Abstract: In one example embodiment, a computer-implemented method for autonomous vehicle control includes determining whether a cargo container is attached to the vehicle base. The method includes controlling a front shield associated with an autonomous vehicle to move from a closed position to an opened position when a cargo container is determined to be attached to a vehicle base associated with the autonomous vehicle. The method includes controlling the front shield to move from the opened position to the closed position when the cargo container is not attached to the vehicle base.

Abstract: In one example embodiment, a computer-implemented method for managing available capacity at a location for receiving an asset includes obtaining data indicative of one or more first assets that will arrive at a first location within a first transfer hub at an arrival time, the one or more first assets being associated with a first service provider. The method includes determining an available capacity at the first location within the first transfer hub for receiving the one or more first assets at the arrival time. The method includes moving one or more second assets positioned at the first location to a second location within the first transfer hub to increase the available capacity at the first location for receiving the one or more first assets at the arrival time.

Abstract: Systems and methods for controlling an autonomous vehicle are provided. In one example embodiment, a computer-implemented method includes obtaining sensor data indicative of a surrounding environment of the autonomous vehicle, the surrounding environment including one or more occluded sensor zones. The method includes determining that a first occluded sensor zone of the occluded sensor zone(s) is occupied based at least in part on the sensor data. The method includes, in response to determining that the first occluded sensor zone is occupied, controlling the autonomous vehicle to travel clear of the first occluded sensor zone.

Abstract: In one example embodiment, a computer-implemented method includes receiving data representing a motion plan of the autonomous vehicle via a plurality of control lanes configured to implement the motion plan to control a motion of the autonomous vehicle, the plurality of control lanes including at least a first control lane and a second control lane, and controlling the first control lane to implement the motion plan. The method includes detecting one or more faults associated with implementation of the motion plan by the first control lane or the second control lane, or in generation of the motion plan, and in response to one or more faults, controlling the first control lane or the second control lane to adjust the motion of the autonomous vehicle based at least in part on one or more fault reaction parameters associated with the one or more faults.

Abstract: A LIDAR system is provided. The LIDAR system includes an emitter. The emitter includes a light source and one or more lenses positioned along a transmit path. The light source is configured to emit a primary laser beam through the one or more lenses in the transmit path to provide a transmit beam. The LIDAR system includes a receiver spaced apart from the emitter. The receiver includes one or more lenses positioned along a receive path such that the one or more lenses receive a reflected laser beam. The LIDAR system includes an optical element positioned along the transmit path. The optical element is configured to direct a portion of the primary laser beam in a direction towards the receive path as a secondary laser beam.

Abstract: The present disclosure is directed to altering vehicle paths. In particular, a computing system can access map data for a geographic area. The computing system can obtain target zone data describing a target zone within the geographic area. The computing system can determine an altered nominal path to traverse the target zone. The computing system can designate a portion of the altered nominal path as a designated action region associated with the target zone. The computing system can generate a longitudinal plan for an autonomous vehicle through the geographic area based on the altered nominal path. The computing system can generate a target velocity for one or more portions of the nominal path within the designated action region. The computing system can generate a trajectory for the autonomous vehicle based on the target velocity and the altered nominal path.

Abstract: Provided are systems and methods that perform multi-task and/or multi-sensor fusion for three-dimensional object detection in furtherance of, for example, autonomous vehicle perception and control. In particular, according to one aspect of the present disclosure, example systems and methods described herein exploit simultaneous training of a machine-learned model ensemble relative to multiple related tasks to learn to perform more accurate multi-sensor 3D object detection. For example, the present disclosure provides an end-to-end learnable architecture with multiple machine-learned models that interoperate to reason about 2D and/or 3D object detection as well as one or more auxiliary tasks. According to another aspect of the present disclosure, example systems and methods described herein can perform multi-sensor fusion (e.g.

Abstract: Systems and methods for controlling the motion of an autonomous are provided. In one example embodiment, a computer-implemented method includes obtaining data associated with an object within a surrounding environment of an autonomous vehicle. The data associated with the object is indicative of a predicted motion trajectory of the object. The method includes determining a vehicle action sequence based at least in part on the predicted motion trajectory of the object. The vehicle action sequence is indicative of a plurality of vehicle actions for the autonomous vehicle at a plurality of respective time steps associated with the predicted motion trajectory. The method includes determining a motion plan for the autonomous vehicle based at least in part on the vehicle action sequence. The method includes causing the autonomous vehicle to initiate motion control in accordance with at least a portion of the motion plan.

Abstract: The present disclosure provides autonomous vehicle systems and methods that include or otherwise leverage a motion planning system that generates constraints as part of determining a motion plan for an autonomous vehicle (AV). In particular, a scenario generator within a motion planning system can generate constraints based on where objects of interest are predicted to be relative to an autonomous vehicle. A constraint solver can identify navigation decisions for each of the constraints that provide a consistent solution across all constraints. The solution provided by the constraint solver can be in the form of a trajectory path determined relative to constraint areas for all objects of interest. The trajectory path represents a set of navigation decisions such that a navigation decision relative to one constraint doesn't sacrifice an ability to satisfy a different navigation decision relative to one or more other constraints.

Abstract: Systems and methods for vehicle spatial path sampling are provided. The method includes obtaining an initial travel path for an autonomous vehicle from a first location to a second location and vehicle configuration data indicative of one or more physical constraints of the autonomous vehicle. The method includes determining one or more secondary travel paths for the autonomous vehicle from the first location to the second location based on the initial travel path and the vehicle configuration data. The method includes generating a spatial envelope based on the one or more secondary travel paths that indicates a plurality of lateral offsets from the initial travel path. And, the method includes generating a plurality of trajectories for the autonomous vehicle to travel from the first location to the second location such that each of the plurality of trajectories include one or more lateral offsets identified by the spatial envelope.

Abstract: Systems and methods for generating synthetic testing data for autonomous vehicles are provided. A computing system can obtain map data descriptive of an environment and object data descriptive of a plurality of objects within the environment. The computing system can generate context data including deep or latent features extracted from the map and object data by one or more machine-learned models. The computing system can process the context data with a machine-learned model to generate synthetic motion prediction for the plurality of objects. The synthetic motion predictions for the objects can include one or more synthesized states for the objects at future times. The computing system can provide, as an output, synthetic testing data that includes the plurality of synthetic motion predictions for the objects. The synthetic testing data can be used to test an autonomous vehicle control system in a simulation.

Abstract: In one example embodiment, a computer-implemented method includes receiving data representing a motion plan of the autonomous vehicle via a plurality of control lanes configured to implement the motion plan to control a motion of the autonomous vehicle, the plurality of control lanes including at least a first control lane and a second control lane, and controlling the first control lane to implement the motion plan. The method includes detecting one or more faults associated with implementation of the motion plan by the first control lane or the second control lane, or in generation of the motion plan, and in response to one or more faults, controlling the first control lane or the second control lane to adjust the motion of the autonomous vehicle based at least in part on one or more fault reaction parameters associated with the one or more faults.

Abstract: Systems and methods are disclosed for motion forecasting and planning for autonomous vehicles. For example, a plurality of future traffic scenarios are determined by modeling a joint distribution of actor trajectories for a plurality of actors, as opposed to an approach that models actors individually. As another example, a diversity objective is evaluated that rewards sampling of the future traffic scenarios that require distinct reactions from the autonomous vehicle. An estimated probability for the plurality of future traffic scenarios can be determined and used to generate a contingency plan for motion of the autonomous vehicle. The contingency plan can include at least one initial short-term trajectory intended for immediate action of the AV and a plurality of subsequent long-term trajectories associated with the plurality of future traffic scenarios.

Abstract: Systems and methods for identifying travel way features in real time are provided. A method can include receiving two-dimensional and three-dimensional data associated with the surrounding environment of a vehicle. The method can include providing the two-dimensional data as one or more input into a machine-learned segmentation model to output a two-dimensional segmentation. The method can include fusing the two-dimensional segmentation with the three-dimensional data to generate a three-dimensional segmentation. The method can include storing the three-dimensional segmentation in a classification database with data indicative of one or more previously generated three-dimensional segmentations. The method can include providing one or more datapoint sets from the classification database as one or more inputs into a machine-learned enhancing model to obtain an enhanced three-dimensional segmentation.

Abstract: Systems and methods for streaming sensor packets in real-time are provided. An example method includes obtaining a sensor data packet representing a first portion of a three-hundred and sixty degree view of a surrounding environment of a robotic platform. The method includes generating, using machine-learned model(s), a local feature map based at least in part on the sensor data packet. The local feature map is indicative of local feature(s) associated with the first portion of the three-hundred and sixty degree view. The method includes updating, based at least in part on the local feature map, a spatial map to include the local feature(s). The spatial map includes previously extracted local features associated with a previous sensor data packet representing a different portion of the three-hundred and sixty degree view than the first portion. The method includes determining an object within the surrounding environment based on the updated spatial map.

Abstract: Systems and methods for integrating radar and LIDAR data are disclosed. In particular, a computing system can access radar sensor data and LIDAR data for the area around the autonomous vehicle. The computing system can determine, using the one or more machine-learned models, one or more objects in the area of the autonomous vehicle. The computing system can, for a respective object, select a plurality of radar points from the radar sensor data. The computing system can generate a similarity score for each selected radar point. The computing system can generate weight associated with each radar point based on the similarity score. The computing system can calculate predicted velocity for the respective object based on a weighted average of a plurality of velocities associated with the plurality of radar points. The computing system can generate a proposed motion plan based on the predicted velocity for the respective object.

Abstract: Systems and methods are disclosed for detecting and predicting the motion of objects within the surrounding environment of a system such as an autonomous vehicle. For example, an autonomous vehicle can obtain sensor data from a plurality of sensors comprising at least two different sensor modalities (e.g., RADAR, LIDAR, camera) and fused together to create a fused sensor sample. The fused sensor sample can then be provided as input to a machine learning model (e.g., a machine learning model for object detection and/or motion prediction). The machine learning model can have been trained by independently applying sensor dropout to the at least two different sensor modalities. Outputs received from the machine learning model in response to receipt of the fused sensor samples are characterized by improved generalization performance over multiple sensor modalities, thus yielding improved performance in detecting objects and predicting their future locations, as well as improved navigation performance.

Abstract: Systems and methods are directed to automated delivery systems. In one example, a vehicle is provided including a drive system, a passenger cabin; and a delivery service pod provided relative to the passenger cabin. The delivery service pod includes an access unit configured to allow for loading and unloading of a plurality of delivery crates into the delivery service pod. The delivery service pod further includes a conveyor unit comprising multiple delivery crate holding positions, the delivery crate holding positions being defined by neighboring sidewalls spaced apart within the delivery service pod such that a respective delivery crate of the plurality of delivery crates can be positioned between neighboring sidewalls, wherein the conveyor unit is configured to be rotated to align each of the delivery crate holding positions with the access unit.

Abstract: Disclosed are methods, systems, and non-transitory computer readable media that control an autonomous vehicle via at least two sensors. One aspect includes capturing an image of a scene ahead of the vehicle with a first sensor, identifying an object in the scene at a confidence level based on the image, determining the confidence level of the identifying is below a threshold, in response to the confidence level being below the threshold, directing a second sensor having a field of view smaller than the first sensor to generate a second image including a location of the identified object, further identifying the object in the scene based on the second image, controlling the vehicle based on the further identification of the object.

Abstract: Systems and methods for controlling the motion of an autonomous are provided. In one example embodiment, a computer implemented method includes obtaining, by one or more computing devices on-board an autonomous vehicle, data associated with one or more objects that are proximate to the autonomous vehicle. The data includes a predicted path of each respective object. The method includes identifying at least one object as an object of interest based at least in part on the data associated with the object of interest. The method includes generating cost data associated with the object of interest. The method includes determining a motion plan for the autonomous vehicle based at least in part on the cost data associated with the object of interest. The method includes providing data indicative of the motion plan to one or more vehicle control systems to implement the motion plan for the autonomous vehicle.