Learning controller for vehicle control
    1.
    发明申请
    Learning controller for vehicle control 有权
    车辆控制学习控制器

    公开(公告)号:US20070156294A1

    公开(公告)日:2007-07-05

    申请号:US11323697

    申请日:2005-12-30

    IPC分类号: G05D1/00

    摘要: A learning controller overcomes tuning problems in vehicle simulation programs by estimating requisite vehicle-specific parameters, effectively learning from its mistakes, as the vehicle is automatically driven around a track. After a sufficient period of calibration, the learned parameters are automatically saved to a car-specific file. The file parameters may be loaded in the controller in the future to optimally control a vehicle without the need to re-run the learning procedure.

    摘要翻译: 学习控制器通过估计必要的车辆特定参数来克服车辆模拟程序中的调谐问题,有效地从其错误中学习,因为车辆被自动地驱动在轨道周围。 经过足够的校准时间后,学习的参数将自动保存到汽车专用文件中。 文件参数可以在将来加载到控制器中以最佳地控制车辆,而不需要重新运行学习过程。

    Computing a target speed in a virtual racing environment
    2.
    发明申请
    Computing a target speed in a virtual racing environment 有权
    在虚拟赛车环境中计算目标速度

    公开(公告)号:US20070155458A1

    公开(公告)日:2007-07-05

    申请号:US11323951

    申请日:2005-12-30

    IPC分类号: A63F13/00

    摘要: A target speed profile for a specified racer is computed at various points along a track. The calculation is based on the real world physics of the racing environment and incorporates physical characteristics of the track, including curvature, undulation, and/or camber. A lateral acceleration component is developed to limit the realistic maximum speed a racer may obtain at any given point along the track. Furthermore, differences in realistic maximum speeds at different points along the track can overwhelm a racer's braking capability. As such, braking capacity adjustments can be applied to decrease the maximum speed in the target speed profile, so that the overall target speed profile is more realistic and attainable.

    摘要翻译: 在轨道的各个点计算指定赛车手的目标速度曲线。 该计算基于赛车环境的现实世界物理学,并结合轨道的物理特性,包括曲率,起伏和/或弯度。 开发横向加速度分量以限制赛车手沿着轨道的任何给定点获得的实际最大速度。 此外,沿着轨道的不同点的现实最大速度的差异可以压倒赛车的制动能力。 因此,可以应用制动能力调整来降低目标速度曲线中的最大速度,使得总体目标速度分布更加逼真和可实现。

    Speed-dependent suggested driving lines

    公开(公告)号:US09643086B2

    公开(公告)日:2017-05-09

    申请号:US12829342

    申请日:2010-07-01

    摘要: In a video game or simulator, suggested speed indicators are computed along a suggested driving line on a path (e.g., a race track) and displayed in a simple, progressive, and user-friendly format. The displayed speed indicators are based on a racer's current speed and target speeds attributed to individual locations along the suggested driving line on the path. The speed indicators provide a dynamic indication of where and how the player should slow down or speed up relative to their current speed as their racer travels along the path. The speed indicators are displayed (e.g., using color to represent different magnitudes of suggested acceleration and deceleration) along the suggested driving line in front of the racer so that the player can anticipate braking and acceleration actions as the path and the racer's speed change.

    Speed-dependent suggested driving lines
    4.
    发明授权
    Speed-dependent suggested driving lines 有权
    速度依赖建议的行车线

    公开(公告)号:US08425293B2

    公开(公告)日:2013-04-23

    申请号:US12943862

    申请日:2010-11-10

    IPC分类号: A63F13/00

    摘要: In a video game or simulator, suggested speed indicators are computed along a suggested driving line on a path (e.g., a race track) and displayed in a simple, progressive, and user-friendly format. The displayed speed indicators are based on a racer's current speed and target speeds attributed to individual locations along the suggested driving line on the path. The speed indicators provide a dynamic indication of where and how the player should slow down or speed up relative to their current speed as their racer travels along the path. The speed indicators are displayed (e.g., using color to represent different magnitudes of suggested acceleration and deceleration) along the suggested driving line in front of the racer so that the player can anticipate braking and acceleration actions as the path and the racer's speed change.

    摘要翻译: 在视频游戏或模拟器中,沿着路径(例如,赛道)上的建议行驶线计算建议的速度指示符,并以简单,渐进和用户友好的格式显示。 所显示的速度指示符是基于赛车目前的速度和目标速度归因于沿着该路径上建议的行车路线的各个位置。 速度指示器提供了一个动态指示,当赛车手沿着路径行进时,玩家应该如何减速或相对于目前的速度加速。 显示速度指示符(例如,使用颜色表示不同幅度的建议的加速和减速)沿着赛车前面的建议行驶线,使得玩家可以预期制动和加速动作作为路径和赛车速度的变化。

    Learning controller for vehicle control
    5.
    发明授权
    Learning controller for vehicle control 有权
    车辆控制学习控制器

    公开(公告)号:US07953521B2

    公开(公告)日:2011-05-31

    申请号:US11323697

    申请日:2005-12-30

    IPC分类号: G06F15/18

    摘要: A learning controller overcomes tuning problems in vehicle simulation programs by estimating requisite vehicle-specific parameters, effectively learning from its mistakes, as the vehicle is automatically driven around a track. After a sufficient period of calibration, the learned parameters are automatically saved to a car-specific file. The file parameters may be loaded in the controller in the future to optimally control a vehicle without the need to re-run the learning procedure.

    摘要翻译: 学习控制器通过估计必要的车辆特定参数来克服车辆模拟程序中的调谐问题,有效地从其错误中学习,因为车辆被自动地驱动在轨道周围。 经过足够的校准时间后,学习的参数将自动保存到汽车专用文件中。 文件参数可以在将来加载到控制器中以最佳地控制车辆,而不需要重新运行学习过程。

    SPEED-DEPENDENT SUGGESTED DRIVING LINES

    公开(公告)号:US20110059783A1

    公开(公告)日:2011-03-10

    申请号:US12943862

    申请日:2010-11-10

    IPC分类号: A63F13/00 A63F9/24

    摘要: In a video game or simulator, suggested speed indicators are computed along a suggested driving line on a path (e.g., a race track) and displayed in a simple, progressive, and user-friendly format. The displayed speed indicators are based on a racer's current speed and target speeds attributed to individual locations along the suggested driving line on the path. The speed indicators provide a dynamic indication of where and how the player should slow down or speed up relative to their current speed as their racer travels along the path. The speed indicators are displayed (e.g., using color to represent different magnitudes of suggested acceleration and deceleration) along the suggested driving line in front of the racer so that the player can anticipate braking and acceleration actions as the path and the racer's speed change.

    Speed-dependent suggested driving lines

    公开(公告)号:US07749057B2

    公开(公告)日:2010-07-06

    申请号:US12260102

    申请日:2008-10-29

    IPC分类号: A63F13/00

    摘要: In a video game or simulator, suggested speed indicators are computed along a suggested driving line on a path (e.g., a race track) and displayed in a simple, progressive, and user-friendly format. The displayed speed indicators are based on a racer's current speed and target speeds attributed to individual locations along the suggested driving line on the path. The speed indicators provide a dynamic indication of where and how the player should slow down or speed up relative to their current speed as their racer travels along the path. The speed indicators are displayed (e.g., using color to represent different magnitudes of suggested acceleration and deceleration) along the suggested driving line in front of the racer so that the player can anticipate braking and acceleration actions as the path and the racer's speed change.

    Speed-dependent suggested driving lines

    公开(公告)号:US07837544B2

    公开(公告)日:2010-11-23

    申请号:US12710202

    申请日:2010-02-22

    IPC分类号: A63F13/00

    摘要: In a video game or simulator, suggested speed indicators are computed along a suggested driving line on a path (e.g., a race track) and displayed in a simple, progressive, and user-friendly format. The displayed speed indicators are based on a racer's current speed and target speeds attributed to individual locations along the suggested driving line on the path. The speed indicators provide a dynamic indication of where and how the player should slow down or speed up relative to their current speed as their racer travels along the path. The speed indicators are displayed (e.g., using color to represent different magnitudes of suggested acceleration and deceleration) along the suggested driving line in front of the racer so that the player can anticipate braking and acceleration actions as the path and the racer's speed change.

    Racing line optimization
    9.
    发明申请
    Racing line optimization 有权
    赛车线优化

    公开(公告)号:US20070156327A1

    公开(公告)日:2007-07-05

    申请号:US11322527

    申请日:2005-12-30

    IPC分类号: G01C21/00

    摘要: An automatic agorithm for finding racing lines via computerized minimization of a measure of the curvature of a racing line is derived. Maximum sustainable speed of a car on a track is shown to be inversely proportional to the curvature of the line it is attempting to follow. Low curvature allows for higher speed given that a car has some maximum lateral traction when cornering. The racing line can also be constrained, or “pinned,” at arbitrary points on the track. Pinning may be randomly, deterministically, or manually and allows, for example, a line designer to pin the line at any chosen points on the track, such that when the automatic algorithm is run, it will produce the smoothest line that still passes through all the specified pins.

    摘要翻译: 导出通过计算机化最小化赛车线的曲率的度量来找到赛车线的自动算法。 轨道上汽车的最大可持续速度显示为与其试图跟随的线的曲率成反比。 由于在转弯时汽车具有一定的最大横向牵引力,所以低曲率允许更高的速度。 赛道也可以在轨道上的任意点受到限制或“固定”。 固定可以是随机的,确定的或手动的,并且允许例如线设计者在轨道上的任何选定点处固定线,使得当运行自动算法时,它将产生仍然通过所有的最平滑的线 指定的引脚。

    Variational relevance vector machine
    10.
    发明授权
    Variational relevance vector machine 有权
    变分相关向量机

    公开(公告)号:US06879944B1

    公开(公告)日:2005-04-12

    申请号:US09520678

    申请日:2000-03-07

    CPC分类号: G06N7/005 G06K9/6269

    摘要: A variational Relevance Vector Machine (RVM) is disclosed. The RVM is a probabilistic basis model. Sparsity is achieved through a Bayesian treatment, where a prior is introduced over the weights governed by a set of what are referred to as hyperparameters—one such hyperparameter associated with each weight. An approximation to the joint posterior distribution over weights and hyperparameters is iteratively estimated from the data. The posterior distribution of many of the weights is sharply peaked around zero, in practice. The variational RVM utilizes a variational approach to solve the model, in particular using product approximations to obtain the posterior distribution.

    摘要翻译: 公开了变分相关性向量机(RVM)。 RVM是概率基础模型。 通过贝叶斯治疗实现稀疏性,其中先前被引入由称为超参数的集合所控制的权重 - 与每个权重相关联的一个这样的超参数。 从数据中迭代地估计了权重和超参数之间的联合后验分布的近似。 在实践中,许多重量的后验分布在零附近急剧高峰。 变分RVM利用变分方法来解决模型,特别是使用产品近似来获得后验分布。