Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed that calibrate error aligned uncertainty for regression and continuous structured prediction tasks/optimizations. An example apparatus includes a prediction model, at least one memory, instructions, and processor circuitry to at least one of execute or instantiate the instructions to calculate a count of samples corresponding to an accuracy-certainty classification category, calculate a trainable uncertainty calibration loss value based on the calculated count, calculate a final differentiable loss value based on the trainable uncertainty calibration loss value, and calibrate the prediction model with the final differentiable loss value.

Abstract: For example, an apparatus may include an input to receive Machine Learning (ML) model information corresponding to an ML model to process input information; and a processor to construct a multi-model ML architecture including a plurality of ML model variants based on the ML model, wherein the processor is configured to determine the plurality of ML model variants based on an attribution-based diversity metric corresponding to a model group including a first ML model variant and a second ML model variant, wherein the attribution-based diversity metric corresponding to the model group is based on a diversity between a first attribution scheme and a second attribution scheme, the first attribution scheme representing first portions of the input information attributing to an output of the first ML model variant, the second attribution scheme representing second portions of the input information attributing to an output of the second ML model variant.

Abstract: Disclosed herein are systems, devices, and methods for an uncertainty-aware robot system that may perform a personalized risk analysis of an observed person. The uncertainty-aware robot system determines a recognized behavior for the observed person based on sensor information indicative of a gait of the observed person. The uncertainty-aware robot system determines an uncertainty score for the recognized behavior based on a comparison of the recognized behavior to potentially expected behaviors associated with the observed person and the environment. The uncertainty-aware robot system generates a remedial action instruction based on the uncertainty score.

Abstract: An exemplary method includes obtaining vehicle data comprising environmental perception data indicating a risk assessment regarding one or more perceived elements of an environment surrounding a vehicle; obtaining driver perception data regarding a driver inside the vehicle; determining an integrated risk assessment based on the vehicle data and the driver perception data; and determining an Operational Design Doman (ODD) compliance assessment of the vehicle at least based on the determined integrated risk assessment.

Abstract: Disclosed herein are systems, devices, and methods for improving the safety of a robot. The safety system may determine a safety envelope of a robot based on a planned movement of the robot and based on state information about a load carried by a robot. The state information may include a dynamic status of the load. The safety system may also determine a safety risk based on a detected object with respect to the safety envelope. The safety system may also generate a mitigating action to the planned movement if the safety risk exceeds a threshold value.

Abstract: Disclosed herein are systems and methods for dynamically distributing a safety, awareness task. The systems and methods may include receiving hardware resources data associated with a plurality of remote computing systems. A plurality of safety assurance profiles may be received. Each of the plurality of safety assurance profiles may be associated with a respective service. A safety assurance task may be dynamically assigned to one of the plurality of remote computing systems based on the hardware resources data and one of the plurality of safety assurance profiles.

Abstract: A computing device, including: a memory configured to store computer-readable instructions; and unintended human motion detection processing circuitry configured to execute the computer-readable instructions to cause the computing device to: interpret a human action; receive autonomous mobile robot (AMR) sensor data from an AMR sensor; and detect whether the human action is intended or unintended, wherein the detection is based on a predicted human action, a current human emotional or physical state, the interpreted human action, and the AMR sensor data.

Abstract: A device may include an image sensor, configured to generate image sensor data representing a vicinity of the device; an image processor, configured to generate a first code from the image sensor data using a code generation protocol; an input validity checker, configured to compare the first code to a second code; and if a similarity of the first code and the second code is within a predetermined range, operate according to a first operational mode; and if the similarity of the first code and the second code is not within the predetermined range, operate according to a second operational mode.

Abstract: Devices and methods for a vehicle are provided in this disclosure. A device for controlling an active seat of a vehicle may include a processor and a memory. The memory may be configured to store a transfer function. The processor may be configured to predict an acceleration of the active seat of the vehicle based on a first sensor data and the transfer function. The first sensor data may include information indicating an acceleration of a vibration source for the vehicle. The processor may be further configured to generate a control signal to control a movement of the active seat at a first instance of time based on the predicted acceleration.

Abstract: Techniques are disclosed to address issues related to the use of personalized training data to supplement machine learning trained models for Driver Monitoring System (DMS), and the accompanying mechanisms to maintain confidentiality of this personalized training data. The techniques disclosed herein also address issues related to maintaining transparency with respect to collected sensor data used in a DMS. Additionally, the techniques disclosed herein facilitate the generation of a digital representation of a driver for use as supplemental training data for the DMS machine learning trained models, which allow for DMS algorithms to be tailored to individual users.

Abstract: Devices and methods for a road user are provided in this disclosure. An apparatus for determining detection of a road user may include a memory configured to store a plurality of data items received from a plurality of further road users. Each of the plurality of data items may include a detection information indicating whether an object has or has not been detected by one of the plurality of further road users. Furthermore, the apparatus may include a processor that is configured to determine a detection result indicating whether the road user has been detected by the one of the plurality of further road users based on the detection information.

Abstract: Disclosed herein is a vehicle handover system that monitors an environment of a vehicle. The vehicle handover system receives a transition request to change control of the vehicle from an automated driving mode to a passenger of the vehicle. The vehicle handover system detects a key event that may be relevant to the transition request and the detection of the key event is based on the monitored environment. The vehicle handover system may generate a handover scene that includes images associated with the key event, and the images include an image sequence over a time-period of the key event. Before the vehicle handover system changes control of the vehicle from the automated driving mode to the passenger, the handover scene is displayed to the passenger.

Abstract: Techniques are disclosed to detect, inform, and automatically correct typical awareness-related human driver mistakes. This may include those that are caused by a misunderstanding of the current situation, a lack of focus or attention, and/or overconfidence in any currently-engaged assistance features. The disclosure is directed to the prediction of vehicle maneuvers using driver and external environment modeling. The consequence of executing a predicted maneuver is categorized based upon its risk or danger posed to the driving environment, and the vehicle may execute various actions based upon the categorization of a predicted riving maneuver to mitigate or eliminate that risk.

Abstract: Methods, systems, and apparatus, including computer programs encoded on non-transitory computer storage medium(s), are directed to improving completeness of map information and data related to maps created through sensor data. Map completeness can be improved by determining object completeness and coverage completeness of a generated map and reducing amount of unknown areas of the generated map.

Abstract: Disclosure herein are systems and methods for deploying an autonomous vehicle during an idle time. As disclosed herein, a request for a mobility service may be received. The request may include constraints for usage of the autonomous vehicle. An optimal mobility service strategy may be determined based on the constraints. The optimal mobility service strategy may be selected from a plurality of mobility service strategies. A notification may be transmitted to a user device. The notification may include details of the optimal mobility service strategy.

Abstract: Disclosed embodiments prioritize gaps in V2X coverage and then selectively route traffic based on the prioritized gaps. Some embodiments combine historical vehicle presence along a route with predicted prospective vehicle traffic along the route to generate a map of regions that have a high confidence of a need for V2X coverage. This high confidence map is compared to a historical V2X coverage in those regions. From this comparison, a set of high priority V2X gaps is identified. Vehicles are then selectively routed either around or into the gaps.

Abstract: Various systems and methods for pedestrian traffic management are described herein, comprising segmenting a pedestrian route into at least one pedestrian walking segment using location information of transportation resources, and determining estimated transit times for the at least one pedestrian walking segment and an estimated wait time for the first transportation resource using received status information of the first transportation resource and the determined estimated transit time for the first pedestrian walking segment.

Abstract: Described herein is a high confidence ground truth information service executing on a network of edge computing devices. A variety of participating devices obtain high confidence ground truth information relating to objects in a local environment. This information is communicated to the ground truth information service, where it may be verified and aggregated with similar information before being communicated as part of an acquired ground truth dataset to one or more subscribing devices. The subscribing devices use the ground truth information, as included in the ground truth dataset, to both validate and improve their supervised learning systems.

Abstract: V2X trusted agents provide technical solutions for technical problems facing falsely reported locations of connected vehicles within V2X systems. These trusted agents (e.g., trusted members) may be used to detect an abrupt physical attenuation of a wireless signal and determine whether the attenuation was caused by signal occlusion caused by the presence of an untrusted vehicle or other untrusted object. When the untrusted vehicle is sending a message received by trusted agents, these temporary occlusions allow trusted members to collaboratively estimate the positions of untrusted vehicles in the shared network, and to detect misbehavior by associating the untrusted vehicle with reported positions. Trusted agents may also be used to pinpoint specific mobile targets. Information about one or more untrusted vehicles may be aggregated and distributed as a service.

Abstract: Various systems and methods for providing autonomous driving within a restricted area are discussed. In an examples, an autonomous vehicle control system can include an interface for receiving data from multiple sensors for detecting an environment about the vehicle, a security processor coupled to the configured to receive sensor information from the sensor interface, and autonomous driving system including one or more virtual machines configured to selectively receive information from the security processor based on a security request from infrastructure of the restricted area.