A robot assembly for safe operation in a manufacturing setting with humans including a sensor for detecting a human location and human movement is provided. A safety control module providing a boundary of a safety zone area that is associated with the human in a task oriented state that includes a largest possible area in which the human or an associated work object can extend when the human is standing in one location and performing the work task. The human movement and safety zone area location being used to develop a capture set area that includes at least one predictive future safety zone area location. Using the at least one predicted future safety zone area, establishing a travel path for moving the robot between locations without overlapping the capture set area.

A pedestrian tracking system includes: a buffer or a memory configured to store a trajectory sequence of a pedestrian; a step attention module and a control module. The step attention module iteratively performs a step attention process to predict states of the pedestrian. Each iteration of the step attention process includes the step attention module: learning the stored trajectory sequence to provide time-dependent hidden states, reshaping each of the time-dependent hidden states to provide two-dimensional tensors; condensing the two-dimensional tensors via convolutional networks to provide convolutional sequences; capturing global information of the convolutional sequences to output a set of trajectory patterns represented by a new sequence of tensors; learning time-related patterns in the new sequence and decoding the new sequence to provide one or more of the states of the pedestrian; and modifying the stored trajectory sequence to include the predicted one or more of the states of the pedestrian.

A pedestrian tracking system includes: a buffer or a memory configured to store a trajectory sequence of a pedestrian; a step attention module and a control module. The step attention module iteratively performs a step attention process to predict states of the pedestrian. Each iteration of the step attention process includes the step attention module: learning the stored trajectory sequence to provide time-dependent hidden states, reshaping each of the time-dependent hidden states to provide two-dimensional tensors; condensing the two-dimensional tensors via convolutional networks to provide convolutional sequences; capturing global information of the convolutional sequences to output a set of trajectory patterns represented by a new sequence of tensors; learning time-related patterns in the new sequence and decoding the new sequence to provide one or more of the states of the pedestrian; and modifying the stored trajectory sequence to include the predicted one or more of the states of the pedestrian.

Techniques and methods for training and/or using a machine learned model that identifies unsafe events. For instance, computing device(s) may receive input data, such as vehicle data generated by one or more vehicles and/or simulation data representing a simulated environment. The computing device(s) may then analyze features represented by the input data using one or more criteria in order to identify potential unsafe events represented by the input data. Additionally, the computing device(s) may receive ground truth data classifying the identified events as unsafe events or safe events. The computing device(s) may then train the machine learned model using at least the input data representing the unsafe events and the classifications. Next, when the computing device(s) and/or vehicles receive input data, the computing device(s) and/or vehicles may use the machine learned model to determine if the input data represents unsafe events.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for predicting how likely it is that a target agent in an environment will yield to another agent when the pair of agents are predicted to have overlapping future paths. In one aspect, a method comprises obtaining a first trajectory prediction specifying a predicted future path for a target agent in an environment; obtaining a second trajectory prediction specifying a predicted future path for another agent in the environment; determining that, at an overlapping region, the predicted future path for the target agent overlaps with the predicted future path for the other agent; and in response: providing as input to a machine learning model respective features for the target agent and the other agent; and obtaining the likelihood score as output from the machine learning model.

A device may receive accelerometer data and video data for a vehicle and may identify bounding boxes and object classes for objects near the vehicle. The device may identify tracks for the objects and may filter out tracks that are not associated with vehicles or vulnerable road users to generate one or more tracks or an indication of no tracks. The device may generate a collision cone identifying a drivable area of the vehicle to identify objects more likely to be involved in a collision and may filter out tracks from the one or more tracks, based on the bounding boxes, and to generate a subset of tracks or another indication of no tracks. The device may determine scores for the subset of tracks and may identify a track of the subset of tracks with a highest score. The device may perform actions based on the identified track.

An autonomous vehicle safety system may activate to prevent collisions by detecting that a planned trajectory may result in a collision. If the safety system is overly sensitive, it may cause false positive activations, and if the system isn't sensitive enough the collision avoidance system may not activate and prevent a collision, which is unacceptable. It may be impossible or prohibitively difficult to detect false positive activations of a safety system and it is unacceptable to risk a false negative, so tuning the safety system is notoriously difficult. Tuning the safety system may include detecting near-miss events using surrogate metrics, and tuning the safety system to increase or decrease a rate of near-miss events as a stand-in for false positives.

A vehicle driver assist system includes an expert evaluation system to fuse information acquired from various data sources. The data sources can correspond to conditions associated with the vehicle as a unit as well as external elements. The expert evaluation system monitors and evaluates the information from the data sources according to a set of rules by converting each data value into a metric value, determining a weight for each metric, assigning the determined weight to the metric, and generating a weighted metric corresponding to each data value. The expert evaluation system compares each weighted metric (or a linear combination of metrics) against one or more thresholds. The results from the comparison provide an estimation of a likelihood of one or more traffic features occurring.

A vehicle driver assist system includes an expert evaluation system to fuse information acquired from various data sources. The data sources can correspond to conditions associated with the vehicle as a unit as well as external elements. The expert evaluation system monitors and evaluates the information from the data sources according to a set of rules by converting each data value into a metric value, determining a weight for each metric, assigning the determined weight to the metric, and generating a weighted metric corresponding to each data value. The expert evaluation system compares each weighted metric (or a linear combination of metrics) against one or more thresholds. The results from the comparison provide an estimation of a likelihood of one or more traffic features occurring.

A driver assistance system for motor vehicles, including at least one sensor for detecting object properties of objects which are located in the surroundings of the motor vehicle; a first interface; an output unit for transmitting the object properties to a user; and a control unit. The sensor transmits the object properties in a form of a first signal to the first interface. The first interface transmits the object properties, received in the form of the first signal, to the control unit in the form of a second signal, the control unit being configured to forward the object properties, received in the form of a second signal, to the output unit and to control the output of the object properties by the output unit.