GM Cruise Holdings Patente

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Various technologies described herein pertain to systems and methods for increasing radar resolution by, for example, combining radar information. In one embodiment, beamforming is performed using radar units that are individually coherent but collectively do not need to be coherent. Each radar transmits and receives its own signal to process and generate target information including beamforming information and/or virtual receiver channel information. The target information from each radar is then merged or summed into a combined beamforming based on all the target information received from all the radar units. When the radar units used in this manner are separated by a distance, the resulting beamforming information is representative of an aperture/resolution based on the total space or distance between the radar units. Thus, having an improved resolution, benefits such as improved target resolution (e.g., size, position, and detection) can be achieved.

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Autonomous vehicles (AVs) utilize perception and understanding of objects on the road to predict behaviors of the objects, and to plan a trajectory for the vehicle. In some scenarios, an AV may benefit from having information about an object that is not within a perceivable area of the sensors of the AV. Another AV in the area that has the object within a perceivable area of the sensors of the other AV may share information with the AV. Rich information about the object determined by the other AV can be compressed using an encoder and transferred efficiently to the AV for inclusion in a temporal map that combines locally determined object information and transferred object information determined by other AV(s). The temporal map may be used in one or more parts of the software stack of the AV.

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Technologies related to a sensor testing system are described herein, where the sensor testing system includes a moveable arm that has a reception region. A sensor device is removably coupleable to the moveable arm at the reception region. A performance test is conducted on the sensor device by moving the moveable arm and evaluating measurements output by the sensor device. A leakage test is performed on the sensor device by evacuating fluid from an interior of the sensor device while the sensor device is coupled to the moveable arm.

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

A low phase noise radar system is disclosed. The system has a signal generator having a stable oscillator that outputs a first lower-frequency signal, a direct digital synthesis circuit that outputs an analog waveform, and a mixer to receive the first lower-frequency signal, and the analog waveform, the mixer to mix the first lower-frequency signal and the analog waveform to generate a signal generator output signal. The system further includes an up converter coupled with the signal generator to filter and to increase frequencies of the signal generator output signal to generate a filtered and frequency multiplied signal to be transmitted.

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Autonomous vehicles utilize perception to identify objects in a vehicle's surrounding environment, and to plan a trajectory. In perceiving an AV's surroundings, an object detection model uses sensor data from various AV sensors to detect objects in the AV surroundings. An object detection model can be trained to detect objects using training datasets having sensor data and ground truth objects. In training, the object detection model uses the sensor data to identify objects in the locations of the ground truth objects. However, sometimes there is little or no sensor data corresponding to the ground truth objects, and the model is not able to learn patterns in sensor data to correctly detect the objects. Systems and methods are provided herein for removing ground truth objects that do not have sufficient corresponding sensor data from the training dataset, thereby preventing these objects from dominating the loss and interfering with the model learning useful patterns.

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

A computer vision module facilitates multi-sensor vision of AVs based on privileged information learning. The module may input first sensor data captured by a first sensor into an already-trained privileged model, input second sensor data captured by a second sensor into a first backbone of a target model, and input third sensor data captured by a third sensor into a second backbone of the target model. The three sensors may be of different types. To train the target model, internal parameters of the target model may be modified to minimize a loss, which may include a privilege loss, which indicates a difference between a latent representation of the first sensor data and a latent representation of the second sensor data, and another privileged loss, which indicates a difference between the latent representation of the first sensor data and a latent representation of the third sensor data.

A method includes dividing an image into a plurality of patches; generating for the patches image tokens each including a halting score associated with the image token; generating a contextual features token representative of at least one contextual feature in connection with the image; processing the image tokens and the contextual features token using a vision transformer block; performing adaptive halting on the image tokens output from the transformer block, the adaptive halting comprising updating the halting scores associated with the image tokens and discarding ones of the image tokens having halting scores greater than or equal to a predetermined threshold score, wherein the non-discarded image tokens comprise remaining image tokens; and forwarding the remaining image tokens to a next processing block.

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …