#!/usr/bin/env python # -*- coding: utf-8 -*- ################################################################## # # Copyright (c) 2023 CICV, Inc. All Rights Reserved # ################################################################## """ @Authors: zhanghaiwen(zhanghaiwen@china-icv.cn), yangzihao(yangzihao@china-icv.cn) @Data: 2023/06/25 @Last Modified: 2023/06/25 @Summary: Comfort metrics """ import os import sys import math import pandas as pd import numpy as np import scipy.signal sys.path.append('../common') sys.path.append('../modules') sys.path.append('../results') from data_info import DataInfoList from score_weight import cal_score_with_priority, cal_weight_from_80 from common import get_interpolation, score_grade, string_concatenate, replace_key_with_value, _cal_max_min_avg import matplotlib.pyplot as plt def peak_valley_decorator(method): def wrapper(self, *args, **kwargs): peak_valley = self._peak_valley_determination(self.df) pv_list = self.df.loc[peak_valley, ['simTime', 'speedH']].values.tolist() if len(pv_list) != 0: flag = True p_last = pv_list[0] for i in range(1, len(pv_list)): p_curr = pv_list[i] if self._peak_valley_judgment(p_last, p_curr): # method(self, p_curr, p_last) method(self, p_curr, p_last, flag, *args, **kwargs) else: p_last = p_curr return method else: flag = False p_curr = [0, 0] p_last = [0, 0] method(self, p_curr, p_last, flag, *args, **kwargs) return method return wrapper class Comfort(object): """ Class for achieving comfort metrics for autonomous driving. Attributes: dataframe: Vehicle driving data, stored in dataframe format. """ def __init__(self, data_processed, scoreModel, resultPath): self.eval_data = pd.DataFrame() self.data_processed = data_processed self.scoreModel = scoreModel self.resultPath = resultPath # self.data = data_processed.obj_data[1] self.data = data_processed.ego_df self.mileage = data_processed.report_info['mileage'] self.ego_df = pd.DataFrame() # self.discomfort_df = pd.DataFrame(columns=['start_time', 'end_time', 'start_frame', 'end_frame', 'type']) self.config = data_processed.config comfort_config = data_processed.comfort_config self.comfort_config = comfort_config # common data self.bulitin_metric_list = self.config.builtinMetricList # dimension data self.weight_custom = comfort_config['weightCustom'] self.metric_list = comfort_config['metric'] self.type_list = comfort_config['type'] self.type_name_dict = comfort_config['typeName'] self.name_dict = comfort_config['name'] self.unit_dict = comfort_config['unit'] # custom metric data # self.customMetricParam = comfort_config['customMetricParam'] # self.custom_metric_list = list(self.customMetricParam.keys()) # self.custom_data = custom_data # self.custom_param_dict = {} # score data self.weight = comfort_config['weightDimension'] self.weight_type_dict = comfort_config['typeWeight'] self.weight_type_list = comfort_config['typeWeightList'] self.weight_dict = comfort_config['weight'] self.weight_list = comfort_config['weightList'] self.priority_dict = comfort_config['priority'] self.priority_list = comfort_config['priorityList'] self.kind_dict = comfort_config['kind'] self.optimal_dict = comfort_config['optimal'] # self.optimal1_dict = self.optimal_dict[0] # self.optimal2_dict = self.optimal_dict[1] # self.optimal3_dict = self.optimal_dict[2] self.multiple_dict = comfort_config['multiple'] self.kind_list = comfort_config['kindList'] self.optimal_list = comfort_config['optimalList'] self.multiple_list = comfort_config['multipleList'] # metric data self.metric_dict = comfort_config['typeMetricDict'] self.lat_metric_list = self.metric_dict['comfortLat'] self.lon_metric_list = self.metric_dict['comfortLon'] # self.lat_metric_list = ["zigzag", "shake"] # self.lon_metric_list = ["cadence", "slamBrake", "slamAccelerate"] self.time_list = data_processed.driver_ctrl_data['time_list'] self.frame_list = data_processed.driver_ctrl_data['frame_list'] self.speed_list = [] self.commandSpeed_list = [] self.accel_list = [] self.accelH_list = [] self.linear_accel_dict = dict() self.angular_accel_dict = dict() self.speed_instruction_dict = dict() self.count_dict = {} self.duration_dict = {} self.strength_dict = {} self.discomfort_count = 0 self.zigzag_count = 0 # self.shake_count = 0 self.cadence_count = 0 self.slam_brake_count = 0 self.slam_accel_count = 0 self.speed_instruction_jump_count = 0 # self.zigzag_strength = 0 # self.shake_strength = 0 # self.cadence_strength = 0 # self.slam_brake_strength = 0 # self.slam_accel_strength = 0 # self.discomfort_duration = 0 # self.zigzag_duration = 0 # self.shake_duration = 0 # self.cadence_duration = 0 # self.slam_brake_duration = 0 # self.slam_accel_duration = 0 self.zigzag_time_list = [] # self.zigzag_frame_list = [] self.zigzag_stre_list = [] self.cur_ego_path_list = [] self.curvature_list = [] self._get_data() self._comf_param_cal() def _get_data(self): """ """ comfort_info_list = DataInfoList.COMFORT_INFO self.ego_df = self.data[comfort_info_list].copy() # self.df = self.ego_df.set_index('simFrame') # 索引是csv原索引 self.df = self.ego_df.reset_index(drop=True) # 索引是csv原索引 def _cal_cur_ego_path(self, row): try: divide = (row['speedX'] ** 2 + row['speedY'] ** 2) ** (3 / 2) if not divide: res = None else: res = (row['speedX'] * row['accelY'] - row['speedY'] * row['accelX']) / divide except: res = None return res def _comf_param_cal(self): """ """ # for i in range(len(self.optimal_list)): # if i % 3 == 2: # continue # else: # self.optimal_list[i] = round(self.optimal_list[i] * self.mileage / 100000, 8) # self.optimal_list = [round(self.optimal_list[i] * self.mileage / 100000, 8) for i in range(len(self.optimal_list))] self.optimal_dict = {key: value * self.mileage / 100000 for key, value in self.optimal_dict.copy().items()} # self.optimal1_dict = {key: value * self.mileage / 100000 for key, value in self.optimal1_dict.copy().items()} # self.optimal2_dict = {key: value * self.mileage / 100000 for key, value in self.optimal2_dict.copy().items()} # [log] self.ego_df['ip_acc'] = self.ego_df['v'].apply(get_interpolation, point1=[18, 4], point2=[72, 2]) self.ego_df['ip_dec'] = self.ego_df['v'].apply(get_interpolation, point1=[18, -5], point2=[72, -3.5]) self.ego_df['slam_brake'] = self.ego_df.apply( lambda row: self._slam_brake_process(row['lon_acc'], row['ip_dec']), axis=1) self.ego_df['slam_accel'] = self.ego_df.apply( lambda row: self._slam_accelerate_process(row['lon_acc'], row['ip_acc']), axis=1) self.ego_df['cadence'] = self.ego_df.apply( lambda row: self._cadence_process_new(row['lon_acc'], row['ip_acc'], row['ip_dec']), axis=1) self.speed_list = self.ego_df['v'].values.tolist() self.commandSpeed_list = self.ego_df['cmd_lon_v'].values.tolist() self.accel_list = self.ego_df['accel'].values.tolist() self.accelH_list = self.ego_df['accelH'].values.tolist() v_jump_threshold = 0.5 self.ego_df['cmd_lon_v_diff'] = self.ego_df['cmd_lon_v'].diff() self.ego_df['cmd_v_jump'] = (abs(self.ego_df['cmd_lon_v_diff']) > v_jump_threshold).astype(int) self.linear_accel_dict = _cal_max_min_avg(self.ego_df['accel'].dropna().values.tolist()) self.angular_accel_dict = _cal_max_min_avg(self.ego_df['accelH'].dropna().values.tolist()) self.speed_instruction_dict = _cal_max_min_avg(self.ego_df['cmd_lon_v_diff'].dropna().values.tolist()) def _peak_valley_determination(self, df): """ Determine the peak and valley of the vehicle based on its current angular velocity. Parameters: df: Dataframe containing the vehicle angular velocity. Returns: peak_valley: List of indices representing peaks and valleys. """ peaks, _ = scipy.signal.find_peaks(df['speedH'], height=0.01, distance=1, prominence=0.01) valleys, _ = scipy.signal.find_peaks(-df['speedH'], height=0.01, distance=1, prominence=0.01) peak_valley = sorted(list(peaks) + list(valleys)) return peak_valley def _peak_valley_judgment(self, p_last, p_curr, tw=6000, avg=0.4): """ Determine if the given peaks and valleys satisfy certain conditions. Parameters: p_last: Previous peak or valley data point. p_curr: Current peak or valley data point. tw: Threshold time difference between peaks and valleys. avg: Angular velocity gap threshold. Returns: Boolean indicating whether the conditions are satisfied. """ t_diff = p_curr[0] - p_last[0] v_diff = abs(p_curr[1] - p_last[1]) s = p_curr[1] * p_last[1] zigzag_flag = t_diff < tw and v_diff > avg and s < 0 if zigzag_flag and ([p_last[0], p_curr[0]] not in self.zigzag_time_list): self.zigzag_time_list.append([p_last[0], p_curr[0]]) return zigzag_flag @peak_valley_decorator def zigzag_count_func(self, p_curr, p_last, flag=True): """ Count the number of zigzag movements. Parameters: df: Input dataframe data. Returns: zigzag_count: Number of zigzag movements. """ if flag: self.zigzag_count += 1 else: self.zigzag_count += 0 @peak_valley_decorator def cal_zigzag_strength_strength(self, p_curr, p_last, flag=True): """ Calculate various strength statistics. Returns: Tuple containing maximum strength, minimum strength, average strength, and 99th percentile strength. """ if flag: v_diff = abs(p_curr[1] - p_last[1]) t_diff = p_curr[0] - p_last[0] self.zigzag_stre_list.append(v_diff / t_diff) # 平均角加速度 else: self.zigzag_stre_list = [] def _cadence_process(self, lon_acc_roc, ip_dec_roc): if abs(lon_acc_roc) >= abs(ip_dec_roc) or abs(lon_acc_roc) < 1: return np.nan # elif abs(lon_acc_roc) == 0: elif abs(lon_acc_roc) == 0: return 0 elif lon_acc_roc > 0 and lon_acc_roc < -ip_dec_roc: return 1 elif lon_acc_roc < 0 and lon_acc_roc > ip_dec_roc: return -1 def _slam_brake_process(self, lon_acc, ip_dec): if lon_acc - ip_dec < 0: return 1 else: return 0 def _slam_accelerate_process(self, lon_acc, ip_acc): if lon_acc - ip_acc > 0: return 1 else: return 0 def _cadence_process_new(self, lon_acc, ip_acc, ip_dec): if abs(lon_acc) < 1 or lon_acc > ip_acc or lon_acc < ip_dec: return np.nan # elif abs(lon_acc_roc) == 0: elif abs(lon_acc) == 0: return 0 elif lon_acc > 0 and lon_acc < ip_acc: return 1 elif lon_acc < 0 and lon_acc > ip_dec: return -1 def _cadence_detector(self): """ # 加速度突变：先加后减，先减后加，先加然后停，先减然后停 # 顿挫：2s内多次加速度变化率突变 # 求出每一个特征点，然后提取，然后将每一个特征点后面的2s做一个窗口，统计频率，避免无效运算 # 将特征点筛选出来 # 将特征点时间作为聚类标准，大于1s的pass，小于等于1s的聚类到一个分组 # 去掉小于3个特征点的分组 """ # data = self.ego_df[['simTime', 'simFrame', 'lon_acc_roc', 'cadence']].copy() data = self.ego_df[['simTime', 'simFrame', 'lon_acc', 'lon_acc_roc', 'cadence']].copy() time_list = data['simTime'].values.tolist() data = data[data['cadence'] != np.nan] data['cadence_diff'] = data['cadence'].diff() data.dropna(subset='cadence_diff', inplace=True) data = data[data['cadence_diff'] != 0] t_list = data['simTime'].values.tolist() f_list = data['simFrame'].values.tolist() group_time = [] group_frame = [] sub_group_time = [] sub_group_frame = [] for i in range(len(f_list)): if not sub_group_time or t_list[i] - t_list[i - 1] <= 1: # 特征点相邻一秒内的，算作同一组顿挫 sub_group_time.append(t_list[i]) sub_group_frame.append(f_list[i]) else: group_time.append(sub_group_time) group_frame.append(sub_group_frame) sub_group_time = [t_list[i]] sub_group_frame = [f_list[i]] group_time.append(sub_group_time) group_frame.append(sub_group_frame) group_time = [g for g in group_time if len(g) >= 1] # 有一次特征点则算作一次顿挫 # group_frame = [g for g in group_frame if len(g) >= 1] # 输出图表值 cadence_time = [[g[0], g[-1]] for g in group_time] # cadence_frame = [[g[0], g[-1]] for g in group_frame] # 将顿挫组的起始时间为组重新统计时间 cadence_time_list = [time for pair in cadence_time for time in time_list if pair[0] <= time <= pair[1]] # stre_list = [] freq_list = [] for g in group_time: # calculate strength g_df = data[data['simTime'].isin(g)] # strength = g_df['lon_acc'].abs().mean() # stre_list.append(strength) # calculate frequency cnt = len(g) t_start = g_df['simTime'].iloc[0] t_end = g_df['simTime'].iloc[-1] t_delta = t_end - t_start frequency = cnt / t_delta freq_list.append(frequency) self.cadence_count = len(freq_list) # cadence_stre = sum(stre_list) / len(stre_list) if stre_list else 0 return cadence_time_list def _slam_brake_detector(self): # 统计急刹全为1的分段的个数，记录分段开头的frame_ID # data = self.ego_df[['simTime', 'simFrame', 'lon_acc_roc', 'ip_dec_roc', 'slam_brake']].copy() data = self.ego_df[['simTime', 'simFrame', 'lon_acc', 'lon_acc_roc', 'ip_dec', 'slam_brake']].copy() # data['slam_diff'] = data['slam_brake'].diff() # res_df = data[data['slam_diff'] == 1] res_df = data[data['slam_brake'] == 1] t_list = res_df['simTime'].values f_list = res_df['simFrame'].values.tolist() group_time = [] group_frame = [] sub_group_time = [] sub_group_frame = [] for i in range(len(f_list)): if not sub_group_time or f_list[i] - f_list[i - 1] <= 1: # 连续帧的算作同一组急刹 sub_group_time.append(t_list[i]) sub_group_frame.append(f_list[i]) else: group_time.append(sub_group_time) group_frame.append(sub_group_frame) sub_group_time = [t_list[i]] sub_group_frame = [f_list[i]] group_time.append(sub_group_time) group_frame.append(sub_group_frame) group_time = [g for g in group_time if len(g) >= 2] # 达到两帧算作一次急刹 # group_frame = [g for g in group_frame if len(g) >= 2] time_list = [element for sublist in group_time for element in sublist] self.slam_brake_count = len(group_time) # / self.mileage # * 1000000 return time_list def _slam_accel_detector(self): # 统计急刹全为1的分段的个数，记录分段开头的frame_ID # data = self.ego_df[['simTime', 'simFrame', 'lon_acc_roc', 'ip_acc_roc', 'slam_accel']].copy() data = self.ego_df[['simTime', 'simFrame', 'lon_acc', 'ip_acc', 'slam_accel']].copy() # data['slam_diff'] = data['slam_accel'].diff() # res_df = data.loc[data['slam_diff'] == 1] res_df = data.loc[data['slam_accel'] == 1] t_list = res_df['simTime'].values f_list = res_df['simFrame'].values.tolist() group_time = [] group_frame = [] sub_group_time = [] sub_group_frame = [] for i in range(len(f_list)): if not group_time or f_list[i] - f_list[i - 1] <= 1: # 连续帧的算作同一组急加速 sub_group_time.append(t_list[i]) sub_group_frame.append(f_list[i]) else: group_time.append(sub_group_time) group_frame.append(sub_group_frame) sub_group_time = [t_list[i]] sub_group_frame = [f_list[i]] group_time.append(sub_group_time) group_frame.append(sub_group_frame) group_time = [g for g in group_time if len(g) >= 2] # group_frame = [g for g in group_frame if len(g) >= 2] time_list = [element for sublist in group_time for element in sublist] self.slam_accel_count = len(group_time) # / self.mileage # * 1000000 return time_list def _speed_instruction_jump_detector(self): data = self.ego_df[['simTime', 'simFrame', 'cmd_lon_v', 'cmd_lon_v_diff', 'cmd_v_jump']].copy() # data['slam_diff'] = data['slam_accel'].diff() # res_df = data.loc[data['slam_diff'] == 1] res_df = data.loc[data['cmd_v_jump'] == 1] t_list = res_df['simTime'].values f_list = res_df['simFrame'].values.tolist() group_time = [] group_frame = [] sub_group_time = [] sub_group_frame = [] for i in range(len(f_list)): if not group_time or f_list[i] - f_list[i - 1] <= 10: # 连续帧的算作同一组跳变 sub_group_time.append(t_list[i]) sub_group_frame.append(f_list[i]) else: group_time.append(sub_group_time) group_frame.append(sub_group_frame) sub_group_time = [t_list[i]] sub_group_frame = [f_list[i]] group_time.append(sub_group_time) group_frame.append(sub_group_frame) group_time = [g for g in group_time if len(g) >= 2] # group_frame = [g for g in group_frame if len(g) >= 2] time_list = [element for sublist in group_time for element in sublist] self.speed_instruction_jump_count = len(group_time) # / self.mileage # * 1000000 return time_list def comf_statistic(self): """ """ # df = self.ego_df[['simTime', 'cur_diff', 'lon_acc', 'lon_acc_roc', 'accelH']].copy() df = self.ego_df[['simTime', 'lon_acc', 'lon_acc_roc', 'accelH']].copy() self.zigzag_count_func() self.cal_zigzag_strength_strength() # if self.zigzag_time_list: # zigzag_df = pd.DataFrame(self.zigzag_time_list, columns=['start_time', 'end_time']) # zigzag_df = get_frame_with_time(zigzag_df, self.ego_df) # zigzag_df['type'] = 'zigzag' # self.discomfort_df = pd.concat([self.discomfort_df, zigzag_df], ignore_index=True) # discomfort_df = pd.concat([time_df, frame_df], axis=1) # self.discomfort_df = pd.concat([self.discomfort_df, discomfort_df], ignore_index=True) zigzag_t_list = [] # 只有[t_start, t_end]数对，要提取为完整time list t_list = df['simTime'].values.tolist() for t_start, t_end in self.zigzag_time_list: index_1 = t_list.index(t_start) index_2 = t_list.index(t_end) zigzag_t_list.extend(t_list[index_1:index_2 + 1]) zigzag_t_list = list(set(zigzag_t_list)) # shake_t_list = self._shake_detector() cadence_t_list = self._cadence_detector() slam_brake_t_list = self._slam_brake_detector() slam_accel_t_list = self._slam_accel_detector() speed_instruction_jump_t_list = self._speed_instruction_jump_detector() discomfort_time_list = zigzag_t_list + cadence_t_list + slam_brake_t_list + slam_accel_t_list + speed_instruction_jump_t_list discomfort_time_list = sorted(discomfort_time_list) # 排序 discomfort_time_list = list(set(discomfort_time_list)) # 去重 time_diff = self.time_list[3] - self.time_list[2] # time_diff = 0.4 self.discomfort_duration = len(discomfort_time_list) * time_diff self.count_dict = { "zigzag": self.zigzag_count, # "shake": self.shake_count, "cadence": self.cadence_count, "slamBrake": self.slam_brake_count, "slamAccelerate": self.slam_accel_count, "speedInstructionJump": self.speed_instruction_jump_count } tmp_comf_arr = [self.zigzag_count, self.cadence_count, self.slam_brake_count, self.slam_accel_count, self.speed_instruction_jump_count] self.discomfort_count = sum(tmp_comf_arr) comf_arr = [tmp_comf_arr] return comf_arr # def _nan_detect(self, num): # if math.isnan(num): # return 0 # return num def comf_score_new(self): arr_comf = self.comf_statistic() print("\n[平顺性表现及得分情况]") print("平顺性各指标值：", [[round(num, 2) for num in row] for row in arr_comf]) arr_comf = np.array(arr_comf) score_model = self.scoreModel(self.kind_list, self.optimal_list, self.multiple_list, arr_comf) score_sub = score_model.cal_score() score_metric = list(map(lambda x: 80 if np.isnan(x) else x, score_sub)) metric_list = [x for x in self.metric_list if x in self.config.builtinMetricList] score_metric_dict = {key: value for key, value in zip(metric_list, score_metric)} # custom_metric_list = list(self.customMetricParam.keys()) # for metric in custom_metric_list: # value = self.custom_data[metric]['value'] # param_list = self.customMetricParam[metric] # score = self.custom_metric_score(metric, value, param_list) # score_metric_dict[metric] = round(score, 2) # score_metric_dict = {key: score_metric_dict[key] for key in self.metric_list} # score_metric = list(score_metric_dict.values()) score_type_dict = {} if self.weight_custom: # 自定义权重 score_metric_with_weight_dict = {key: score_metric_dict[key] * self.weight_dict[key] for key in self.weight_dict} for type in self.type_list: type_score = sum( value for key, value in score_metric_with_weight_dict.items() if key in self.metric_dict[type]) score_type_dict[type] = round(type_score, 2) score_type_with_weight_dict = {key: score_type_dict[key] * self.weight_type_dict[key] for key in score_type_dict} score_comfort = sum(score_type_with_weight_dict.values()) else: # 客观赋权 self.weight_list = cal_weight_from_80(score_metric) self.weight_dict = {key: value for key, value in zip(self.metric_list, self.weight_list)} score_comfort = cal_score_with_priority(score_metric, self.weight_list, self.priority_list) for type in self.type_list: type_weight = sum(value for key, value in self.weight_dict.items() if key in self.metric_dict[type]) self.weight_dict = {key: round(value / type_weight, 4) for key, value in self.weight_dict.items() if key in self.metric_dict[type]} type_score_metric = [value for key, value in score_metric_dict.items() if key in self.metric_dict[type]] type_weight_list = [value for key, value in self.weight_dict.items() if key in self.metric_dict[type]] type_priority_list = [value for key, value in self.priority_dict.items() if key in self.metric_dict[type]] type_score = cal_score_with_priority(type_score_metric, type_weight_list, type_priority_list) score_type_dict[type] = round(type_score, 2) score_comfort = round(score_comfort, 2) print("平顺性各指标基准值：", self.optimal_list) print(f"平顺性得分为：{score_comfort:.2f}分。") print(f"平顺性各类型得分为：{score_type_dict}。") print(f"平顺性各指标得分为：{score_metric_dict}。") return score_comfort, score_type_dict, score_metric_dict def zip_time_pairs(self, zip_list, upper_limit=9999): zip_time_pairs = zip(self.time_list, zip_list) zip_vs_time = [[x, upper_limit if y > upper_limit else y] for x, y in zip_time_pairs if not math.isnan(y)] return zip_vs_time def report_statistic(self): """ Returns: """ # report_dict = { # "name": "平顺性", # "weight": f"{self.weight * 100:.2f}%", # "weightDistribution": weight_distribution, # "score": score_comfort, # "level": grade_comfort, # 'discomfortCount': self.discomfort_count, # "description1": comf_description1, # "description2": comf_description2, # "description3": comf_description3, # "description4": comf_description4, # # "comfortLat": lat_dict, # "comfortLon": lon_dict, # # "speData": ego_speed_vs_time, # "speMarkLine": discomfort_slices, # # "accData": lon_acc_vs_time, # "accMarkLine": discomfort_acce_slices, # # "anvData": yawrate_vs_time, # "anvMarkLine": discomfort_zigzag_slices, # # "anaData": yawrate_roc_vs_time, # "anaMarkLine": discomfort_zigzag_slices, # # "curData": [cur_ego_path_vs_time, curvature_vs_time], # "curMarkLine": discomfort_shake_slices, # } # brakePedal_list = self.data_processed.driver_ctrl_data['brakePedal_list'] # throttlePedal_list = self.data_processed.driver_ctrl_data['throttlePedal_list'] # steeringWheel_list = self.data_processed.driver_ctrl_data['steeringWheel_list'] # # # common parameter calculate # brake_vs_time = self.zip_time_pairs(brakePedal_list, 100) # throttle_vs_time = self.zip_time_pairs(throttlePedal_list, 100) # steering_vs_time = self.zip_time_pairs(steeringWheel_list) report_dict = { "name": "平顺性", "weight": f"{self.weight * 100:.2f}%", # 'discomfortCount': self.discomfort_count, } score_comfort, score_type_dict, score_metric_dict = self.comf_score_new() score_comfort = int(score_comfort) if int(score_comfort) == score_comfort else round(score_comfort, 2) grade_comfort = score_grade(score_comfort) report_dict["score"] = score_comfort report_dict["level"] = grade_comfort description = f"· 在平顺性方面，得分{score_comfort}分，表现{grade_comfort}，" is_good = True if any(score_metric_dict[metric] < 80 for metric in self.lon_metric_list): is_good = False description += "线加速度变化剧烈，" tmp = [metric for metric in self.lon_metric_list if score_metric_dict[metric] < 80] str_tmp = "、".join(tmp) description += f"有{str_tmp}情况，需重点优化。" if any(score_metric_dict[metric] < 80 for metric in self.lat_metric_list): is_good = False description += "角加速度变化剧烈，" tmp = [metric for metric in self.lat_metric_list if score_metric_dict[metric] < 80] str_tmp = "、".join(tmp) description += f"有{str_tmp}情况，需重点优化。" if is_good: description += f"线加速度和角加速度变化平顺，表现{grade_comfort}。" report_dict["description"] = replace_key_with_value(description, self.name_dict) # indexes description1 = f"最大值：{self.linear_accel_dict['max']}m/s²；" \ f"最小值：{self.linear_accel_dict['min']}m/s²；" \ f"平均值：{self.linear_accel_dict['avg']}m/s²" description2 = f"最大值：{self.angular_accel_dict['max']}rad/s²；" \ f"最小值：{self.angular_accel_dict['min']}rad/s²；" \ f"平均值：{self.angular_accel_dict['avg']}rad/s²" description3 = f"次数:{self.speed_instruction_jump_count}次; " \ f"最大值：{self.speed_instruction_dict['max']}m/s；" \ f"最小值：{self.speed_instruction_dict['min']}m/s；" \ f"平均值：{self.speed_instruction_dict['avg']}m/s" linearAccelerate_index = { "weight": self.weight_type_dict['comfortLon'], "score": score_type_dict['comfortLon'], "description": description1 } angularAccelerate_index = { "weight": self.weight_type_dict['comfortLat'], "score": score_type_dict['comfortLat'], "description": description2 } speedInstruction_index = { "weight": self.weight_type_dict['comfortSpeed'], "score": score_type_dict['comfortSpeed'], "description": description3 } indexes_dict = { "comfortLat": linearAccelerate_index, "comfortLon": angularAccelerate_index, "comfortSpeed": speedInstruction_index } report_dict["indexes"] = indexes_dict # LinearAccelerate.png plt.figure(figsize=(12, 3)) plt.plot(self.time_list, self.accel_list, label='Linear Accelerate') plt.xlabel('Time(s)') plt.ylabel('Linear Accelerate(m/s^2)') plt.legend() # 调整布局，消除空白边界 plt.tight_layout() plt.savefig(os.path.join(self.resultPath, "LinearAccelerate.png")) plt.close() # AngularAccelerate.png plt.figure(figsize=(12, 3)) plt.plot(self.time_list, self.accelH_list, label='Angular Accelerate') plt.xlabel('Time(s)') plt.ylabel('Angular Accelerate(rad/s^2)') plt.legend() # 调整布局，消除空白边界 plt.tight_layout() plt.savefig(os.path.join(self.resultPath, "AngularAccelerate.png")) plt.close() # Speed.png plt.figure(figsize=(12, 3)) plt.plot(self.time_list, self.speed_list, label='Speed') plt.xlabel('Time(s)') plt.ylabel('Speed(m/s)') plt.legend() # 调整布局，消除空白边界 plt.tight_layout() plt.savefig(os.path.join(self.resultPath, "Speed.png")) plt.close() # commandSpeed.png draw plt.figure(figsize=(12, 3)) plt.plot(self.time_list, self.commandSpeed_list, label='commandSpeed') plt.xlabel('Time(s)') plt.ylabel('commandSpeed(m/s)') plt.legend() # 调整布局，消除空白边界 plt.tight_layout() plt.savefig(os.path.join(self.resultPath, "CommandSpeed.png")) plt.close() print(report_dict) return report_dict # def get_eval_data(self): # df = self.eval_data[ # ['simTime', 'simFrame', 'playerId', 'ip_acc', 'ip_dec', 'slam_brake', 'slam_accel', 'cadence']].copy() # return df