Abstract: System, methods, and other embodiments described herein relate to adjusting a prediction model for control at handling limits associated with a projected trajectory during automated driving. In one embodiment, a method includes adjusting parameters of a prediction model using friction estimates and sideslip costs associated with a projected trajectory of a vehicle, the friction estimates being derived from Kalman filtering. The method also includes scaling, using the prediction model, handling limits of the vehicle for the projected trajectory according to a friction circle. The method also includes generating, by the prediction model, vehicle dynamics using a load transfer and a brake distribution, the vehicle dynamics being associated with estimated road conditions and the handling limits. The method also includes outputting, by the prediction model using the vehicle dynamics, a driving command to the vehicle for the projected trajectory.

Abstract: System, methods, and other embodiments described herein relate to the detection of lanes in a driving scene through segmenting road regions using an ontology enhanced to derive semantic context. In one embodiment, a method includes segmenting an image of a driving scene, independent of maps, by lane lines and road regions defined by an ontology and a pixel subset from the image has semantics of lane information from the ontology. The method also includes computing pixel depth from the image for the lane lines and the road regions using a model. The method also includes deriving 3D context using relations between the semantics and the pixel depth, the relations infer a driving lane for a vehicle from types of the lanes lines and the road regions adjacent to the driving lane. The method also includes executing a task to control the vehicle on the driving lane using the 3D context.

Abstract: Systems and methods are provided for dynamic driver training, and may include: a communication interface to receive sensor data, the sensor data comprising driver biometric data and driver performance data for a driver operating a vehicle; a driver inference circuit to infer a skill level and emotional state of the driver operating the vehicle; and a driver training circuit to, based on the inferred skill level and emotional state of the driver operating the vehicle, dynamically adjust a driver training level for the driver while the driver is operating the vehicle.

Abstract: Systems and methods described herein relate to reconstructing a scene in three dimensions from a two-dimensional image. One embodiment processes an image using a detection transformer to detect an object in the scene and to generate a NOCS map of the object and a background depth map; uses MLPs to relate the object to a differentiable database of object priors (PriorDB); recovers, from the NOCS map, a partial 3D object shape; estimates an initial object pose; fits a PriorDB object prior to align in geometry and appearance with the partial 3D shape to produce a complete shape and refines the initial pose estimate; generates an editable and re-renderable 3D scene reconstruction based, at least in part, on the complete shape, the refined pose estimate, and the depth map; and controls the operation of a robot based, at least in part, on the editable and re-renderable 3D scene reconstruction.

Abstract: A method for an electric vehicle trip simulator is described. The method includes determining parameters for an upcoming trip of an electric vehicle, including at least a start location and a destination location. The method also includes analyzing data associated with a plurality of points of interest between the start location and the destination location. The method further includes selecting a set of locations from the plurality of points of interest for the upcoming trip of the electric vehicle, according to the analyzing of the data. The method also includes displaying a travel order recommendation associated with the set of locations selected for the upcoming trip of the electric vehicle, including at least one charging station location according to a current charge capacity of the electric vehicle.

Abstract: A method of generating additional supervision data to improve learning of a geometrically-consistent latent scene representation with a geometric scene representation architecture is provided. The method includes receiving, with a computing device, a latent scene representation encoding a pointcloud from images of a scene captured by a plurality of cameras each with known intrinsics and poses, generating a virtual camera having a viewpoint different from viewpoints of the plurality of cameras, projecting information from the pointcloud onto the viewpoint of the virtual camera, and decoding the latent scene representation based on the virtual camera thereby generating an RGB image and depth map corresponding to the viewpoint of the virtual camera for implementation as additional supervision data.

Abstract: The disclosure provides implicit representations for multi-object 3D shape, 6D pose and size, and appearance optimization, including obtaining shape, 6D pose and size, and appearance codes. Training is employed using shape and appearance priors from an implicit joint differential database. 2D masks are also obtained and are used in an optimization process that utilizes a combined loss minimizing function and an Octree-based coarse-to-fine differentiable optimization to jointly optimize the latest shape, appearance, pose and size, and 2D masks. An object surface is recovered from the latest shape codes to a desired resolution level. The database represents shapes as Signed Distance Fields (SDF), and appearance as Texture Fields (TF).

Abstract: A system for trajectory prediction using a predicted endpoint conditioned network includes one or more processors and a memory that includes a sensor input module, an endpoint distribution module, and a future trajectory module. The modules cause the one or more processors to the one or more processors to obtain sensor data of a scene having a plurality of pedestrians, determine endpoint distributions of the plurality of pedestrians within the scene, the endpoint distributions representing desired end destinations of the plurality of pedestrians from the scene, and determine future trajectory points for at least one of the plurality of pedestrians based on prior trajectory points of the plurality of pedestrians and the endpoint distributions of the plurality of pedestrians. The future trajectory points may be conditioned not only on the pedestrian and their immediate neighbors' histories (observed trajectories) but also on all the other pedestrian's estimated endpoints.

Abstract: Embodiments of a deformable gripper are described. The deformable gripper comprises a base, a first inner membrane and a second inner membrane coupled to the base, an outer membrane attached to the base such that the outer membrane is positioned to enclose the first inner membrane and the second inner membrane, and an actuator operable to independently expand and contract the first inner membrane and the second inner membrane such that a portion of an outer surface of the outer membrane expands and contracts responsive to the expansion and contraction of at least one of the first inner membrane and the second inner membrane.

Abstract: A method for self-supervised depth and ego-motion estimation is described. The method includes determining a multi-camera photometric loss associated with a multi-camera rig of an ego vehicle. The method also includes generating a self-occlusion mask by manually segmenting self-occluded areas of images captured by the multi-camera rig of the ego vehicle. The method further includes multiplying the multi-camera photometric loss with the self-occlusion mask to form a self-occlusion masked photometric loss. The method also includes training a depth estimation model and an ego-motion estimation model according to the self-occlusion masked photometric loss. The method further includes predicting a 360° point cloud of a scene surrounding the ego vehicle according to the depth estimation model and the ego-motion estimation model.

Abstract: A method for fitting an odometry noise model of a vehicle is described. The method includes collecting multiple passes of sensor measurements from motion sensors of the vehicle to measure a motion sensor noise during a testing operation of the vehicle. The method also includes determining an estimated standard deviation of the motion sensor noise measured during the testing operation of the vehicle. The method further includes determining the odometry noise model of the vehicle according to the estimated standard deviation of the motion sensor noise measured during the testing operation of the vehicle. The method also includes compensating, using the odometry noise model, the motion sensor noise during normal operation of the vehicle.

Abstract: A method for multiple object tracking includes receiving, with a computing device, a point cloud dataset, detecting one or more objects in the point cloud dataset, each of the detected one or more objects defined by points of the point cloud dataset and a bounding box, querying one or more historical tracklets for historical tracklet states corresponding to each of the one or more detected objects, implementing a 4D encoding backbone comprising two branches: a first branch configured to compute per-point features for each of the one or more objects and the corresponding historical tracklet states, and a second branch configured to obtain 4D point features, concatenating the per-point features and the 4D point features, and predicting, with a decoder receiving the concatenated per-point features, current tracklet states for each of the one or more objects.

Abstract: Systems and methods for learning and managing robot user interfaces are disclosed herein. One embodiment generates, based on input data including information about past interactions of a particular user with a robot and with existing HMIs of the robot, a latent space using one or more encoder neural networks, wherein the latent space is a reduced-dimensionality representation of learned behavior and characteristics of the particular user, and uses the latent space as input to train a decoder neural network associated with (1) a new HMI distinct from the existing HMIs or (2) a particular HMI among the existing HMIs to alter operation of the particular HMI. The trained first decoder neural network is deployed in the robot to control, at least in part, operation of the new HMI or the particular HMI in accordance with the learned behavior and characteristics of the particular user.

Abstract: A method of representation learning for object detection from unlabeled point cloud sequences is described. The method includes detecting moving object traces from temporally-ordered, unlabeled point cloud sequences. The method also includes extracting a set of moving objects based on the moving object traces detected from the sequence of temporally-ordered, unlabeled point cloud sequences. The method further includes classifying the set of moving objects extracted from on the moving object traces detected from the sequence of temporally-ordered, unlabeled point cloud sequences. The method also includes estimating 3D bounding boxes for the set of moving objects based on the classifying of the set of moving objects.

Abstract: A method of closed loop simulation for accelerated material discovery is described. The method includes ranking a plurality of candidate systems according to corresponding properties of interest predicted by a first prediction model. The method also includes simulating a first top-N of the plurality of candidate systems according to the corresponding properties of interest predicted by the first prediction model. The method further includes re-ranking the plurality of candidate systems according to the corresponding properties of interest predicted by a second prediction model. The method also includes simulating a second top-N of the plurality of candidate systems according to the corresponding properties of interest predicted by the second prediction model.

Abstract: Systems and methods for determining whether a user employs System 1 type thinking or System 2 type thinking when engaged in a task are disclosed. The systems and methods include determining one or more properties of the task based on information regarding the task received from a database storing information regarding the task, determining one or more properties of the user with respect to the task, determining a state of the user based on one or more physiological sensors configured to sense one or more characteristics of the user, and determining that the user employs System 1 type thinking or System 2 type thinking when engaged in the task based on the determined one or more properties of the task, the determined one or more properties of the user, and the determined state of the user.

Abstract: Systems, methods, and other embodiments described herein relate to training a multi-task network using real and virtual data. In one embodiment, a method includes acquiring training data that includes real data and virtual data for training a multi-task network that performs at least depth prediction and semantic segmentation. The method includes generating a first output from the multi-task network using the real data and second output from the multi-task network using the virtual data. The method includes generating a mixed loss by analyzing the first output to produce a real loss and the second output to produce a virtual loss. The method includes updating the multi-task network using the mixed loss.

Abstract: Methods, systems, and non-transitory machine-readable mediums for ranking on an absolute scale include displaying, on an electronic display, a first handle, a second handle, and an interactor, determining a value of the first handle and a value of the second handle based on their respective positions on the interactor, in response to a user dragging the first and second handles on the interactor, and determining a rank of the first and second handles based on the values of the first and second handles, in response to the user dragging the first and second handles on the interactor.

Abstract: System, methods, and other embodiments described herein relate to communicating alerts about a recommended speed by adapting headlight color. In one embodiment, a method includes computing a recommended speed using an automated driving system (ADS) during an operator controlling a vehicle while the ADS is disengaged. The method also includes, responsive to determining that a vehicle speed satisfies a threshold associated with the recommended speed and an offset value set according to a driving environment, adapting an alert color projected by headlights of the vehicle according to the vehicle speed and the alert color is corrected for operator perception of visible colors associated with the driving environment.

Abstract: A method of conditional neural ground planes for static-dynamic disentanglement is described. The method includes extracting, using a convolutional neural network (CNN), CNN image features from an image to form a feature tensor. The method also includes resampling unprojected 2D features of the feature tensor to form feature pillars. The method further includes aggregating the feature pillars to form an entangled neural ground plane. The method also includes decomposing the entangled neural ground plane into a static neural ground plane and a dynamic neural ground plane.