Abstract: Methods and systems are provided for predicting temporal Lidar labels with a single click. In some aspects, a process can include steps for receiving point cloud data based on a detected object from an autonomous vehicle, determining an object based on the point cloud data of the detected object and corresponding models related to the detected object, updating the models based on the point cloud data of the detected object and selected object labels, the selected object labels being based on 3D bounding boxes of the detected object, and providing the updated models to the autonomous vehicle for deployment. Systems and machine-readable media are also provided.

Abstract: A solar loading-based system includes a memory, a disturbance prediction module, a cabin temperature estimation module and a thermal control module. The memory stores a cabin thermal load model of an interior cabin of a host vehicle and a solar load prediction model. The disturbance prediction module: receives signals indicative of states of cabin thermal actuators and comfort metrics; and predicts an effect of solar loading over a known portion of a predicted route including predicting cabin temperatures based on the solar load prediction model, the states of the cabin thermal actuators, and the comfort metrics. The cabin temperature estimation module, based on the cabin thermal load model, determines a first comfort metric based on the predicted cabin temperatures. The thermal control module controls cabin thermal actuators to adjust cabin states, including the first comfort metric, to respective target values based on the predicted effect of solar loading.

Abstract: A system and method for selectively augmenting information in a vehicle includes receiving a scene information from at least one sensor. identifying a region of interest from the scene information, analyzing the scene information to determine whether the region of interest is occluded, and augmenting the region of interest using a display system when the region of interest is occluded. The region of interest includes an object identified within the scene information that is classified as related to vehicle safety.

Abstract: A vehicle trim component, a vehicle including a vehicle trim component, and method of making a vehicle trim component. The vehicle trim component includes a substrate including a first polymer. The substrate includes a first surface, and the first polymer includes bisphenol-A based polycarbonate. The vehicle trim component also includes an exterior layer including a second polymer. The second polymer includes isosorbide-based polycarbonate. The exterior layer includes an exterior surface, and the exterior layer is laminated to the first surface of the substrate.

Abstract: Low waste methods for three-dimensional printing techniques are provided. A method includes performing a preceding additive infusion process including: solubilizing an additive into a medium in a supercritical fluid state; contacting a preceding material with the medium to infuse a portion of the additive into the preceding material to form a preceding additive-infused material; and separating remaining additive from the medium. Further, the method includes performing at least one succeeding additive infusion process including: solubilizing the remaining additive and, optionally, additional additive, into the medium in a supercritical fluid state; and contacting a succeeding material with the medium to infuse at least a portion of the remaining and additional additive into the succeeding material to form a succeeding additive-infused material, wherein the medium from the preceding additive infusion process is reused in the at least one succeeding additive infusion process.

Abstract: An antenna system includes a first antenna operational to transmit a first radio-frequency signal, a second antenna operational to receive a second radio-frequency signal and receive the first radio-frequency signal, a first electromagnetic polarizer disposed between the first antenna and the second antenna and operational to change a polarization of the first radio-frequency signal, a second electromagnetic polarizer disposed between the first electromagnetic polarizer and the second antenna and operational to further change the polarization of the first radio-frequency signal, and a conductive ground plane disposed on a ground side of the first antenna and the second antenna. The conductive ground plane defines a gap between the first antenna and the second antenna. The gap extends under the first electromagnetic polarizer. The gap extends under the second electromagnetic polarizer. A horizontal component of the second polarization of the first radio-frequency signal is maintained across the gap.

Abstract: A button assembly for a release system comprises a housing and an actuator coupled to the housing and translatable along a first axis. The actuator comprises a contact surface configured for engagement by an operator to translate the actuator along the first axis, and a rack gear extending along the first axis and away from the contact surface. The button assembly further comprises a pinion gear coupled to the housing and rotatable about a second axis, orthogonal to the first axis. The pinion gear is meshed with the rack gear and with the extension member coupled to the pinion gear. The mesh between the pinion gear and the rack gear facilitates rotation of the pinion gear as the rack gear translates, with the rotation of the pinion gear facilitating movement of the extension member and movement of the latch between the engagement and disengagement positions.

Abstract: Platforms to support and manage an autonomous vehicle (AV) fleet can be implemented on and supported by cluster infrastructure. Cluster infrastructure may include different clusters, such as a cluster for an AV fleet with safety drivers, and a cluster for an AV fleet without safety drivers. Updates to the cluster infrastructure can be made to multiple clusters at once. Such updates may cause an outage that impacts multiple clusters and create a massive vehicle retrieval event for all AV fleets. To mitigate the risk and allow for prioritization of clusters, updates can be rolled out in a staged and ordered manner according to order values associated with different clusters. After applying an update to a cluster at a stage of the roll out, the cluster may be evaluated to confirm the success of the update, before the roll out can be moved to the next stage.

Abstract: Compiler failure testing is used to test compilers for compiling software where a high degree of reliability is required, e.g., compilers for software that runs on automobiles. A compiler failure testing system includes tests for testing different coding rules. When a change is made to a software compiler, the failure testing system tests the software compiler's response to the tests. If the software compiler is enforcing prescribed coding rules (e.g., AUTOSAR and/or MISRA rules), the software compiler fails to compile the tests and returns an error message. If the software compiler successfully compiles a test, this indicates that the software compiler is not enforcing all of the prescribed coding rules. In this case, developers can be alerted to make needed changes to the software compiler, so that the software compiler properly enforces the coding rules.

Abstract: Presented are high-voltage (HV) electrical systems pairing solid-state relays (SSRs) with electromechanical contactors for optimized galvanic disconnect, methods for making/using such systems, and vehicles equipped with such systems. An HV electrical system includes a first circuit loop that connects a rechargeable energy storage system (RESS) to an electrified powertrain. A second circuit loop, which is parallel to the first circuit loop, connects the RESS to a charge inlet of a battery charging system. A first contactor switch on the first circuit loop serially connects with the powertrain's electric motor and a first terminal of a RESS battery assembly. A second contactor switch on the second circuit loop serially connects with the charge inlet and the first terminal. One or more SSR switches electrically connect in series with a second terminal of the battery assembly, the electric motor and/or charge inlet, and the two contactor switches across the battery assembly.

Abstract: Applications supporting operations of an autonomous vehicle fleet can be implemented on and supported by cluster infrastructure. Demands on the cluster infrastructure from these systems can vary greatly and change often. Specifications for the hardware and software for the cluster infrastructure may be updated frequently. Therefore, significant resources can be spent to maintain the cluster infrastructure. If not managed or monitored properly, some changes to the cluster infrastructure may cause disruption to the systems running on the cluster infrastructure. The process of managing the upgrades to the cluster infrastructure can be laborious. To address at least some of these concerns, a computer-implemented operator can determine a migration plan based on the systems that are running on the cluster infrastructure.

Abstract: Applications supporting operations of an autonomous vehicle fleet can be implemented on and supported by cluster infrastructure. These applications have endpoints where data traffic runs in and out of these applications. Monitoring the health of these endpoints can be performed by a third-party vendor solution. Third-party vendor solutions cannot access protected endpoints in the cluster infrastructure easily. Also, some solutions are resource intensive. To address some of these shortcomings, an endpoint monitoring system can be developed by cluster operators and implemented directly on the cluster infrastructure based on a producer-consumer model. The consumers of the model can perform health checks on the protected endpoints in the cluster using the same authorized path as other users of the cluster infrastructure.

Abstract: Failures can occur when a software process is running, or when the software process is undergoing tests. A remote debugging session can be created to run and inspect the software process, so that a developer can fix the bug that caused a failure. Remote debugging sessions can consume valuable resources on cluster infrastructure. Debugging the failures can take up a significant amount of developer time. To alleviate some of these problems, a remote debugging session can be created on-demand at a later time when a developer is ready to start the remote debugging session. The deferred creation of the remote debugging session can be triggered by activating a uniform resource identifier that has information for creating the remote debugging session encoded therein. The resulting implementation makes it easy for a developer to create a remote debugging session, and resources can be allocated on an as-needed basis.

Abstract: A control loop for scaling cloud-based agents in a cluster includes a controller and a feedback signal. The controller may be a proportional-integral controller, or a proportional-integral-derivative controller. The controller may calculate a control variable based on a target number of idle agents for the cluster. The controller receives a target number of idle agents, as well as a current number of idle agents in a cluster. The controller computes the control variable based on the error between the target and current numbers of idle agents, and an integral of the error over time.

Abstract: A build system for compiling and building software projects includes an integrity verification system that serves as a gate for whether to add code to a repository. When the build system receives a software package, the integrity verification system determines an integrity level for the received software package, which may be based on the intended use of the software and how other pieces of software depend on the software package. The integrity verification system determines whether the software package meets the requirements of the determined integrity level, e.g., in terms of code review, code testing, adherence to best practices, etc.

Abstract: Vehicles and related systems and methods are provided for managing energy consumption by resources associated with the vehicle. A power management service receives an abstract request for a resource from a software entity, obtains current status information for the vehicle from one or more systems associated with the vehicle, determines whether the requested activation of the resource associated with the abstract resource abstract request is permitted based at least in part on the current status information and a usage profile associated with the abstract resource request, and in response to determining the requested activation of the resource is permitted, the power management service automatically provides a concrete activation request to the resource.

Abstract: Build, execution, and testing on software may be performed remotely on cluster infrastructure. Tests can be scheduled on workers in the cluster infrastructure, and results of the tests are reported to the developer. If a test fails, the developer may receive an exit code from the failed test. For tests that are flaky, an exit code provides little to no benefit to identify the cause of the flakiness. To make it easier for the developer to debug flaky tests, a test identified to be flaky can be run many times in parallel, one or more parallel executions that result in failure can be paused, and one or more remote debugging sessions can be created for the one or more parallel executions. A developer can access the remote debugging session to inspect the paused execution of the test equipped with debugging tools to determine the cause of the flakiness.