Toyota Motor Engineering & Manufacturing North America, Inc.

Toyota Jidosha Kabushiki Kaisha

Yongkang Liu

Kentaro Oguchi

Xuewei Qi

Prashant Tiwari

Kyungtae Han

Emrah Akin Sisbot

Ziran Wang

Zhenyu Shou

Takamasa Higuchi

Seyhan Ucar

System, methods, and other embodiments described herein relate to predicting trajectories of multiple vehicles using graphs and multiple decoding models. In one embodiment, a method includes computing, using an encoding model, a graph having a geographic map and vehicle features associated with a plurality of vehicles in an area according to characteristics, prior trajectories, and spatiotemporal interactions. The method also includes processing, using the encoding model, updates for the geographic map and the vehicle features separately in association with encoded features of neighboring vehicles. The method also includes decoding, using a probability model and a regression model, the geographic map and the vehicle features to output estimated trajectories for the plurality of vehicles.

Systems and methods for predicting trajectories of multiple vehicles

Systems and methods are provided for estimating the energy range of an electric vehicle, including updating an energy consumption estimation model based on the location of a vehicle or based on the current time. One embodiment comprises obtaining a route of a vehicle and deploying an energy consumption estimation model to provide an energy consumption estimate along the route from a first location to a destination. In response to determining that the vehicle enters a subsequent location, the energy consumption estimation model is updated with a location model received from an edge/cloud server, to estimate an energy range along the route through the subsequent location.

Customized electrical vehicle range estimation system based on location and driver

Systems, methods, and other embodiments described herein relate to improving the performance of a device in different geographic locations by using transfer learning to provide a customized learning model for the different locations. In one embodiment, a method includes receiving segments of a model from separate members in a geographic hierarchy and assembling the segments into the model. The segments include at least a first segment, a second segment, and a third segment. The method includes processing sensor data using the model to provide an output for assisting a device.

Hierarchical transfer learning system

A trailer monitoring system for a vehicle includes a processor and a memory communicably coupled to the processor. The memory stores instructions that when executed by the processor cause the processor to receive, from at least one monocular camera mounted to a vehicle towing a trailer, at least one monocular camera image of at least a portion of the trailer. The instructions also cause the processor to generate at least one depth map based on the at least one monocular camera image. The instructions further cause the processor to identify a trailer irregularity based on the at least one depth map.

Trailer monitoring system

An object detection system for a vehicle includes a processor and a memory communicably coupled to the processor. The memory stores instructions that when executed by the processor cause the processor to receive a priority assignment set by an occupant of a vehicle. The priority assignment corresponds to a customization of at least one warning characteristic. The at least one warning characteristic includes a distance threshold. The instructions also cause the processor to detect an object in an external environment of the vehicle and apply the priority assignment to the object. The instructions further cause the processor to issue a warning according to the at least one warning characteristic. According to the distance threshold, the warning is issued when a distance from the vehicle to the object meets the distance threshold.

Object detection system

A rest stop recommendation system monitors driving behavior of a driver and stores information indicating the driving behavior as historical data, determines, based at least in part on the historical data, a driver tiredness state, a continuous driving length preference, and a refueling pattern preference, determines a time to recommend a rest stop based at least in part on the driver tiredness state, the continuous driving length preference, and the refueling pattern preference, extracts, from a map database, a plurality of rest stops within a predetermined radius of a position of the vehicle, determines rest stop characteristic preferences based at least in part on the historical data, selects one or more potential rest stops from among the plurality of rest stops based at least in part on the rest stop characteristic preferences, and presents the one or more potential rest stops to the driver in a recommendation.

Rest stop recommendation system

System, methods, and other embodiments detecting and localizing objects within an image in a wide-view format using a synthetic representation. The method includes converting a real image in a wide-view format to a synthetic representation using a style model, wherein the synthetic representation depicts a distorted view of an object. The method also includes identifying features of the object using an extraction model that distinguishes different scales of the synthetic representation and a simulated scene to define structures associated with the distorted view. The method also includes detecting the object using a decoder model that identifies an attribute and a bounding box of the object from the features. The method also includes executing a task using the attribute and the bounding box to localize the object in the simulated scene.

Systems and methods for detecting objects within an image in a wide-view format

In accordance with one embodiment of the present disclosure, method includes obtaining multi-level environment data corresponding to a plurality of driving environment levels, encoding the multi-level environment data at each level, extracting features from the multi-level environment data at each encoded level, fusing the extracted features from each encoded level with a spatial-temporal attention framework to generate a fused information embedding, and decoding the fused information embedding to predict driving environment information at one or more driving environment levels.

Multi-scale driving environment prediction with hierarchical spatial temporal attention

A method for generating a dataset is provided. The method includes generating, within a simulated environment, a simulated image including one or more distortions, the simulated image includes a plurality of vehicles, generating vehicle image patches and ground truth from the simulated image, performing, using a style transfer module, a style-transfer operation on the vehicle image patches, combining the vehicle image patches, on which the style-transfer operation is performed, with a background image of a real-world location, and generating a dataset based on the ground truth and the combination of the vehicle image patches and the background image.

Methods and systems for generating simulated datasets for fisheye camera applications

A method comprises making initial predictions of whether a first vehicle will perform a lane change at a plurality of future time steps based on sensor data captured by an egovehicle; and in response to making an initial prediction that the first vehicle will perform a lane change at a first one of the future time steps, making final predictions that the first vehicle will perform a lane change at each of a plurality of time steps subsequent to the first one of the future time steps.

Systems and methods for long-term prediction of lane change maneuver

An object detection system can identify a specific object in a two-dimensional image. A processor can receive the two-dimensional image with bounding boxes around objects. The processor can cause a point to appear in the two-dimensional image. The point can represent a position, in three-dimensional space, of the specific object. The processor can determine an existence of a condition. The condition can be that the point is enclosed by a plurality of bounding boxes. The processor can receive, in response to the existence of the condition, a depth image. The processor can determine, in response to the existence of the condition and based on information included in the depth image and a location of the point in the two-dimensional image, a specific bounding box that encloses the point. The processor can cause, based on a location of the specific bounding box, an indication of the specific object to be presented.

Identifying a specific object in a two-dimensional image of objects

Systems and methods described herein relate to providing guidance to vehicle drivers regarding predicted lane-change behavior of other drivers. One embodiment transforms historical vehicle trajectory data into a corresponding alternative representation; applies a clustering algorithm to group a plurality of drivers into groups of similar drivers; applies Bayesian inference to train a Bayesian neural network (BNN) for the drivers in each group; adapts the BNN for each group to generate a personalized BNN for each driver in that group; identifies a particular driver on a roadway; receives information regarding the particular driver's vehicle and one or more other nearby vehicles; estimates a probability that the particular driver will change lanes using the personalized BNN for that driver; and communicates guidance regarding predicted lane-change behavior of the particular driver to at least one nearby vehicle based, at least in part, on the estimated probability that the particular driver will change lanes.

Growing community of inventors

Plano, TX, United States of America

Yongkang Liu