An autonomous driving system includes: at least one sensor (1) configured to collect environment information around a vehicle; a primary decision unit (21) configured to calculate decision information based on the environment information collected by the at least one sensor (1), and transmit the decision information to a controller (3); an alternative decision unit (22) configured to calculate decision information based on the environment information collected by the at least one sensor (1) in response to detecting that the primary decision unit (21) is abnormal, and transmit the decision information to the controller (3); and the controller (3) configured to calculate vehicle control information based on the received decision information, and transmit the vehicle control information to a bottom vehicle controller. In this way, the stability and reliability of the autonomous driving system can be improved and safety of autonomous driving of the vehicle can be guaranteed.

Methods and systems for monitoring use and determining risks associated with operation of a vehicle having one or more autonomous operation features are provided. According to certain aspects, operating data may be recorded during operation of the vehicle. This may include information regarding the vehicle, the vehicle environment, use of the autonomous operation features, and/or control decisions made by the features. The control decisions may include actions the feature would have taken to control the vehicle, but which were not taken because a vehicle operator was controlling the relevant aspect of vehicle operation at the time. The operating data may be recorded in a log, which may then be used to determine risk levels associated with vehicle operation based upon risk levels associated with the autonomous operation features. The risk levels may further be used to adjust an insurance policy associated with the vehicle.

This document describes systems and techniques for clustering track pairs for multi-sensor track association. Many track-association algorithms use pattern-matching processes that can be computationally complex. Clustering tracks derived from different sensors present on a vehicle may reduce the computational complexity by reducing the pattern-matching problem into groups of subproblems. The weakest connection between two sets of tracks is identified based on both the perspective from each track derived from a first sensor and the perspective of each track derived from a second sensor. By identifying and pruning the weakest connection between two sets of tracks, a large cluster of tracks may be split into smaller clusters. The smaller clusters may require fewer computations by limiting the quantity of candidate track pairs to be evaluated. Fewer computations result in processing the sensor information more efficiently that, in turn, may increase the safety and reliability of an automobile.

A control apparatus includes a Wi-Fi communication module, a processor, a controller that controls a component of a vehicle, and a memory, wherein the memory stores at least one piece of position information corresponding to a position in the vehicle, and at least one registered pattern of a gesture, face, or shape, the Wi-Fi communication module transmits a transmission signal to the position corresponding to the at least one piece of position information by a Wi-Fi communication method at a preset frequency and receives a reflection signal reflected from an object in response to the transmission signal, the processor acquires an input pattern of a gesture, face, or shape of the object by analyzing the reflection signal, and retrieves a registered pattern matching the input pattern from the at least one registered pattern, and the controller controls the component according to an instruction corresponding to the retrieved registered pattern.

This document describes Kurtosis based pruning for sensor-fusion systems. Kurtosis based pruning minimizes a total quantity of comparisons performed when fusing together large sets of data. Multiple candidate radar tracks may possibly align with one of multiple candidate visual tracks. For each candidate vision track, a weight or other evidence of matching is assigned to each candidate radar track. An inverse of matching errors between each candidate vision and each candidate radar track contributes to this evidence, which may be normalized to produce, for each candidate vision track, a distribution associated with all candidate radar tracks. A Kurtosis or shape of this distribution is calculated. Based on the Kurtosis values, some candidate radar tracks are selected for matching and other remaining candidate radar tracks are pruned. The Kurtosis aids in determining how many candidates to retain and how many to prune. In this way, Kurtosis based pruning can prevent combinatorial explosions due to large-scale matching.

A method is provided for offloading autonomous vehicle (AV) data to a download pole. The AV may include a transceiver. The download pole may include a transceiver. The method may include identifying, by the AV, the download pole in a parking spot that is close to the AV. The method may also include establishing short range wireless link between the AV and the download pole. The method may also include positioning the AV so that the transceiver of the AV is aligned with the transceiver of the download pole based on instructions received over the Bluetooth connection from the download pole. The method may further include establishing a first link between the transceiver of the AV and the transceiver of the download pole.

A method for assisting a vision of a driver includes: receiving a signal indicating that weather information is emergency weather information from a navigation device according to setting by a vehicle driver, and turning on a vision assisting device included in the vehicle in response to the signal; obtaining an image of an infrared thermal camera of the vision assisting device, which photographs a front of the vehicle when the vehicle travels, and obtaining an image of a camera of the vision assisting device, which photographs the front of the vehicle when the vehicle travels; controlling an image processor of the vision assisting device to determine whether a matching rate between image data of the infrared thermal camera and image data of the camera is equal to or less than a first threshold; and, when the matching rate is equal to or less than the first threshold, using distances between the vehicle and respective objects located at the front, a rear, and sides of the traveling vehicle, speeds of the respective objects, which are detected by a radar sensor of the vision assisting device, and the images of the infrared thermal camera photographing the front of the vehicle to generate a surrounding state image of the vehicle, which includes the distances and the speeds.

There is provided a portable electronic monitoring device for providing an in-vehicle user warning system about how a semi-autonomous vehicle is being driven autonomously during a driving period. The device is removably and securely mountable to the vehicle and comprises: a sensor set comprising at least one sensor for sensing an exterior environment outside of the vehicle and movement of the vehicle within the exterior environment, an interface for receiving user input commands and delivering a warning output; and a processor operatively connected to the sensor set and the interface; wherein the sensor set is configured to monitor the automatic operation of the semi-autonomous vehicle within the exterior environment during the driving period and to generate sensor data representing driving events concerning the automated driving behaviour of the vehicle with respect to the exterior environment occurring during the driving period. The processor is configured to: process the sensor data during the driving period to compare the detected automated driving behaviour of the vehicle in the external environment with a model of expected automated vehicle driving behaviour for a particular driving event; identify a dangerous driving event, if the detected automated driving behaviour deviates beyond a threshold from the expected automated vehicle driving behaviour; and if a dangerous driving event has been detected, generate a warning alert via the interface to alert the driver to the occurrence of the dangerous driving event.

A system and corresponding method for autonomous driving of a vehicle are provided. The system comprises at least one neural network (NN) that generates at least one output for controlling the autonomous driving. The system further comprises a main data path that routes bulk sensor data to the at least one NN and a low-latency data path with reduced latency relative to the main data path. The low-latency data path routes limited sensor data to the at least one NN which, in turn, employs the limited sensor data to improve performance of the at least one NN's processing of the bulk sensor data for generating the at least one output. Improving performance of the at least one NN's processing of the bulk sensor data enables the system to, for example, identify a safety hazard sooner, enabling the autonomous driving to divert the vehicle and avoid contact with the safety hazard.

A vehicle security method includes: acquiring an input signal from a sensor unit equipped in a vehicle; setting a detection mode to a heart rate detection mode, in response to a security release operation being started, setting a radar sensor of the sensor unit to detect a target, and detecting heart rate information on the target; determining whether the heart rate information matches pre-stored heart rate information; setting the detection mode to a general detection mode, in response to the heart rate information matching the pre-stored heart rate information, measuring a distance, an azimuth, and/or an elevation angle between the vehicle and the target, and detecting body shape information of the target; determining whether the body shape information matches pre-stored body shape information; and releasing a security of a security device, in response to the body shape information matching the pre-stored body shape information.