Xerox Corporation

Conduent Business Services, LLC

Naver Corporation

Naver Labs Corporation

Tomi Silander

Julien Perez

Christopher R Dance

Adrian Corneliu Mos

Michel Aractingi

A training system for training a trained model for use by a navigating robot to perform visual navigation includes memory including N base virtual training environments, each of the N base virtual training environments including a field of view at a location within an indoor space, where N is an integer greater than 1. A randomization module is configured to generate N varied virtual training environments based on the N base virtual training environments, respectively, by varying at least one characteristic of the respective N base virtual training environments. A training module is configured to train the trained model for use by the navigating robot to perform visual navigation based on a training set including: the N base virtual training environments; and the N varied virtual training environments.

Systems and methods for improving generalization in visual navigation

A system and method for predicting a sequence of actions employ a Gated End-to-End Memory Policy Network (GMemN2NP), which includes a sequence of hop(s). Supporting memories of the hops include memory cells generated from observations made at different times. A sequence of actions is predicted, based on input agent-specific variables. For each action, the model, at each hop, outputs an updated controller state which is used as input to the next hop or, for the terminal hop, for computing the respective action. Each hop includes a transform gate mechanism which is used to control the influence of output of the supporting memories on the updated controller state. For the second and subsequent hops, respective actions are predicted, after using any intervening observations to update the supporting memories. The model is learned, on a training set of observations, to optimize the cumulative reward of a sequence of two or more actions.

Non-Markovian control with gated end-to-end memory policy networks

A method and apparatus for detecting an error in a business process via an exchange of email messages. In one example, the method may be executed by a processor of a business process analysis server (BPAS). For example, the method includes receiving an email, wherein the email includes an address of the BPAS, analyzing the email to determine at least one feature, determining the business process based on the at least one feature, determining one or more variables that is associated with the business process, detecting the error in the business process associated with the email based on at least variable of the one or more variables associated with the business process and generating an alert email in response to the error that is detected, wherein the alert email requests a correction to the at least one variable to complete the business process.

System and method for automatic process error detection and correction

A proactive interaction system includes memory which stores a contextual model. The contextual model includes supporting memory storing a representation of each of a set of past observations. Each of the past observations having an observed reward for a respective user for a respective action selected from a set of candidate actions. The contextual model is configured for estimating a reward for each of a current set of candidate actions, based on the stored representations of past observations and a representation of a current user. Each candidate action is associated with a respective action representation. A contextual bandit selects one of the candidate actions, based on the estimated reward for each of the set of candidate actions, to optimize a cumulative reward over a sequence of candidate action selections. An act output component performs a user-detectable act based on the selected one of the candidate actions.

Contextual memory bandit for proactive dialogs

Data characterizing a system is received at an electronic processor. For example, parking event data from parking sensors of a parking facility is received. The electronic processor constructs a current state for the system (e.g. parking occupancy state of the parking facility) at a current time from the received data. State probabilities at a future time are computed (e.g. occupancy state probabilities are computed for the parking facility) using a continuous-time Markov chain model modified by multiplying the time input to the model by a random variable and scaling the state probabilities by an expectation of the random variable. In parking occupancy forecasting, parking guidance information is generated based at least on the computed occupancy state probabilities, and is transmitted to an electronic device other than the electronic processor (e.g. a parking recommendation transmitted to a vehicle navigation device, or a control signal transmitted to a 'lot full' sign).

Growing community of inventors

Grenoble, France

Tomi Silander