer of trays; wherein an axial center of the tray is provided with a shaft; the tray is provided with a first slot that has an openable first door; an end of the tray extends upwardly to form a tray wall; a space separator for partitioning a storage bin is provided along the shaft of the tray till the tray wall; and the space separator is in rotary connection to the shaft of the tray and is rotatable about the shaft of the tray. This embodiment may adjust the size of the storage bin and the number of items placed in the storage bin, and by outputting the item through the openable first door, the output efficiency of the item in the storage bin is improved.

Robot for sorting

A flexible suction device and a robot system using the same are provided. The flexible suction device includes a flexible tube portion, and a suction cup connected to one end of the flexible tube portion, such that the suction cup may grasp an object by a suction force. The flexible tube portion is controllable to switch between a straight state and at least one bending state, such that the flexible tube portion is configured to bend from the straight state to the at least one bending state in order to swing and flip the object being grasped by the suction cup. In operation, the flexible suction device is controlled to grasp and lift the object in the straight state, and then switch to the bending state in order to swing the object being grasped. Thus, the flexible suction device may release the object, such that the object is flipped.

Flexible suction device, robot system and method using the same

A system for object detection and tracking includes technologies to, among other things, detect and track moving objects, such as pedestrians and/or vehicles, in a real-world environment, handle static and dynamic occlusions, and continue tracking moving objects across the fields of view of multiple different cameras.

Real-time detection, tracking and occlusion reasoning

A complex video event classification, search and retrieval system can generate a semantic representation of a video or of segments within the video, based on one or more complex events that are depicted in the video, without the need for manual tagging. The system can use the semantic representations to, among other things, provide enhanced video search and retrieval capabilities.

Classification, search and retrieval of complex video events

Technology for performing continuous authentication of a mobile device utilizes user activity context data and biometric signature data related to the user. A biometric signature can be selected based on the activity context, and the selected biometric signature can be used to verify the identity of the user.

Continuous authentication of mobile device users

An entity interaction recognition system algorithmically recognizes a variety of different types of entity interactions that may be captured in two-dimensional images. In some embodiments, the system estimates the three-dimensional spatial configuration or arrangement of entities depicted in the image. In some embodiments, the system applies a proxemics-based analysis to determine an interaction type. In some embodiments, the system infers, from a characteristic of an entity detected in an image, an area or entity of interest in the image.

Recognizing entity interactions in visual media

Growing community of inventors

Sunnyvale, CA, United States of America

Hui Ting Cheng