Abstract: A method and apparatus for determining an action for minimizing jerk to improve the ride comfort of an autonomous vehicle based on deep reinforcement learning.

Abstract: Provided is a method and an apparatus for determining a vehicle behavior, and more specifically, to a method and an apparatus for determining a vehicle behavior for bottleneck congestion control in a bottleneck section. Tn apparatus for determining a vehicle behavior may include an information collection unit collecting surrounding information of a target driving vehicle from a road side unit (RSU), a vehicle observation unit obtaining observation information based on the target driving vehicle from a sensing module mounted on the target driving vehicle, a reward determination unit determining a reward for the target driving vehicle through a reward function which uses the surrounding information and the observation information, a model training unit updating and training a decision making model through the reward, and a behavior determination unit determining a behavior of the target driving vehicle by inputting the observation information into the decision making model.

Abstract: A deep reinforcement learning-based vehicle action decision apparatus for merging strategy of an autonomous vehicle in an on-ramp merging zone is disclosed.

Abstract: A traffic control method and apparatus with an autonomous vehicle based on adaptive reward. A traffic control apparatus for an autonomous vehicle based on adaptive reward comprises an information observation unit that collects observation information from a sensing module of an autonomous vehicle or a roadside unit (RSU); a policy execution unit that decides on an action including adjusting acceleration and changing lanes of the autonomous vehicle based on the observation information and policy; and a reward determination unit that determines reward according to observation information at a next timestep according to the decision made, wherein reward in the reward determination unit includes penalty in an event of an accident and reward when driving, wherein the reward when driving includes an adaptive target speed reward term, a successful lane change reward term, and a safety distance compliance reward term that are adaptively determined according to road traffic.

Abstract: A fine-tuning method and system for classifying an anomaly type. The fine-tuning system for classifying an anomaly type comprises an anomaly detection device configured to collect abnormal data and normal data, and detect anomaly in the collected data through a hierarchical anomaly detection model with a plurality of pre-trained detection stages to output an entire latent vector for the collected data for each of the plurality of detection stages and a latent vector of data detected as anomaly; and an anomaly type classification device configured to perform pre-training and fine-tuning of the classification model for each of the plurality of detection stages using a set of the entire latent vectors and a set of latent vectors detected as anomaly, and classify an anomaly type of data detected as anomaly in each of the plurality of detection stages using the fine-tuned classification model.

Abstract: A deep reinforcement learning-based decision-making apparatus through prior data and selective imitation learning is disclosed. The deep reinforcement learning-based decision-making apparatus comprises a prior data collection unit configured to collect prior data from one or more other agents; a prior data processing unit configured to process the collected prior data into data including state, action, next state, and reward; and a policy learning unit configured to learn policy of an ego agent using the processed prior data and interaction data including state, action, next state, and reward obtained through real-time interaction with environment.

Abstract: A deep reinforcement learning-based vehicle action decision apparatus for merging strategy of an autonomous vehicle in an on-ramp merging zone is disclosed.

Abstract: An offline reinforcement learning apparatus for n-step return-based implicit regularization is disclosed. The offline reinforcement learning apparatus comprises a processor; and a memory connected to the processor, wherein the memory comprises program instructions, in response to being executed by the processor, perform operations comprising, sampling, among datasets collected in a preset domain, some datasets including state, action, state at the next time point, reward, and return in n-step, calculating an objective function of a state value model that evaluates a value of a specific state using the sampled data set to update a parameter of the state value model, setting a TD (temporal difference) target based on the state value model, calculating an objective function of a state-action value model that evaluates a value of a specific state and action.

Abstract: A traffic control method and apparatus with an autonomous vehicle based on adaptive reward. A traffic control apparatus for an autonomous vehicle based on adaptive reward comprises an information observation unit that collects observation information from a sensing module of an autonomous vehicle or a roadside unit (RSU); a policy execution unit that decides on an action including adjusting acceleration and changing lanes of the autonomous vehicle based on the observation information and policy; and a reward determination unit that determines reward according to observation information at a next timestep according to the decision made, wherein reward in the reward determination unit includes penalty in an event of an accident and reward when driving, wherein the reward when driving includes an adaptive target speed reward term, a successful lane change reward term, and a safety distance compliance reward term that are adaptively determined according to road traffic.

Abstract: A method and apparatus for augmenting knowledge using federated learning information. An apparatus for augmenting knowledge using federated learning information comprises a transceiver unit that receives local information including a global parameter of a local model, a local latent vector, and a local loss value from each of a plurality of individual devices, a data storage unit that stores the local information, a federated learning execution unit that collects a global parameter of the local model and generates a federated global parameter for a global model, and a large model learning unit that generates a true label approximate value for learning a large model using the local information and the federated global parameter, and learns the large model using a prediction result obtained by inputting the local latent vector into the large model and the true label approximate value.

Abstract: An offline reinforcement learning-based foresighted decision-making apparatus and method for interaction between multiple agents.

Abstract: Provided is an anomaly detection method performed by an electronic device. The method performed by an electronic device including one or more processors, a communication circuit which communicates with an external device, and one or more memories storing at least one instruction executed by the one or more processors may include: by the one or more processors, receiving target data for discriminating whether an anomaly occurs, in which the target data includes a value for each of a plurality of features; inputting a value for at least one important feature among the plurality of features into an anomaly detection model, in which the at least one important feature is determined by important feature information received from the external device; and determining whether the target data is abnormal based on an output of the anomaly detection model.

Abstract: Provided is a method and an apparatus for determining a vehicle behavior, and more specifically, to a method and an apparatus for determining a vehicle behavior for bottleneck congestion control in a bottleneck section. Tn apparatus for determining a vehicle behavior may include an information collection unit collecting surrounding information of a target driving vehicle from a road side unit (RSU), a vehicle observation unit obtaining observation information based on the target driving vehicle from a sensing module mounted on the target driving vehicle, a reward determination unit determining a reward for the target driving vehicle through a reward function which uses the surrounding information and the observation information, a model training unit updating and training a decision making model through the reward, and a behavior determination unit determining a behavior of the target driving vehicle by inputting the observation information into the decision making model.

Abstract: Provided is a method of personalized federated learning performed by an electronic device. The method is performed by an electronic device including one or more processors, a communication circuit which communicates with an external device, and one or more memories storing at least one instruction executed by the one or more processors. The method may include, by the one or more processors, training a local model using local data, in which the local model as an artificial neural network model includes a first parameter set corresponding to a global parameter set and a second parameter set corresponding to a local parameter set, transmitting the first parameter set to the external device, receiving a 1-1st parameter set for renewing the first parameter set from the external device, changing the first parameter set included in the local model to the 1-1st parameter set, and training the local model including the 1-1st parameter set.

Abstract: A method for propagating network management data for energy-efficient internet of things network management and an energy-efficient internet of things node apparatus are disclosed herein. The method includes dividing a plurality of sub-nodes into at least two terminal sub-nodes and the remaining intermediate sub-nodes, and determining a transmission path so that the terminal sub-nodes and the intermediate sub-nodes satisfy an acyclic graph condition, dividing the plurality of pieces of data of network management information into at least two data groups, and transmitting one of the at least two data groups to one of the terminal sub-nodes respectively, transmitting the data of the received data group to adjacent intermediate sub-nodes, performing network coding on selected two pieces of data, transmitting the network-coded data to the at least two intermediate adjacent sub-nodes, and decoding the received network-coded data using previously held data.

Abstract: A method for propagating network management data for energy-efficient internet of things network management and an energy-efficient internet of things node apparatus are disclosed herein. The method includes dividing a plurality of sub-nodes into at least two terminal sub-nodes and the remaining intermediate sub-nodes, and determining a transmission path so that the terminal sub-nodes and the intermediate sub-nodes satisfy an acyclic graph condition, dividing the plurality of pieces of data of network management information into at least two data groups, and transmitting one of the at least two data groups to one of the terminal sub-nodes respectively, transmitting the data of the received data group to adjacent intermediate sub-nodes, performing network coding on selected two pieces of data, transmitting the network-coded data to the at least two intermediate adjacent sub-nodes, and decoding the received network-coded data using previously held data.