A method for a follower vehicle following a lead vehicle, comprising establishing, in a first control mode of the follower vehicle, a path for the follower vehicle to follow the lead vehicle, characterized by generating environmental data which is related to the environment of the lead vehicle, determining, based on the generated environmental data, an expected behaviour of an operational parameter of the lead vehicle, determining an actual behaviour of the lead vehicle operational parameter, comparing the determined expected behaviour of the lead vehicle operational parameter and the determined actual behaviour of the lead vehicle operational parameter, determining based on said comparison whether to continue in first control mode of the follower vehicle, or in a second control mode of the follower vehicle, differing from the first control mode.

Systems, apparatus and methods may be configured to implement actively-controlled light emission from a robotic vehicle. A light emitter(s) of the robotic vehicle may be configurable to indicate a direction of travel of the robotic vehicle and/or display information (e.g., a greeting, a notice, a message, a graphic, passenger/customer/client content, vehicle livery, customized livery) using one or more colors of emitted light (e.g., orange for a first direction and purple for a second direction), one or more sequences of emitted light (e.g., a moving image/graphic), or positions of light emitter(s) on the robotic vehicle (e.g., symmetrically positioned light emitters). The robotic vehicle may not have a front or a back (e.g., a trunk/a hood) and may be configured to travel bi-directionally, in a first direction or a second direction (e.g., opposite the first direction), with the direction of travel being indicated by one or more of the light emitters.

A side collision risk estimation system for a vehicle comprises a speed sensor, a road line markers detector, a movement sensor, an object detector, and a controller. The controller is configured to estimate: the current speed of the vehicle, a heading of the adjacent road line ahead of the vehicle, a heading of the vehicle, a compensated heading of the vehicle, a predicted lateral change position of the vehicle, a heading of a target vehicle relative to the vehicle, the current speed of the target vehicle, the current lateral distance between the vehicles, the heading of the adjacent road line ahead of the target vehicle, a compensated relative heading of the target vehicle, a predicted lateral change position of the target vehicle, a predicted lateral distance over time between the vehicles, and a side collision risk over time from the predicted lateral distance between the vehicles.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for predicting near-curb driving behavior. One of the methods includes obtaining agent trajectory data for an agent in an environment, the agent trajectory data comprising a current location and current values for a predetermined set of motion parameters of the agent; processing a model input generated from the agent trajectory data using a trained machine learning model to generate a model output comprising a prediction of whether the agent will exhibit near-curb driving behavior within a predetermined timeframe, wherein an agent exhibits near-curb driving behavior when the agent operates within a particular distance of an edge of a road in the environment; and using the prediction to generate a planned path for a vehicle in the environment.

Systems and methods for detecting a surprise or unexpected movement of an actor with respect to an autonomous vehicle are provided. An example computer-implemented method can include, for a first compute cycle, obtaining motion forecast data based on first sensor data collected with respect to an actor relative to an autonomous vehicle; and determining, based on the motion forecast data, failsafe region data representing an unexpected path or area where a likelihood of the actor following the unexpected path or entering the unexpected area is below a threshold. For a second compute cycle after the first compute cycle, the method can include obtaining second sensor data; determining, based on the second sensor data and the failsafe region data, that the actor has followed the unexpected path or entered the unexpected area; and in response to such determination, determining a deviation for controlling a movement of the autonomous vehicle.

This specification discloses an obstacle trajectory prediction method and apparatus. In embodiments of the present disclosure, a global interaction feature under joint action of a vehicle and obstacles is determined according to historical status information and current status information of the vehicle, historical status information and current status information of the obstacles, and a future motion trajectory planned by the vehicle; an individual interaction feature of a to-be-predicted obstacle is determined according to the global interaction feature and current status information of the to-be-predicted obstacle; and a future motion trajectory of the to-be-predicted obstacle is predicted through the individual interaction feature and information about an environment around the vehicle.

A method for monitoring uncertainty for human-like behavioral modulation of trajectory planning includes: retrieving map and agent information of a current driving state of an autonomously operated host automobile vehicle; dividing uncertainty conditions affecting a trajectory of the host automobile vehicle into an expected uncertainty and an unexpected uncertainty; calculating the expected uncertainty in a first operation branch by forming attention zones according to identified portions of lanes which may potentially collide with a planned route of the host automobile vehicle; determining the unexpected uncertainty in a second operation branch by calculating an anomaly score for any other vehicles in a surrounding area of the host automobile vehicle positioned in the lanes which may potentially collide with the planned route of the host automobile vehicle; and modulating trajectory operation signals determined for the expected uncertainty if the unexpected uncertainty meets or exceeds a predetermined threshold.

A method using unsupervised velocity prediction and correction for urban driving from sequences of noisy position estimates includes: performing a vehicle velocity prediction for one or more other vehicles in a vicinity of a host automobile vehicle; calculating a first heuristic based on a uniformity test; calculating a second heuristic based on a vehicle speed of the one or more other vehicles; combining the first heuristic and the second heuristic using a weighted sum; determining an uncertainty mask applying the combined first heuristic and the second heuristic and a heuristic threshold; and applying the uncertainty mask to identify a velocity correction for use by the host automobile vehicle.

An apparatus, including: an interface configured to receive raw images of one or more objects across a timeseries of frames corresponding to a movement event from a perspective of a vehicle of interest (Vol); and processing circuitry that is configured to: track a change in intensity or direction information represented in motion vectors (MVs) generated based on the raw images; generate, based on the change in the intensity or direction information, a weight of an influence vector representing a Vol influence on the movement event; and transmit the weight of the influence vector and an identity of the movement event to an assessment system that is configured to utilize the weight of the influence vector in an assessment of the Vol.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, that determine yield behavior for an autonomous vehicle. An agent that is in a vicinity of an autonomous vehicle can be identified. An obtained crossing intent prediction characterizes a predicted likelihood that the agent intends to cross a roadway during a future time period. First features of the agent and of the autonomous vehicle are obtained. An input that includes the first features and the crossing intent prediction is processed using a machine learning model to generate an intent yielding score that represents a likelihood that the autonomous vehicle should perform a yielding behavior due to the intent of the agent to cross the roadway. From at least the intent yielding score, an intent yield behavior signal is determined and indicates whether the autonomous vehicle should perform the yielding behavior prior to reaching the first crossing region.