Abstract: An end effector for a robotic arm. The end effector includes an angle compensator for attaching a suction cup, a vacuum control valve, a vacuum generator, a level compensator, and an extension tube which are sequentially connected along a central axis and in fluid communication, and a vacuum sensor connected to the vacuum control valve for measuring vacuum, a proximity sensor attached to the extension tube 121 for determining position of the level compensator. The vacuum is generated when compressed air passes the extension tube, the level compensator and the vacuum generator along the central axis. The level compensator provides compensation along the central axis.

Abstract: A system and a method for pose tracking, particularly for top-down, online, multi-person pose tracking. The system includes a computing device having a processor and a storage device storing computer executable code. The computer executable code, when executed at the processor, is configured to: provide a plurality of sequential frames of a video, the sequential frames comprising at least one keyframe and a plurality of non-keyframes; for each of the non-keyframes: receive a previous inference bounding box of an object inferred from a previous frame; estimate keypoints from the non-keyframe in an area defined by the previous inference bounding box to obtain estimated keypoints; determine object state based on the estimated keypoints, wherein the object state comprise a “tracked” state and a “lost” state; and when the object state is “tracked,” infer an inference bounding box based on the estimated keypoints to process a frame next to the non-keyframe.

Abstract: A system for alarm correlation and aggregation. The system includes a computing device. The computing device has a process and a storage device storing computer executable code. The computer executable code, when executed at the processor, is configured to: provide a plurality of alarms triggered by components of the system; provide aggregation patterns; perform iteratively until a criterion is met: generating itemsets from the alarms using the aggregation patterns, computing a new aggregation pattern from the generated itemsets using frequent itemset mining, and updating the aggregation pattern using the new aggregation pattern to obtain updated aggregation patterns; and aggregate the alarms using the updated aggregation patterns to obtain aggregated alarms.

Abstract: A method and a system for self-checkout. The system includes a scanner, an imaging device, and a computing device. The computing device is configured to: initiate a self-checkout event; instruct the imaging device to capture video frames of a region of interest (ROI); track the product; record scanning status and location status of the product; in response to receive a scanning signal from the scanner, record scanning status of the product as scanned; calculate a shoplifting risk score based on a number of the product having the scanning status of unscanned and disappears from the table region or ROI; and provide a shoplifting warning when the shoplifting score is large.

Abstract: A soft package includes a package body made of a soft deformable material, and a plurality of rigid gripping components disposed at periphery or corners of the package body. Each of the rigid gripping components includes a rigid ring structure configured to be gripped by a robot device. A robot system may be used to process the soft package, by controlling a computer vision system of the robot system to capture images of the soft package, processing the images of the soft package to recognize the locations of the rigid gripping components, and controlling the robot devices of the robot system to grasp the rigid gripping components.

Abstract: A method, a device and a non-transitory computer readable medium for tracking poses of multiple objects. The method includes detecting, by a processor, objects from each of a plurality of consecutive frames in a video sequence; estimating, by the processor, a pose of each of the objects within each of the plurality of consecutive frames; and tracking, by the processor, the poses of each of the objects across the plurality of consecutive frames.

Abstract: 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.

Abstract: A method for generating a deserialization vulnerability report of a Java project, includes: determining, by a computing device, if interior knowledge of the Java project is available, and when the interior knowledge of the Java project isn't available, performing a black box analysis to generate the deserialization vulnerability report; and when the interior knowledge of the Java project is available, determining by the computing device if source code of the Java project is accessible, when the source code of the Java project is accessible, performing a white box analysis to generate the deserialization vulnerability report, and when the source code of the Java project isn't accessible, performing a gray box analysis to generate the deserialization vulnerability report.

Abstract: A method and system for constructing an evolving ontology database. The method includes: receiving a plurality of data entries; calculating semantic similarity scores between any two of the data entries; clustering the data entries into a multiple current themes based on the semantic similarity scores; selecting, new concepts from the current themes by comparing the current themes with a plurality of previous themes prepared using previous data entries; and updating the evolving ontology database using the new concepts. The semantic score between any two of the data entries are calculated by: semantic similarity score=?i=0nsie?j=0kwj×f j, where si is weight of features sources, fj is a feature similarity between the two of the data entries, wj is a weight of fj, and j, k and n are positive integers.

Abstract: A method and system for searching encrypted data using wildcard keywords. The method includes: obtaining, by a first computing device, a keyword for data to be encrypted, where the keyword has a fixed length; generating a sequence of primes; determining corresponding one prime from the sequence of primes for each character of the keyword; and defining a product of the corresponding primes of the characters of the keyword as index of the encrypted data, where the index can be searched using a wildcard search keyword.

Abstract: System and method for semantic segmentation. The system includes a computing device. The computing device has a processor and a non-volatile memory storing computer executable code. The computer executable code, when executed at the processor, is configured to: receive an image of a scene; process the image by an encoder to form an encoder feature map; process the encoder feature map by a pyramid pooling module (PPM) to form an PPM feature map; and process the PPM feature map by a decoder to form a segmentation feature map.

Abstract: A method and system for encryption and decryption. The system includes a user computing device, a root secret server, and a backend server. The root secret server has a root secret code, and when receiving a fingerprint of the user computing device, calculates a device secret code for that device using the fingerprint. When sensitive data needs to be encrypted, the user computing device calculates a data key for the data based on the device secret code and the data information, and encrypts the data. The backend server retrieves the root secret code from the root secret server, and in response to receiving the encrypted data, retrieves data information and calculates the data key to decrypt the data. Similarly, the backend server can encrypt data and the user computing device can decrypt data. The root secret code, the device code, and the data key form a three level encryption mechanism.

Abstract: A system and method for autonomous navigation using a visual sparse map. The system includes a robotic device having an RGB-D camera, a processor and a storage device storing computer executable code. The computer executable code is configured to: obtain the visual sparse map based on captured RGB-D images; capture an RGB image; acquire a current pose of the robotic device; find a keyframes nearest to the current pose of the robotic device; find a target waypoint that is ahead of the nearest keyframe at about a pre-defined distance; compute transition velocity and rotation velocity of the robotic device based on relative location between the robotic device and the target waypoint; and control operation of the robotic device using the computed transition velocity and rotation velocity to achieve autonomous navigation.

Abstract: A system for monitoring file integrity in a host computing device having a process and a storage device storing computer executable code. The computer executable code is configured to: provide containers, an agent external to the containers, and a policy file configuring policy for the containers; intercept a system call indicating mounting, and construct a first correspondence between a container file path and a host file path having mounting correspondence; intercept a system call of the container indicating opening of the policy file, and construct a second correspondence between the container file path and the violation of the container file path; aggregate the first and second correspondences to obtain a correspondence between the host file path and the violation; and monitor file integrity of the container by detecting violation of the host file path.

Abstract: A method and system for generating an answer to a question. The system includes a computing device. The computing device has a processor and a storage device storing computer executable code. The computer executable code, when executed at the processor, is configured to: receive the question inputted by a user regarding a product; extract target answers from a question-answer (QA) knowledge base using the question to form an answer set; extract user comments regarding the product from a comment database to form a comment set; cluster keywords in the answer set to obtain cluster centers; filter the answer set and the comment set using the cluster centers to obtain answer subset and comment subset; and generate the answer to the question from the comment subset, wherein the answer is selected from the comment subset and has high sentence similarity to sentences in the answer subset.

Abstract: A method and system for monitoring an e-commerce platform using artificial intelligence and fixing malfunctions on the e-commerce platform. The method includes: receiving, by a computing device, a feedback submitted by a user through the e-commerce platform; generating a vector based on content of the feedback, context of the feedback and profile of the user using AI processors; and classifying the vector to determine function corresponding to the feedback and status of the function using AI classifiers. The content includes text, voice, image and video; the context includes time, location and submission channel of the feedback; the profile includes attributes, history and preference of the user. Dimensions of the vector respectively corresponding to the text, voice, image, video, time, location, submission channel, attributes, history, and preference of the user.

Abstract: A method and system for true product word recognition using a computing device. The method includes: obtaining title words from titles of products; determining word vectors based on a word matrix, where the word matrix is constructed based on a number of cooccurrence of each of the title words and all the other title words; determining title vectors based on a title matrix, where the title matrix is constructed based on the number of cooccurrence of each of the title words and all the other title words, and the title words in each of the titles; calculating scores for the title words in corresponding one of the titles based on the corresponding word vector and title vector; and recognizing true product words of the corresponding one of the titles based on the scores.

Abstract: 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.

Abstract: A mobile robotic device and a method for controlling the mobile robotic device to move are provided. The mobile robotic device includes: a body; a rotatable portion connected to the body and configured to support the body in a rotatable manner; and an operational portion which comprises at least two arms connected to the body and configured to support the body in a walkable manner. In operation, the mobile robotic device is switchable between a manipulation mode in which the rotatable portion supports the body in the rotatable manner and a locomotion mode in which the at least two arms support the body in the walkable manner.

Abstract: A method and system for generating an article of a product. The method includes: receiving a request from a user; when the request include an identification of the product, retrieving traits of the product from a trait database, when the request include keywords, retrieving the traits of the product by comparing the similarity between the keywords and the traits or the synonym of the traits; generating candidate sentences corresponding to the traits; selecting sentences from the candidate sentences, and revising and rearranging the sentences to generate the article.