In the previous quizzes, you designed a cost function to choose a lane when trying to reach a goal in highway driving:

cost=1−e​−​​∣Δd∣​​​​/​Δs

Here, Δ was the lateral distance between the goal lane and the final chosen lane, and Δ was the longitudinal distance from the vehicle to the goal.

In this quiz, we'd like you to implement the cost function in C++, but with one important change. The finite state machine we use for vehicle behavior also includes states for planning a lane change right or left (PLCR or PLCL), and the cost function should incorporate this information. We will provide the following four inputs to the function:

  • Intended lane: the intended lane for the given behavior. For PLCR, PLCL, LCR, and LCL, this would be the one lane over from the current lane.
  • Final lane: the immediate resulting lane of the given behavior. For LCR and LCL, this would be one lane over.
  • The Δs distance to the goal.
  • The goal lane.

Your task in the implementation will be to modify Δd in the equation above so that it satisifes:

  • Δd is smaller as both intended lane and final lane are closer to the goal lane.
  • The cost function provides different costs for each possible behavior: KL, PLCR/PLCL, LCR/LCL.
  • The values produced by the cost function are in the range 0 to 1.

You can implement your solution in cost.cpp below.

cost.cpp

  1. float goal_distance_cost(int goal_lane, int intended_lane, int final_lane, float distance_to_goal) {
  2. /*
  3. The cost increases with both the distance of intended lane from the goal
  4. and the distance of the final lane from the goal. The cost of being out of the
  5. goal lane also becomes larger as vehicle approaches the goal.
  6. */
  7. int delta_d = 2.0*goal_lane - intended_lane - final_lane;
  8. float cost = - exp(-(abs(delta_d) / distance_to_goal));
  9. return cost;
  10. }

behavior planning——13. implement a cost function in C++的更多相关文章

  1. behavior planning——14.implement a cost function in C++

    n most situations, a single cost function will not be sufficient to produce complex vehicle behavior ...

  2. behavior planning——11 create a cost function speed penalty

    A  key part of getting transitions to happen when we want  them to is the design of reasonable cost ...

  3. behavior planning——15.cost function design weightTweaking

    Designing cost functions is difficult and getting them all to cooperate to produce reasionable vehic ...

  4. behavior planning——12.example cost funtion -lane change penalty

      In the image above, the blue self driving car (bottom left) is trying to get to the goal (gold sta ...

  5. machine learning(11) -- classification: advanced optimization 去求cost function最小值的方法

    其它的比gradient descent快, 在某些场合得到广泛应用的求cost function的最小值的方法 when have a large machine learning problem, ...

  6. behavior planning——10 behaior planning pseudocode

    One way to implement a transition function is by generating rough trajectories for each accessible & ...

  7. loss function与cost function

    实际上,代价函数(cost function)和损失函数(loss function 亦称为 error function)是同义的.它们都是事先定义一个假设函数(hypothesis),通过训练集由 ...

  8. 【caffe】loss function、cost function和error

    @tags: caffe 机器学习 在机器学习(暂时限定有监督学习)中,常见的算法大都可以划分为两个部分来理解它 一个是它的Hypothesis function,也就是你用一个函数f,来拟合任意一个 ...

  9. 逻辑回归损失函数(cost function)

    逻辑回归模型预估的是样本属于某个分类的概率,其损失函数(Cost Function)可以像线型回归那样,以均方差来表示:也可以用对数.概率等方法.损失函数本质上是衡量”模型预估值“到“实际值”的距离, ...

随机推荐

  1. POJ 3628 Bookshelf 2【背包型DFS/选or不选】

    Bookshelf 2 Time Limit: 1000MS   Memory Limit: 65536K Total Submissions: 11105   Accepted: 4928 Desc ...

  2. 问题解决:在js中绑定onclick事件为什么不加括号,在html代码中必须要加?(转载)

    <!DOCTYPE html> <html lang="en"> <head> <meta charset="UTF-8&quo ...

  3. 对于MD5加密处理方式

    来源:http://blog.51cto.com/xqtesting/1924977 但有时候我们请求的参数可能需要加密,比如登录接口中的密码可能需要经过md5加密这时候怎么处理呢? 这种方法比较简单 ...

  4. Winform实现调用asp.net数据接口实例

    本文实例讲述了Winform实现调用asp.net数据接口的方法,分享给大家供大家参考.具体实现方法如下: 一.问题: 最近一个WPF项目需要改写成android项目,思路是在asp.net项目中编写 ...

  5. MyEclipse编写ExtJS卡死问题解决方法

    MyEclipse 8.6  在 jsp 中编写 ExtJS时,会出现卡死现象,让人甚是头疼.网上找了很多方法,折腾半天,还是不管用. 什么MyEclipse 优化,Validation 取消,MyE ...

  6. django的admin后台管理

    Admin后台管理 要进入admin后台管理首先要创建管理员账户 createsuperuser 其中密码要大于8位 使用之前要到应用下的admin.py中注册要管理的模型表 from django. ...

  7. vue移动端项目

    用vue mint-ui  jquery-weui写了一个移动端demo 技术栈 vue2.0 vue-router axios mint-ui jquery-weui webpack 页面截图 最后 ...

  8. golang中特殊的标识符

    你会发现在 Go 代码中的几乎所有东西都有一个名称或标识符.另外,Go 语言也是区分大小写的,这与 C 家族中的其它语言相同.有效的标识符必须以字符(可以使用任何 UTF-8 编码的字符或 _)开头, ...

  9. 春蔚专访--MaxCompute 与 Calcite 的技术和故事

    摘要:2019大数据技术公开课第一季<技术人生专访>,来自阿里云计算平台事业部高级开发工程师雷春蔚向大家讲述了MaxCompute 与 Calcite 的技术和故事. 具体内容包括: 1) ...

  10. JavaScript-- 函数既是函数又是对象

    <!DOCTYPE html> <html lang="en"> <head> <meta charset="UTF-8&quo ...