An information processing system includes a pre-processor that obtains input data; a model processor that obtains output data by inputting the input data to part of a machine learning model, and outputs the output data; and a post-processor which obtains the output data from the model processor, and executes post-processing using the output data. The model processor obtains data indicating a feature as the output data, the data being data output from the part of the machine learning model for the input data and being obtained in the middle of the prediction performed by the data. The post-processor identifies the result of the prediction performed by the machine learning model by inputting the output data to a remaining part of the machine learning model, and executes post-processing on the result of the prediction.

A LIDAR system is disclosed. The LIDAR system may include at least one light source configured to project laser light toward a field of view of the LIDAR system, at least one sensor configured to detect laser light reflections from objects in the field of view of the LIDAR system, and at least one processor configured to perform operations. The processor may be configured to use the laser light reflections to generate point-cloud representations of an environment of the LIDAR system within the field of view of the LIDAR system, output navigational information based on the generated point-cloud representations to one or more processors associated with a vehicle on which the LIDAR system is mounted, and store at least some of the generated point-cloud representations in a cache memory to provide a point-cloud archive. The processor may further be configured to detect occurrence of a point-cloud archive output triggering event, in response to detection of the point-cloud archive output triggering event, collect from the cache memory two or more point clouds from the point-cloud archive that were generated within a predetermined period of time relative to the detected point-cloud archive output triggering event, and output the two or more point clouds collected from the cache memory.

To improve user data management in vehicles, a computer-implemented method, for deletion of data in a data storage of a vehicle having an HSM, includes: a) a user causing an HMI to generate an erase command for private data that is suitable to personally identify the user; b) transmitting the erase command to an ECU of the vehicle; c) identifying the user by checking a user ID stored in a user ID database and determining the existence of the user ID and, if the user ID is determined to exist, continuing in step d), otherwise continuing in step e); d) generating a request for destruction of an encryption key that is associated with the user ID and sending said request to the HSM and the HSM destroying the encryption key; and e) delete the private data indicated by the user.

A system and a method for calibrating a wake-up sequence for a user includes determining that the user is asleep based upon sensor data, activating one or more stimulus mechanisms for a set period of time in a test wake-up sequence upon occurrence of a wake-up condition, determining an elapsed time within the set period of time of the one or more stimulus mechanisms being activated in the test wake-up sequence at which the user wakes from sleep based on additional sensor data, comparing the elapsed time to a threshold time indicative of a sufficient wake-up time, and determining a calibrated wake-up sequence including the one or more stimulus mechanisms having elapsed times below the threshold time.

Described herein are various techniques, including a system that uses high-rate acceleration data for computing an accident score indicative of a potential collision and triggering an action in response to determining that the accident score indicates a potential collision. The system is configured to filter out undesired high-rate acceleration trigger events such as noise and harsh braking events prior to determining the accident score. The accident score is based on contexts or scores computed from high-rate acceleration data, speed, and GPS data captured by a telematics monitor deployed in a vehicle.

A control device is configured to generate a control command for controlling a movable body, using measurement results of a plurality of distance measurement devices. The control device includes a point cloud combining unit configured to create combined point cloud data by combining two or more pieces of three-dimensional point cloud data that are obtained by two or more distance measurement devices of the plurality of distance measurement devices. The control device is configured to execute a first estimation process of estimating at least one of the position and orientation of the movable body, using the combined point cloud data.

After a driver parks a vehicle and has left the vehicle, a system relocates the autonomous vehicle into an optimized parking spot. The system obtains availability of other parking spots within a parking lot in which the vehicle is located. The system estimates whether any alternate parking spot would optimize cabin temperature and whether the energy consumed to complete an autonomous relocation of the vehicle will obtain a net savings in fuel economy relative to the energy expended by the relocation. The system determines the benefits of these optimized parking spots by using shaded and unshaded areas, GPS location of the vehicle, current date and time, and weather and fuel consumption estimates. If a favorable parking spot is determined, the autonomous vehicle relocates into the optimal alternate parking spot and informs the driver of the new location.

A system and a method for calibrating a wake-up sequence for a user includes determining that the user is asleep based upon sensor data, activating one or more stimulus mechanisms for a set period of time in a test wake-up sequence upon occurrence of a wake-up condition, determining an elapsed time within the set period of time of the one or more stimulus mechanisms being activated in the test wake-up sequence at which the user wakes from sleep based on additional sensor data, comparing the elapsed time to a threshold time indicative of a sufficient wake-up time, and determining a calibrated wake-up sequence including the one or more stimulus mechanisms having elapsed times below the threshold time.

A processor-implemented method with path generation includes obtaining input data that includes recognition sensor data and state data, inputting the input data into an artificial neural network (ANN) model and outputting output data corresponding to the input data in a single forward process, and obtaining path data and control data corresponding to the path data, based on the output data.

A contextual communication system includes an external device including a communication receiver and an electronic control unit (ECU). The ECU includes data processing hardware and memory hardware that stores actions and action settings. The data processing hardware includes a contextual communication feature that has a telematics system configured to detect the external device and a contextual event. The contextual communication feature is configured to selectively issue a contextual alert based on the detected external device and in response to the contextual event.