Fujitsu Corporation

Massachusetts Institute of Technology

Takuro Ikeda

Eiji Kitagawa

Hiroshi Yamada

Ryosuke Miyata

Toshiyuki Fukuoka

Kyouko Okuyama

Vishal Sharma

Taizo Anan

Shigeyoshi Umemiya

Moshe E Ben-Akiva

Masashi Yamaumi

Bilge Atasoy

Ryosuko Miyata

An action selection learning device includes a memory; and a processor coupled to the memory and configured to generate a reference model that is a set of model parameter vectors that indicate an influence level of each factor that influences selection of an action alternative, calculate a selection probability for each action alternative, for each of the model parameter vectors, calculate a model parameter vector for each user using a subset of model parameter vectors extracted from the reference model, based on the selection probability for each action alternative and a selection history of the action alternative by each user, generate the action alternatives based on the model parameter vector for each user, and transmit the generated action alternatives to a terminal device.

Action selection learning device, action selection learning method, and storage medium

An estimation method executed by a computer, the estimation method includes estimating a fouling degree of a target ship based on an accumulation period since a most recent maintenance on the target ship; selecting, as training data, one piece of data that has a fouling degree that resembles the estimated fouling degree, from among a plurality of pieces of data, when generating a machine learning model for estimating an amount of fuel consumption due to navigation; and generating the machine learning model based on the selected training data.

Estimation method, training method, storage medium, and estimation device

A congestion management apparatus includes a memory configured to store, on a per-action-option basis, upper limits on numbers of users allowed to be guided to action options, and a processor coupled to the memory and configured to: generate the action options by time slot for a user; calculate for each of the generated action options, choice probabilities of the action options with respect to the user, and store the calculated choice probabilities in the memory; and calculate for each of the action options, estimated numbers of previous users assumed to have selected the action options, based on choice probabilities of each of the action options with respect to the previous users, the choice probabilities being obtained from the memory, wherein the processor is configured to extract, based on the upper limits and the estimated numbers for the action options, action options to be presented to the user.

Congestion management apparatus and congestion management method

A transportation service reservation method executes, by a computer, a process including receiving a ride request specifying an origin and a destination, generating feasible products having service types, by referring to a storage unit that stores information indicating a schedule allocated to each vehicle and the service types of the schedule, for each vehicle capable of providing products having the service types, computing a choice probability of each product forming an assortment of the feasible products, for each of assortments satisfying a predetermined condition amongst the subsets of the feasible product set that are generated, computing an expected value of a number of future ride requests, and selecting an assortment to be presented with respect to the ride request, from the assortment satisfying the predetermined condition, based on the choice probability and the expected value.

Transportation service reservation method, transportation service reservation apparatus, and computer-readable storage medium

A vehicle behavior estimation device includes: a storage unit configured to store a restriction condition at a point of a vehicle for which behavior is estimated; vehicle state data that includes position information and speed information of the vehicle; behavior parameters that include speed information and acceleration information of the vehicle; and physical restriction conditions that include an upper limit and a lower limit of the acceleration information; and a processor configured to obtain the vehicle state data by using the restriction condition at the point; calculate behavior parameters of a vehicle model that satisfy a physical restriction condition from the vehicle state data and the restriction condition at the point; update the vehicle state data of the vehicle model based on the behavior parameters; and repeat processing to calculate behavior parameters by using the updated vehicle state data and to update the vehicle state data.

Vehicle behavior estimation device

A simulator used in a distributed process simulation includes: a storage unit configured to store map information, agent information, and area allocation information; a simulation execution unit; a condition determination unit configured to determine the condition of the reference agent to be referenced by the simulation execution unit based on a movement state of the agent; an allocation discrimination unit configured to discriminate another computer allocated an area in which the reference agent corresponding to the condition can be located; and an agent information acquisition unit configured to acquire the information about the agent satisfying the condition of the reference agent from the other discriminated computer.

Distributed process simulator

A drive assist apparatus includes: a road-information storage unit storing road information; a traffic-signal information storage unit to store information regarding a traffic-signal change timing; a receiving unit to receive other-vehicle information; an obtaining unit to obtain host-vehicle information; a determining unit to determine whether the other vehicle becomes an obstacle to the host vehicle; and a calculating unit to calculate a recommended speed based on the host-vehicle information, the road information, and information regarding the traffic-signal change timing, when the other vehicle is determined to not become an obstacle to the host vehicle, and calculate the recommended speed based on the host-vehicle information, the road information, the information regarding the traffic-signal change timing, and an arrival delay time for avoiding an obstacle caused by the other vehicle, when the other vehicle is determined to become the obstacle to the host vehicle.

Drive assist apparatus, method, and recording medium

A simulator simulates the behavior of a plurality of agents existing in the virtual space. Each of a plurality of calculators, communicable with one another, includes a space allocation storage that stores space allocation information, a space allocation control part that updates the space allocation information, an allocation change candidate space extracting part that extracts a divided space to be a candidate for the allocation change, a communication amount estimating part that calculates an amount of communication or an amount of change in communication generated between calculators based on the number of agents, a space allocation change judging part that determines whether or not to allocate a divided space to another calculator based on the amount of communication or the amount of change in communication, and a space allocation change executing part that requests the space allocation control part and other calculators to change the space allocation.

Distributed processing-type simulator

There is provided a driving assist system comprising: a road side apparatus which transmits the traffic circumstance information; and a vehicle-mounted apparatus including: an outputting part which outputs driving assist information for assisting a driving operation on the basis of output data on the basis of the at least one kind of the traffic circumstance information; and a controller for: generating the output data for outputting the driving assist information based on the traffic circumstance information; determining whether the output data is valid; and selecting one the output data which is determined as valid, on the basis of a predetermined standard validity, wherein the outputting part outputs the driving assist information using the selected output data.

Driving assist system and vehicle-mounted apparatus

A navigation device includes a data transmission-reception portion for performing data transmission and reception with a portable terminal, an address list cooperation portion for receiving address list data, a schedule cooperation portion for receiving and managing schedule data, a candidate location specifying information recording portion for searching and extracting information for specifying a location corresponding to one schedule item from the address list data concerning a schedule indicated in schedule data to record the extracted information, a position specifying information obtaining portion for obtaining position specifying information for specifying a position on a map corresponding to each piece of candidate location specifying information, a selecting portion for selecting one position specifying information from position specifying information, and a path managing portion for determining a position of each destination on the path in accordance with the selected position specifying information to manage the path information.

Growing community of inventors

Kawasaki, Japan

Takuro Ikeda