Intel Corporation

Uisee Technologies (beijing) Ltd

Uisee (shanghai) Automotive Technologies Ltd.

Xiaocheng Zhou

Shoumeng Yan

Sai Luo

Hu Tiger Chen

Ying Gao

Bratin Saha

Dan Zhang

Yan Jiang

Xin Zhou

Mohan Rajagopalan

Jinzhan Peng

Avi Mendelson

Peinan Zhang

Jesse Z Fang

Milind Baburao Girkar

Stephen Junkins

David M Putzolu

Tin-Fook Ngai

Robert Geva

Lomesh Agarwal

Xinyu Qi

Chunxiao Lin

Clark F Nelson

Ravi Narayanaswamy

Rajiv Deodhar

Kang Zhao

Patrick Xi

Tiger Chen

Haiyang Zhu

Hu Chen

A speed planning method and apparatus and a calculating apparatus for automatic driving of a vehicle. The method comprises: using a training sample set to perform machine learning to obtain a machine learning model; partitioning an input space, and obtaining a decision result corresponding to a determined partition based on the obtained machine learning model to form a partition decision table of each partition corresponding to the corresponding decision result; and obtaining each dimensional feature vector of a vehicle while driving in real time as an input feature, determining an input partition to which the input feature belongs, and querying the partition decision table based on the determined partition to obtain the corresponding decision result.

Speed planning method and apparatus and calculating apparatus for automatic driving of vehicle

The present disclosure provides for a steering control method and a steering control system for self-driving of a vehicle. The method comprises the steps of: obtaining information about an expected steering angle of a vehicle based on an automatic planning control operation; detecting whether an effective torque is applied to a steering wheel by a driver; and when it is detected that the driver has applied the effective torque to the steering wheel, computing a difference between a turning angle of the steering wheel controlled by the driver and the expected steering angle of a vehicle, and determining a self-driving intent prompt torque according to the difference between the two, wherein the self-driving intent prompt torque is to be applied to a steering system.

Steering control method and system of self-driving vehicle

An objective of the present application is to provide a road characterization method, comprising: acquiring a target road, wherein the target road comprises one or more road segments; determining one or more atomic lanes corresponding to the road segments according to the road segment attribute information of the road segments; and determining lane association information related to the atomic lanes corresponding to the target road; wherein the one or more atomic lanes and the lane association information are used for characterizing the target road. The method can functionally completely describe objective connections of lanes within a target area, including lane connectivity and lane change feasibility.

Road characterization method, method for displaying road information and devices

A processing device includes a processing core, coupled to a memory, to execute a task including a code segment identified as being monitored and a kernel recorder, coupled to the processing core via a core interface. The kernel recorder includes a first filter circuit to responsive to determining that the task being executed enters the code segment, set the kernel recorder to a first mode under which the kernel recorder is to record, in a first record, a plurality of memory addresses accessed by the code segment, and responsive to determining that the execution of the task exits the code segment, set the kernel recorder to a second mode under which the kernel recorder is to detect a write operation to a memory address recorded in the first record and record the memory address in a second record.

Multicore memory data recorder for kernel module

A speed planning method and apparatus and a calculating apparatus for automatic driving of a vehicle. The method comprises: using a training sample set to perform machine learning to obtain a machine learning model (S); partitioning an input space, and obtaining a decision result corresponding to a determined partition based on the obtained machine learning model to form a partition decision table of each partition corresponding to the corresponding decision result (S); and obtaining each dimensional feature vector of a vehicle while driving in real time as an input feature, determining an input partition to which the input feature belongs, and querying the partition decision table based on the determined partition to obtain the corresponding decision result (S). The present disclosure effectively solves the problem that a model trained by means of machine learning cannot be locally adjusted and easily modifies the decision of a certain partition without affecting the decision results of other partitions at all. The intuitive nature of a partition decision table can effectively help to find and solve problems in the machine learning process. The partition decision table can speed up the decision process.

A steering control method and a steering control system for self-driving of a vehicle are disclosed. The method comprises obtaining information about an expected steering angle of a vehicle based on an automatic planning control operation; detecting whether an effective torque is applied to a steering wheel by a driver; and when it is detected that the driver has applied the effective torque to the steering wheel, computing a difference between a turning angle of the steering wheel controlled by the driver and the expected steering angle of a vehicle, and determining a self-driving intent prompt torque according to the difference between the two, wherein the self-driving intent prompt torque is to be applied to a steering system.

A computer system may comprise a computer platform and input-output devices. The computer platform may include a plurality of heterogeneous processors comprising a central processing unit (CPU) and a graphics processing unit (GPU) and a shared virtual memory supported by a physical private memory space of at least one heterogeneous processor or a physical shared memory shared by the heterogeneous processor. The CPU (producer) may create shared multi-version data and store such shared multi-version data in the physical private memory space or the physical shared memory. The GPU (consumer) may acquire or access the shared multi-version data.

Sharing virtual memory-based multi-version data between the heterogeneous processors of a computer platform

Embodiments of the invention provide a programming model for CPU-GPU platforms. In particular, embodiments of the invention provide a uniform programming model for both integrated and discrete devices. The model also works uniformly for multiple GPU cards and hybrid GPU systems (discrete and integrated). This allows software vendors to write a single application stack and target it to all the different platforms. Additionally, embodiments of the invention provide a shared memory model between the CPU and GPU. Instead of sharing the entire virtual address space, only a part of the virtual address space needs to be shared. This allows efficient implementation in both discrete and integrated settings.

Shared virtual memory

Various embodiments are generally directed an apparatus and method for configuring an execution environment in a user space for device driver operations and redirecting a device driver operation for execution in the execution environment in the user space including copying instructions of the device driver operation from the kernel space to a user process in the user space. In addition, the redirected device driver operation may be executed in the execution environment in the user space.

Techniques for dynamically redirecting device driver operations to user space

An audio accelerator includes a decoder to decode first and second sets of data blocks, a processor to process the first and second sets of decoded data blocks, a storage area to store the first and second sets of processed data blocks, and a controller to generate interrupt signals for controlling operation of the decoder. The controller may control a rate at which data blocks are to be decoded by the decoder to reduce a time gap between outputting adjacent ones of the data blocks from the first and second sets in the storage area.

System and method for controlling audio data processing

Systems and methods may provide for using audio output device driver logic to maintain one or more states of an audio accelerator in a memory store, detect a suspend event, and deactivate the audio accelerator in response to the suspend event. In addition, firmware logic of the audio accelerator may be used to detect a resume event with respect to the audio output accelerator, and retrieve one or more states of the audio accelerator directly from the memory store in response to the resume. Thus, the retrieval of the one or more states can bypass the driver logic.

Lightweight power management of audio accelerators

Embodiments of the invention provide language support for CPU-GPU platforms. In one embodiment, code can be flexibly executed on both the CPU and GPU. CPU code can offload a kernel to the GPU. That kernel may in turn call preexisting libraries on the CPU, or make other calls into CPU functions. This allows an application to be built without requiring the entire call chain to be recompiled. Additionally, in one embodiment data may be shared seamlessly between CPU and GPU. This includes sharing objects that may have virtual functions. Embodiments thus ensure the right virtual function gets invoked on the CPU or the GPU if a virtual function is called by either the CPU or GPU.

Language level support for shared virtual memory

A computing platform may include heterogeneous processors (e.g., CPU and a GPU) to support sharing of virtual functions between such processors. In one embodiment, a CPU side vtable pointer used to access a shared object from the CPUmay be used to determine a GPU vtable if a GPU-side table exists. In other embodiment, a shared non-coherent region, which may not maintain data consistency, may be created within the shared virtual memory. The CPU and the GPU side data stored within the shared non-coherent region may have a same address as seen from the CPU and the GPU side. However, the contents of the CPU-side data may be different from that of GPU-side data as shared virtual memory may not maintain coherency during the run-time. In one embodiment, the vptr may be modified to point to the CPU vtable and GPU vtable stored in the shared virtual memory.

Growing community of inventors

Beijing, China

Xiaocheng Zhou