Abstract: Systems and methods are provided for assessing generalizations of machine learning models implemented in new environments, such as those not included in training data used to train the machine learning models. Examples include, after training the machine learning model on a set of training data, implementing the trained machine learning model a number of times in a new environment. For each implementation of the trained machine learning model in the new environment, a performance metric associated with performance of the machine learning model in the new environment can be measured and a confidence interval on a success rate of the machine learning model in the new environment can be determined based on the performance metric. The machine learning model can then be deployed on machines in the new environment based on the confidence interval.

Abstract: System, methods, and other embodiments described herein relate to communicating a recommended speed through feedback on a combined pedal for acceleration or braking. In one embodiment, a control system includes a pedal coupled to a first device having a throttle sensor for a vehicle and a first actuator that generates throttle feedback by applying force to the pedal. The control system also includes the pedal being coupled to a second device having a brake activation sensor for the vehicle and a second actuator that generates braking feedback, the first actuator triggers a rotation of the pedal that initiates a braking command through the brake activation sensor according to a recommended speed computed using vehicle data.

Abstract: Systems, methods, and other embodiments described herein relate to estimating scaled depth maps by sampling variational representations of an image using a learning model. In one embodiment, a method includes encoding data embeddings by a learning model to form conditioned latent representations using attention networks, the data embeddings including features about an image from a camera and calibration information about the camera. The method also includes computing a probability distribution of the conditioned latent representations by factoring scale priors. The method also includes sampling the probability distribution to generate variations for the data embeddings. The method also includes estimating scaled depth maps of a scene from the variations at different coordinates using the attention networks.

Abstract: A method for indicating occlusion information at an ego agent includes observing a spatial area from a first viewpoint of one or more first sensors associated with the ego agent. The method also includes identifying the spatial area as an occluded area in accordance with observing the spatial area from a second viewpoint of the one or more first sensors after observing the spatial area from the first viewpoint. The method further includes receiving, from a target agent, a message indicating the spatial area is occluded from one or more second sensors associated with the target agent. The method still further includes transmitting, to the target agent in accordance with receiving the message, the occlusion information indicating information associated the spatial area based on identifying the spatial area as the occluded area.

Abstract: Systems and methods for determining a maximum phase recovery envelope are disclosed herein. In one example, a system includes a processor and a memory having a vehicle control module. The vehicle control module includes instructions that, when executed by the processor, cause the processor to determine a critical point on a phase plane indicating a maximum defined recovery point a vehicle can recover from, perform forward and reverse simulations from the critical point to define outermost contours of a maximum phase recovery envelope using parameters and state of the vehicle, and cause the vehicle to operate within the maximum phase recovery envelope.

Abstract: A method for depth estimation performed by a depth estimation system associated with an agent includes determining a first depth of a first image and a second depth of a second image, the first image and the second image being captured by a sensor associated with the agent. The method also includes generating a first 3D image of the first image based on the first depth, a first pose associated with the sensor, and the second image. The method further includes generating a warped depth image based on transforming the first depth in accordance with the first pose. The method also includes updating the first pose based on a second pose associated with the warped depth image and the second depth, and updating the first 3D image based on the updated first pose. The method further includes controlling an action of the agent based on the updated first 3D image.

Abstract: A steering wheel-based HMI system for a vehicle includes a steer-by-wire system and a control module. The steer-by-wire system includes a steering wheel and a torque feedback unit mechanically connected to the steering wheel. The control module is communicatively connected to the torque feedback unit. The control module is configured to identify a communication, gather information about user securement of the steering wheel, and operate the torque feedback unit to apply a supplementary torque to the steering wheel for haptically issuing the communication through the steering wheel. The supplementary torque has a magnitude that is scaled based on the information about user securement of the steering wheel.

Abstract: A method for 3D object perception is described. The method includes extracting features from each image of a synthetic stereo pair of images. The method also includes generating a low-resolution disparity image based on the features extracted from each image of the synthetic stereo pair images. The method further includes predicting, by a trained neural network, a feature map based on the low-resolution disparity image and one of the synthetic stereo pair of images. The method also includes generating, by a perception prediction head, a perception prediction of a detected 3D object based on the feature map predicted by the trained neural network.

Abstract: An apparatus for determining an erroneous cause for a belief and presenting interventions. The apparatus includes one or more memories comprising processor-executable instructions; and one or more processors configured to execute the processor-executable instructions and cause the apparatus to receive a communication through at least one of a direct method or indirect method, extract a target belief, identify an attributable cause based on the communication, compile known causes of the target belief and determine if the known cause is false, compare the attributable cause to the known causes and generate a score based on an amount of similarities, determine that the attributable cause corresponds to a known cause that is false, when the score is greater than a predetermined threshold, and generate interventions for presentation on the user interface device based on the determination that the attributable cause corresponds to the known cause that is false.

Abstract: A method for controlling an ego vehicle in an environment includes detecting one or more changes in a position of an agent vehicle over time in accordance with capturing at least a first representation of the environment and a second representation of the environment via one or more sensors associated with the ego vehicle. The method also includes determining a velocity of the object based on detecting the one or more changes. The method further includes classifying the agent vehicle as parked based on the velocity and contextual data associated with the agent vehicle and/or the environment. The method still further includes planning a trajectory for the ego vehicle based on classifying the agent vehicle as parked. The method also includes controlling the ego vehicle to navigate along the trajectory.

Abstract: Systems and methods of model or prediction algorithm selection are provided. An autonomous control system may include a perception component that, based on environmental inputs regarding an object(s), a vehicle's operating characteristics, etc., outputs a current state of the vehicle's surrounding environment. This in turn, is used as input to a prediction component comprising a plurality of prediction algorithms. The prediction component outputs a set of predictions regarding the trajectory of the object(s). Accordingly, for each object, a set of trajectories at specific timesteps may be generated by the different prediction algorithms which are input to a planner component. These trajectories may then be analyzed, compared, or otherwise processed to determine which trajectory regarding the object is most accurate. The prediction algorithm or model that produced the most accurate predicted trajectory may then be used for subsequent predictions/timesteps.

Abstract: Systems and methods are provided for determining intoxication in a driver. The system can receive data of a driver's face over a time interval and for each frame of the data, determine one or more parameters associated with eye movements and characteristics of the driver. Based on the one or more parameters for each frame, the frames can be featurized into one or more vectors, where each of the one or more vectors corresponds to a parameter of the one or more parameters. A weight can be applied to each of the one or more vectors and based on the weight of each of the one or more vectors, the system can predict whether the driver surpassed an intoxication threshold. If the driver surpassed the intoxication threshold, the system can alter an operating characteristic of a vehicle of the driver.

Abstract: Systems, methods, and other embodiments described herein relate to integrating human decision-making into a model-based system. In one embodiment, a method includes acquiring sensor data, including driver data about a driver of a vehicle and driving data about the vehicle and a surrounding environment of the vehicle. The method includes encoding, using a world encoder, the sensor data into a latent representation. The method includes determining human decision- making characteristics according to the latent representation. The method includes generating a control signal for providing shared control of the vehicle according to the human decision-making characteristics and the latent representation.

Abstract: The present disclosure is directed to methods for training and using an artificial intelligence model for use with predicting a task output. The method includes generating a plurality of individual datasets, each of the plurality of individual datasets comprising data of at least one answer to at least one of a plurality of questions of each of a plurality of questionnaires, generating a first batch of individual datasets, the first batch of individual datasets comprising one or more of the plurality of individual datasets, inputting the first batch of individual datasets into the artificial intelligence model, and encoding the data of the first batch of individual datasets with an autoencoder.

Abstract: A method for a driver prediction system is described. The method includes training a neural network to a learn a set of polynomial basis functions. The method also includes selecting, using a trained neural network, a learned polynomial basis function to perform a prediction of an action of an autonomous dynamic object (ADO) agent. The method further includes computing projection coefficients of the learned polynomial basis function to weigh the learned polynomial basis function. The method also includes using the projection coefficients of the learned polynomial basis function to weigh the learned polynomial basis function to provide a distribution regarding a likelihood of the prediction of the action of the ADO agent.

Abstract: A teaching curriculum method for generating teaching actions for drivers, includes obtaining driving data from a plurality of driving scenarios, the driving data comprises vehicle trajectory information and corresponding scene context information, the driving scenarios comprising instructed driving events and uninstructed driving events, encoding, with a behavior model, the driving data, wherein the encoded driving data comprises an indication that a corresponding one of the driving scenarios comprises one of the instructed driving event or the uninstructed driving event, determining, with a trajectory estimator processing the encoded driving data, one or more driving skill transitions based on a presence or an absence of the indication, and generating, with a teacher action model, a teaching action for one of the plurality of driving scenarios.

Abstract: Systems, methods, and other embodiments described herein relate to predicting future trajectories of ado vehicles and an ego vehicle based on the awareness of the driver of the ego vehicle towards the ado vehicles. In one embodiment, a method includes determining an awareness of a driver of an ego vehicle to ado vehicles in the vicinity of the ego vehicle. The method also includes altering track data of ado vehicles based on a lack of awareness of the driver towards the ado vehicles. The method also includes transmitting altered track data of the ado vehicles to a prediction module. The prediction module predicts future trajectories of the ado vehicles and the ego vehicle based on the altered track data and an ego vehicle track data.

Abstract: Systems, methods, and other embodiments described herein relate to stylizing messages within a vehicle according to an occupant and a current context. In one embodiment, a method includes determining a style for presenting messages associated with an occupant of a vehicle according to a context defined in relation to an occupant and an environment of the vehicle. The method includes generating a message according to the style for the occupant. The method includes providing the message to the occupant.

Abstract: In one embodiment, a computer-implemented method for driver training using zone of proximal learning (ZPL) includes receiving, by one or more processors, driving data with respect to a driver operating a vehicle, estimating, using a personal behavior model, a driver profile based on the driving data, estimating one or more zone of proximal development (ZPD) states based at least in part on the driver profile, and performing one or more vehicle actions to place the driver into the one or more ZPD states.

Abstract: A system for training an operator of a vehicle to perform a maneuver of the vehicle can include a processor and a memory. The memory can store an automated motion module, an instruction module, and a communications module. The automated motion module can cause the processor to cause the vehicle to perform, in an automated manner, a first iteration of the maneuver. The instruction module can cause the processor to cause an instruction to be provided to the operator during a second iteration of the maneuver. The communications module can cause the processor to receive, during the second iteration, a query from the operator about a performance of the second iteration. The communications module can cause the processor to communicate a response to the query to train the operator to perform the second iteration or a third iteration of the maneuver in a manner that mimics the first iteration.