学习Python实现自动驾驶系统

pip install gym

pip install --user git+https://github.com/eleurent/highway-env

import gymimport highway_env%matplotlib inlineenv = gym.make('highway-v0')env.reset()for _ in range(3):action = env.action_type.actions_indexes["IDLE"]obs, reward, done, info = env.step(action)env.render()

config = {"observation": {"type": "Kinematics",#选取5辆车进行观察（包括ego vehicle）"vehicles_count": 5,#共7个特征"features": ["presence", "x", "y", "vx", "vy", "cos_h", "sin_h"],"features_range":{"x": [-100, 100],"y": [-100, 100],"vx": [-20, 20],"vy": [-20, 20]},"absolute": False,"order": "sorted"},"simulation_frequency": 8,# [Hz]"policy_frequency": 2,# [Hz]}

ACTIONS_ALL = {0: 'LANE_LEFT',1: 'IDLE',2: 'LANE_RIGHT',3: 'FASTER',4: 'SLOWER'}

import torchimport torch.nn as nnfrom torch.autograd import Variableimport torch.nn.functional as Fimport torch.optim as optimimport torchvision.transforms as Tfrom torch import FloatTensor, LongTensor, ByteTensorfrom collections import namedtupleimport randomTensor = FloatTensorEPSILON = 0# epsilon used for epsilon greedy approachGAMMA = 0.9TARGET_NETWORK_REPLACE_FREQ = 40 # How frequently target netowrk updatesMEMORY_CAPACITY = 100BATCH_SIZE = 80LR = 0.01 # learning rateclass DQNNet(nn.Module):def __init__(self):super(DQNNet,self).__init__()self.linear1 = nn.Linear(35,35)self.linear2 = nn.Linear(35,5)def forward(self,s):s=torch.FloatTensor(s)s = s.view(s.size(0),1,35)s = self.linear1(s)s = self.linear2(s)return sclass DQN(object):def __init__(self):self.net,self.target_net = DQNNet(),DQNNet()self.learn_step_counter = 0self.memory = []self.position = 0self.capacity = MEMORY_CAPACITYself.optimizer = torch.optim.Adam(self.net.parameters(), lr=LR)self.loss_func = nn.MSELoss()def choose_action(self,s,e):x=np.expand_dims(s, axis=0)if np.random.uniform() <h4>3、运行结果</h4><p>各个部分都完成之后就可以组合在一起训练模型了，流程和用CARLA差不多，就不细说了。</p><p>初始化环境（DQN的类加进去就行了）：</p><pre class="brush:python;toolbar:false;">import gymimport highway_envfrom matplotlib import pyplot as pltimport numpy as npimport timeconfig = {"observation": {"type": "Kinematics","vehicles_count": 5,"features": ["presence", "x", "y", "vx", "vy", "cos_h", "sin_h"],"features_range":{"x": [-100, 100],"y": [-100, 100],"vx": [-20, 20],"vy": [-20, 20]},"absolute": False,"order": "sorted"},"simulation_frequency": 8,# [Hz]"policy_frequency": 2,# [Hz]}env = gym.make("highway-v0")env.configure(config)

dqn=DQN()count=0reward=[]avg_reward=0all_reward=[]time_=[]all_time=[]collision_his=[]all_collision=[]while True:done = Falsestart_time=time.time()s = env.reset()while not done:e = np.exp(-count/300)#随机选择action的概率，随着训练次数增多逐渐降低a = dqn.choose_action(s,e)s_, r, done, info = env.step(a)env.render()dqn.push_memory(s, a, r, s_)if ((dqn.position !=0)&(dqn.position % 99==0)):loss_=dqn.learn()count+=1print('trained times:',count)if (count%40==0):avg_reward=np.mean(reward)avg_time=np.mean(time_)collision_rate=np.mean(collision_his)all_reward.append(avg_reward)all_time.append(avg_time)all_collision.append(collision_rate)plt.plot(all_reward)plt.show()plt.plot(all_time)plt.show()plt.plot(all_collision)plt.show()reward=[]time_=[]collision_his=[]s = s_reward.append(r)end_time=time.time()episode_time=end_time-start_timetime_.append(episode_time)is_collision=1 if info['crashed']==True else 0collision_his.append(is_collision)