Abstract: A vehicle includes a first wheel, a second wheel, and a controller. The first and second of wheels have first and second tires, respectively. The controller is programmed to receive inputs indicative of tire tread wear of the first and second wheels. The controller is further programmed to, in response to a command to adjust torques of the first and second wheels to first and second desired torque values, respectively, and a difference between a tire tread wear of the first wheel and a tire tread wear of the second wheel exceeding a threshold, adjust the torque of the first electric machine to less than the first desired torque value and adjust the torque of the second electric machine to greater than the second desired torque value.

Abstract: A method for calibrating a vehicle sensor of a motor vehicle. The method includes the steps: ascertaining, by way of the vehicle sensor, sensor data at a plurality of measurement times, the motor vehicle moving in relation to objects in surroundings of the motor vehicle; computing object positions of the objects on the basis of the ascertained sensor data; computing a Hough transformation on the basis of the computed object positions; ascertaining an alignment of the vehicle sensor in relation to a driving axis of the motor vehicle on the basis of the computed Hough transformation; and calibrating the vehicle sensor on the basis of the ascertained alignment of the vehicle sensor in relation to the driving axis of the motor vehicle.

Abstract: Techniques are provided for foreground extraction from a point cloud (e.g., a LiDAR point cloud) using surface fitting. In an embodiment, one or more processors of a vehicle can receive point cloud data from one or more vehicle sensors. The one or more processors can identify points in the point cloud data as foreground points or ground points using a spatial Kalman filter to capture changes in the terrain. A route or trajectory in a driving area for the vehicle can be generated using the identified foreground points and ground points. A vehicle controller can control the vehicle while the vehicle is traveling on the route or trajectory in the driving area.

Abstract: Provided is a method for performing accurate object recognition in a stable manner in consideration of changes in a shooting environment. In such a method, a camera captures an image of a shooting location where an object is to be placed and an object included in an image of the shooting location is recognized utilizing a machine learning model for object recognition. The method further involves: determining necessity of an update operation on the machine learning model for object recognition at a predetermined time; when the update operation is necessary, causing the camera to capture an image of the shooting location where no object is placed to thereby re-acquire a background image for training; and causing the machine learning model to be trained using a composite image of a backgroundless object image and the re-acquired background image for training as training data.

Abstract: A vehicle that can effectively prevent a collision between the tail gate and an obstacle in the situation where the tail gate is automatically opened or closed includes: a tail gate; a driving unit engaged to the tail gate and configured to open or close the tail gate; a UWB module configured to communicate with a smart key according to an authentication signal transmitted from the smart key in a first mode, and transmit a detection signal to an object and detect the object according to the detection signal reflected from the object in a second mode; and a controller connected to the UWB module and configured to operate the UWB module in the second mode when the driving unit operates, and stop the operation of the driving unit when the object is detected from the UWB module operating in the second mode during operation of the driving unit.

Abstract: A tire state estimation system (10) is provided with a crack shape acquisition unit (240) for acquiring the shape of a crack on the outer surface of a tire, a crack information DB (230) for holding a correspondence relationship in which at least either degree of opening or deviation width of the crack based on the shape of the crack is associated with the depth of the crack, and a crack depth estimation unit (250) for estimating the depth of the crack based on the acquired crack shape and the correspondence relationship.

Abstract: Systems and methods for using image analysis techniques to assess unsafe driving conditions by a vehicle operator are discloses. According to aspects, a computing device may access and analyze image data depicting the vehicle operator. In analyzing the image, the computing device may measure certain visible metrics as depicted in the image data and compare the metrics to corresponding threshold values, and may accordingly determine whether the vehicle operator is exhibiting an unsafe driving condition. The computing device may generate and present alerts that indicate any determined unsafe driving condition.

Abstract: A LIDAR data based object recognition apparatus merges segments over-segmented in a LIDAR data based segmentation process. The apparatus includes a segment generator generating a plurality of segments by grouping points acquired from a LIDAR sensor. A target segment selector selects a target segment that is a base for merging from the plurality of segments and a segment merging determination unit checks whether segments other than the target segment are mergeable segments and determines whether to merge the target segment and the mergeable segments based on attribute information of the target segment and the mergeable segments. A segment merger merges the target segment and the mergeable segments and outputs a merged segment.

Abstract: Configuration, in which images output to a display unit are switched and displayed in accordance with the behavior of a driver, such as movements of the head of the driver, is achieved. Driver information indicating the behavior of the driver of a moving apparatus and images captured by a plurality of cameras that images a situation around the moving apparatus from different viewpoints are input. The images output to the display unit are switched in accordance with the driver information. The plurality of cameras is, for example, a plurality of rear cameras installed in the rear of the moving apparatus. For example, a direction of the face or line-of-sight of the driver is detected. An image in a direction corresponding to the detected direction of the face or line-of-sight of the driver is selected as an output image, and displayed on the display unit. Alternatively, an image in a direction indicated by a gesture of the driver is selected, and displayed on the display unit.

Abstract: A system and method of identifying and tracking objects comprises registering an identity of a person who visits an area designated for holding objects, capturing an image of the area designated for holding objects, submitting a version of the image to a deep neural network trained to detect and recognize objects in images like those objects held in the designated area, detecting an object in the version of the image, associating the registered identity of the person with the detected object, retraining the deep neural network using the version of the image if the deep neural network is unable to recognize the detected object, and tracking a location of the detected object while the detected object is in the area designated for holding objects.

Abstract: A geometric approach may be used to detect objects on a road surface. A set of points within a region of interest between a first frame and a second frame are captured and tracked to determine a difference in location between the set of points in two frames. The first frame may be aligned with the second frame and the first pixel values of the first frame may be compared with the second pixel values of the second frame to generate a disparity image including third pixels. One or more subsets of the third pixels that have a value above a first threshold may be combined, and the third pixels may be scored and associated with disparity values for each pixel of the one or more subsets of the third pixels. A bounding shape may be generated based on the scoring.

Abstract: An information processing device includes processing circuitry configured to acquire feature measurement information indicating locations of features including a road having a boundary and trajectory information indicating a trajectory along the road. Additionally, the processing circuitry is further configured to generate candidate location information indicating locations of candidate elements for the boundary, based on the acquired feature measurement information. Further, the processing circuitry is configured to select candidate elements from among the candidate elements indicated by the generated candidate location information, based on the acquired trajectory information. Finally, the processing circuitry is configured to generate boundary location information indicating determined locations of the boundary, using the selected candidate elements.

Abstract: Context-based data valuation and transmission, including: acquiring sensor data from a plurality of sensors of the autonomous vehicle, wherein the sensor data comprises a plurality of portions and the plurality of sensors comprises at least two cameras; determining, for each portion of the sensor data, a value based on one or more conditions under which the sensor data was captured; determining, based on the values for the sensor data, an upload policy; and transmitting, based on the upload policy, one or more portions of the sensor data to a server.

Abstract: Generally, a system including an imaging device and a processing unit is disclosed. The imaging device may be configured to acquire a plurality of datasets of corresponding plurality of image frames by performing corresponding plurality of image frame handling cycles. The processing unit may be configured to define a special region of interest (SROI) in each of at least some of the plurality of the image frames acquired by the imaging device, based on the datasets of the respective image frames. The imaging device may be further configured to acquire at least one partial dataset of the SROI, during each of at least some of the plurality of image frame handling cycles and within a residual time between an end of an image frame acquiring time and an end of the respective image frame handling cycle.

Abstract: A system for determining blockage of a vehicle camera is configured to apply a partition grid having a plurality of locations to a sequence of images to form a plurality of regions. The system determines at least one spatial feature corresponding to the partition grid and at least one temporal feature corresponding to the partition grid. The system generates a sequence of classifications for each location of the plurality of locations based on the at least one spatial feature, the at least one temporal feature, and reference information. The system applies a smoothing technique to determine a subset of regions that are blocked among the sequence of classifications, and generates an output signal based on the subset of regions. The output may be provided to an output system to wash the camera lens, notify the user or the vehicle of the blockage, or modify image processing.

Abstract: A navigation system may include a processor programmed to analyze a first image to identify a non-semantic road feature; identify a first image location, in the first image, of one point associated with the non-semantic road feature; analyze a second image to identify a representation of the non-semantic road feature in the second image; identify a second image location, in the second image, of the one point associated with the non-semantic road feature; determine, based on a difference between the first and second image locations and based on motion information for a vehicle between a capture of the first image and a capture of the second image, three-dimensional coordinates for the one point associated with the non-semantic road feature; and send the three-dimensional coordinates for the one point associated with the non-semantic road feature to a server for use in updating a road navigation model.

Abstract: A method for determining a maximum value for a parameter range of a driving operation parameter of a motor vehicle. The motor vehicle includes a control device, at least one electric traction motor, an electric energy storage device which can be operated in an operating temperature range for operating the traction motor, and at least one temperature sensor for determining a temperature of the energy storage device. The control device determines the maximum value as a function of a current temperature of the energy storage device determined by the temperature sensor in such a manner that, after the approach of a destination known to the control device and/or after a journey over a predetermined distance with the driving operation parameter restricted by the maximum value of the parameter range, a predicted temperature of the energy storage device lies within a charging temperature range.

Abstract: Systems and methods described herein relate to jointly training a machine-learning-based monocular optical flow, depth, and scene flow estimator. One embodiment processes a pair of temporally adjacent monocular image frames using a first neural network structure to produce a first optical flow estimate; processes the pair of temporally adjacent monocular image frames using a second neural network structure to produce an estimated depth map and an estimated scene flow; processes the estimated depth map and the estimated scene flow using the second neural network structure to produce a second optical flow estimate; and imposes a consistency loss between the first optical flow estimate and the second optical flow estimate that minimizes a difference between the first optical flow estimate and the second optical flow estimate to improve performance of the first neural network structure in estimating optical flow and the second neural network structure in estimating depth and scene flow.

Abstract: The present technique relates to an information processing apparatus, an information processing method, a program, and a mobile body which enable accuracy of detection processing related to a passage around a mobile body to be improved. The information processing apparatus includes: a transforming unit configured to respectively transform a plurality of photographed images with partially overlapping photographing ranges into bird's eye images; a compositing unit configured to generate a composite image by compositing a plurality of the bird's eye images; and a detecting unit configured to perform detection processing related to a passage around a mobile body based on the composite image. For example, the present technique can be applied to an apparatus that detects a lane marking of a road.

Abstract: A distance measurement device includes an imaging unit which captures a subject image formed by an imaging optical system, an emission unit which emits directional light as light having directivity along an optical axis direction of the imaging optical system, a light receiving unit which receives reflected light of the directional light from the subject, a derivation unit which derives a distance to the subject based on the timing at which the directional light is emitted and the timing at which the reflected light is received, a display unit which displays the subject image, and a control unit which performs control such that, in a case of performing a distance measurement, the display unit displays the subject image as a motion image and transition is made to a state where actual exposure by the imaging unit is possible at the timing of the end of the distance measurement.

Abstract: A navigation system may include a processor programmed to receive, from a camera of the host vehicle, one or more images captured from an environment of the host vehicle, and analyze the one or more images to detect an indicator of an intersection. The processor may also be programmed to determine, based on output received from at least one sensor of the host vehicle, a stopping location of the host vehicle relative to the detected intersection, and analyze the one or more images to determine an indicator of whether one or more other vehicles are in front of the host vehicle. The processor may further be programmed to send the stopping location of the host vehicle and the indicator of whether one or more other vehicles are in front of the host vehicle to a server for use in updating a road navigation model.

Abstract: Methods and apparatus for route selection to a destination may include receiving a starting point and one or more destinations, and transmitting a request to a server for routes associated with the starting point and the one or more destinations. Additionally, the methods and apparatus may include receiving, from the server, a plurality of routes to the one or more destinations. Furthermore, the methods and apparatus may include selecting a route from the plurality of routes based at least on one or more reliability parameters associated with each route of the plurality of routes, the one or more reliability parameters comprising a likelihood of determining a position location along each route, the likelihood being based at least on detectability of features in each route by one or more object detection modalities.

Abstract: Systems, methods, and other embodiments described herein relate to improving identification of a path for an ego vehicle on a roadway. In one embodiment, a method includes, in response to acquiring sensor data from at least one sensor of the ego vehicle about a surrounding environment, identifying roadway elements from the sensor data as cues about the path. The roadway elements include one or more of lane markers of the roadway and surrounding vehicles. The method includes grouping the roadway elements into two or more groups according to characteristics of roadway elements indicating common curvatures. The method includes analyzing the two or more groups according to a confidence heuristic to determine a priority group from the two or more groups that corresponds with a trajectory of the ego vehicle. The method includes providing an identifier for the priority group to facilitate at least path planning for the ego vehicle.

Abstract: Systems and methods for more accurate and robust determination of subject characteristics from an image of the subject. One or more machine learning models receive as input an image of a subject, and output both facial landmarks and associated confidence values. Confidence values represent the degrees to which portions of the subject's face corresponding to those landmarks are occluded, i.e., the amount of uncertainty in the position of each landmark location. These landmark points and their associated confidence values, and/or associated information, may then be input to another set of one or more machine learning models which may output any facial analysis quantity or quantities, such as the subject's gaze direction, head pose, drowsiness state, cognitive load, or distraction state.

Abstract: A method of predicting occupancy of unseen areas in a region of interest (ROI) includes obtaining a depth image of the ROI, the depth image being captured from a first height; generating an occupancy map based on the obtained depth image, the occupancy map comprising an array of cells corresponding to locations in the ROI; and generating an inpainted map by inputting the occupancy map into a trained inpainting network, the inpainted map comprising an array of cells corresponding to the ROI, and wherein the inpainting network is trained by comparing an output of the inpainting network, based on inputting a training depth image taken from the first height, to a ground truth map, the ground truth map being based on a combination of the training depth image and a depth image taken at a height different than the first height.

Abstract: Systems, methods, tangible non-transitory computer-readable media, and devices for associating objects are provided. For example, the disclosed technology can receive sensor data associated with the detection of objects over time. An association dataset can be generated and can include information associated with object detections of the objects at a most recent time interval and object tracks of the objects at time intervals in the past. A subset of the association dataset including the object detections that satisfy some association subset criteria can be determined. Association scores for the object detections in the subset of the association dataset can be determined. Further, the object detections can be associated with the object tracks based on the association scores for each of the object detections in the subset of the association dataset that satisfy some association criteria.

Abstract: Methods, systems, and non-transitory computer-readable media are configured to perform operations comprising determining a symmetric scenario for a scenario; training a first machine learning model for the scenario based on first training data generated from second training data for the symmetric scenario; and generating a prediction for the scenario based on the first machine learning model.

Abstract: A vehicle headlight device capable of improving overlooking of pedestrians by a driver. The device includes: a left-side photoirradiator (left-side pattern irradiation lamp) which irradiates light on a left-side light distribution region (irradiation pattern light distribution region) on a left side of a travel roadway of a vehicle in an irradiation pattern in which a bright region a1 and a dark region are alternately repeated; and a right-side photoirradiator (right-side pattern irradiation lamp) which irradiates light on a right-side light distribution region (irradiation pattern light distribution region) on a right side of a travel roadway of the vehicle in an irradiation pattern in which a bright region a1 and a dark region are alternately repeated. In this embodiment, the left-side photoirradiator (left-side pattern irradiation lamp) is illuminated during left turn of the vehicle, and the right-side photoirradiator (right-side pattern irradiation lamp) is illuminated during right turn of the vehicle.

Abstract: Provided is an object detection device or the like which efficiently generates good-quality training data. This object detection device is provided with: a detection unit which uses a dictionary to detect objects from an input image; a reception unit which displays, on a display device, the input image accompanied by a display emphasizing partial areas of detected objects, and receives, from one operation of an input device, a selection of a partial area and an input of the class of the selected partial area; a generation unit which generates training data from the image of the selected partial area and the inputted class; and a learning unit which uses the training data to learn the dictionary.

Abstract: An object tracking system according to the present disclosure includes: object position detection means for detecting a position of an object by using a sensor; object tracking parameter storage means for storing a parameter related to an erroneous detection or a non-detection caused by a detection characteristic of the sensor; object tracking means for performing tracking based on the position obtained by the object position detection means and the parameter stored in the object tracking parameter storage means; object tracking result evaluation means for calculating an evaluation index based on a result obtained by the object tracking means; and object tracking parameter updating means for determining the parameter based on the evaluation index calculated by the object tracking result evaluation means and updating the parameter stored in the object tracking parameter storage means.

Abstract: A system for generating approximately coordinated region maps (RM), the system comprising a processing resource configured to: provide a data repository comprising one or more RMs, each mapping a corresponding region, and each including information of a relative location of synchronization objects (SOs) located within the corresponding region with respect to a coordinate-system (CS) origin of a CS of the corresponding RM; obtain a given RM including information of relative locations of given SOs located within the given region with respect to a given CS origin of a given CS of the given RM; retrieve, from the data repository, reference RMs that meet a criteria; identify the reference RMs associated with at least one SO that match at least one of the given SO, giving rise to optimization RMs; and determine, utilizing an optimization scheme, an approximate transformation between the given CS and the CSs of the optimization RMs.

Abstract: A collision avoidance assist apparatus executes an emergency steering control including processes to determine a target steering torque used to change a steering angle to avoid a collision of a vehicle with an obstacle so as not to move the vehicle out of a moving lane when the vehicle has a high probability of colliding with the obstacle, and the moving lane is a straight lane, and applies a steering torque corresponding to the determined target steering torque to a steering mechanism. The collision avoidance assist apparatus stops executing the emergency steering control when determining that the moving lane is a curved lane, based on only one of left and right lane markings at an avoidance side of the obstacle which is the left or the right side of the obstacle which the vehicle passes over while executing the emergency steering control.

Abstract: An information processing apparatus that detects an object from an image, includes a determination unit configured to determine a boundary at which a movement of the object between partial regions in the image is estimated, the partial regions each including a plurality of objects, and an estimation unit configured to estimate movement information indicating a number of objects that have passed the boundary determined by the determination unit.

Abstract: A vehicle lamp control device includes: an imaging unit that takes an image ahead of a host vehicle; a target analysis unit that detects target objects ahead of the host vehicle based on the information obtained from an imaging unit configured to take an image ahead of the host vehicle; and a tracking unit that determines a specific target object from the target objects detected by the target analysis unit and to detect displacement of the specific target object based on a detection result of an luminance analysis unit configured to detect luminance of each of a plurality of individual areas ahead of the host vehicle based on information obtained from the imaging unit. A light distribution pattern to be formed by a light source unit of a vehicle lamp is determined based on the detection result of the luminance analysis unit and a detection result of the tracking unit.

Abstract: A vehicle includes one or more cameras that capture a plurality of two-dimensional images of a three-dimensional object. A light detector and/or a semantic classifier search within those images for lights of the three-dimensional object. A vehicle signal detection module fuses information from the light detector and/or the semantic classifier to produce a semantic meaning for the lights. The vehicle can be controlled based on the semantic meaning. Further, the vehicle can include a depth sensor and an object projector. The object projector can determine regions of interest within the two-dimensional images, based on the depth sensor. The light detector and/or the semantic classifier can use these regions of interest to efficiently perform the search for the lights.

Abstract: A system for an autonomous vehicle that receives driving environment information corresponding to a driving environment provided by another autonomous vehicle, and determines a navigation route based on a degree of reliability of the driving environment information provided by the another autonomous vehicle.

Abstract: An apparatus, method and computer program product provide a map layer of one or more temporary dynamic obstructions. For example, the apparatus is configured to receive vehicle/driver behavior data associated with a vehicle at a portion of a road, determine a likelihood of a temporary dynamic obstruction existing proximate to the portion based on the vehicle behavior data, and update a datapoint of a map layer based on the likelihood. The datapoint indicates a state of existence of the temporary dynamic obstruction at the portion.

Abstract: A system and a method for processing a plurality of images, each image of the plurality of images being acquired by a respective image acquisition module of a vehicle and each image acquisition module being oriented outwardly with respect to the vehicle, the method comprising: elaborating a bird's eye view image of surroundings of the vehicle using pixel values of pixels of at least one portion of each image of the plurality of images as pixel values of the bird's eye view image, and performing, on the bird's eye view image, a detection of at least one lane marked on a surface on which the vehicle is and visible on the bird's eye view image.

Abstract: A method of providing an interactive personal mobility system, performed by one or more processors, comprises determining an initial pose by visual-inertial odometry performed on images and inertial measurement unit (IMU) data generated by a wearable augmented reality device. Sensor data transmitted from a personal mobility system is received, and sensor fusion is performed on the data received from the personal mobility system to provide an updated pose. Augmented reality effects are displayed on the wearable augmented reality device based on the updated pose.

Abstract: A computer, including a processor and a memory, the memory including instructions to be executed by the processor to train a quantile neural network to input an image and output a lower quantile (LQ) prediction, a median quantile (MQ) prediction and an upper quantile (UQ) prediction corresponding to an object in the image, wherein an LQ loss, an MQ loss and a UQ loss are determined for the LQ prediction, the MQ prediction and the UQ prediction respectively and wherein the LQ loss, the MQ loss and the UQ loss are combined to form a base layer loss and output the quantile neural network.

Abstract: A method of recognizing a specific image includes detecting image features from the specific image and storing in a memory each of detected relevant image features, detecting relevant image features from an input image and selecting from the memory a portion corresponding to each of the detected relevant image features, generating a restoration image using portions selected in the selecting, and determining whether the generated restoration image matches with the input image by a matching process and recognizing that, when it is determined that the restoration image matches with the input image, the input image is the specific image.

Abstract: Methods and systems for crowd level estimation are provided. The system for crowd level estimation includes an input module and a crowd level estimation module. The input module receives an input image of a crowd and the crowd level estimation module estimates a crowd level of the crowd in the input image in response to a crowd density level.

Abstract: A control device for a mobile object including one or more imaging devices, the control device includes an image acquisition unit configured to acquire an image of an external environment of the mobile object from the one or more imaging devices, a correction unit configured to perform distortion reduction processing for reducing distortion of an image for each of one or more regions included in an image acquired from the one or more imaging devices, and a recognition unit configured to recognize the external environment of the mobile object based on an image on which the distortion reduction processing has been performed. The correction unit is configured to determine the one or more regions to be a target of the distortion reduction processing in accordance with a predetermined rule according to a moving scene of the mobile object.

Abstract: An apparatus and a method for increasing the movement speed of the rail vehicle while carrying out measures for controlling weeds on track systems A rail vehicle equipped with an apparatus for increasing the movement speed of the rail vehicle while carrying out measures for controlling weeds on track systems.

Abstract: A road congestion detection method realized by a computer includes obtaining K images taken by L cameras corresponding to a first road at a same target time point, the first road including M road sections, each road section corresponding to at least one camera, M, L, K each being a positive integer, L being greater than or equal to M, performing target detection on each image to obtain area ratio information, the area ratio information representing a ratio of an area of vehicles on a lane of a target road section to an area of the lane of the target road section, the target road section being a road section corresponding to the image in the M road sections, and determining a first congestion detection result of the first road at the target time point in accordance with K pieces of area ratio information corresponding to the M road sections.

Abstract: Among other things, techniques are described for cross-modality active learning for object detection. In an example, a first set of predicted bounding boxes and a second set of predicted bounding boxes is generated. The first set of predicted bounding boxes and the second set of predicted bounding boxes are projected into a same representation. The projections are filtered, wherein predicted bounding boxes satisfying a maximum confidence score are selected for inconsistency calculations. Inconsistencies are calculated across the projected bounding boxes based on filtering the projections. An informative scene is extracted based on the calculated inconsistencies. A first object detection neural network or a second object detection neural network is trained using the informative scenes.

Abstract: A detection device includes: a first detector which irradiates light onto the target object and detects light emitted from the target object; a first shape information generator which generates first shape information representing a first shape of the target object on the basis of a detection result of the first detector; and a second shape information generator which adds a second shape, which is based on information different from the detection result of the first detector, to the first shape, and which generates second shape information representing a shape including the first shape and the second shape.

Abstract: A method may include: receiving a first image captured by a camera at a first time instance, wherein the first image includes at least a portion of an observed vehicle; determining a first ray angle based on a coordinate system of an ego-vehicle and a coordinate system of the observed vehicle corresponding to the first image; receiving a second image captured by the camera at a second time instance, wherein the second image includes at least a portion of the observed vehicle oriented at a different viewpoint; determining a second ray angle based on a coordinate system of the ego-vehicle and the coordinate system of the observed vehicle corresponding to the second image; determining a local angle difference based on the first ray angle and the second ray angle; and training a deep neural network using the local angle difference, the first image, and the second image.

Abstract: An apparatus for packaging containers of devices for pharmaceutical use includes a robotic arm movable from a gripping position, in which it picks up a container previously sealed by at least one protective sheet, to a release position in which it inserts the container into a bag through a suitable opening provided on a side of the bag; wherein the robotic arm is connected to at least one position control camera configured to read coordinates of a midpoint of the opening with respect to a lying plane on which the bag lies and/or an angle of rotation of the bag with respect to an axis perpendicular to the lying plane, so as to ensure the correct positioning and release of the container inside the bag.

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.