|
IVALab Python Libraries
Collection of code for computer vision and robotics with specific API.
|
This module focuses on analyzing the cosolve data collected to generate a report. More...
Functions | |
| def | analyze_human_effort (file_path, mask) |
| def | analyze_human_tending (file_path) |
| def | analyze_progress (file_path) |
| def | analyze_robot_effort (file_path, mask, progress_start_time=None, output_figure_path="robot_effort_over_time.png") |
| def | classify_action (row, mask) |
| def | compute_duration (row) |
| def | generate_plots (solve_effort, progress, output_figure_path, mask) |
| def | getCameraExtrinsics () |
| def | label_at_pixel (x_coord, y_coord, mask) |
| def | main (args) |
| def | normalize_timestamp (timestamp, reference_time) |
| def | parse_arguments () |
| def | robot_estimate (perf_model_file, effort_file, mask) |
Variables | |
| def | arguments = parse_arguments() |
| home = str(Path.home()) | |
| manCfg = ROSConfig() | |
| manipulation_cfg_file = os.path.join(mary_autonomy, "config", "manipulation.yaml") | |
| mary_autonomy = rpkg.get_path("mary_autonomy") | |
| maryCalPath = rpkg.get_path("mary_calibrate") | |
| string | PERF_MODEL = home + "/visman/mary_ws/src/Mary_ROS/ros/analysis/performance.yaml" |
| string | PROGRESS = home + "visman/Research_Data/Nihit_trial/Direct_Place_Tending/trial_1/progress_20260505_140920.csv" |
| rpkg = rospkg.RosPack() | |
| int | SOLUTION_LABEL = 5 |
| string | SOLVE_EFFORT = home + "/visman/mary_ws/src/Mary_ROS/ros/analysis/trial_1/solve_effort_20260505_140920.csv" |
| string | TEND = home + "/visman/Research_Data/Nihit_trial/Direct_Place_Tending/trial_1/tending_times_20260505_140920.csv" |
| int | UNORGANIZED_LABEL = 6 |
| zoneDet = regact.imageRegions.load(zoneFile) | |
| zoneFile = os.path.join(maryCalPath, "config", manCfg.perception.sort) | |
| list | ZONES = [i for i in range(1, SOLUTION_LABEL)] |
| zones_mask = zoneDet.imRegions | |
This module focuses on analyzing the cosolve data collected to generate a report.
Co-Solve stats : robot activity counts (# sort actions, # place actions, # direct place actions) human activity counts - estimates: # sort actions, # place actions. Human: total time sort, total time place. Human: total tend time Robot: total time sort, total time place, total time direct place. Robot model to estimate time spent picking and placing given number of pieces.
| def analyze_human_effort | ( | file_path, | |
| mask | |||
| ) |
| def analyze_human_tending | ( | file_path | ) |
| def analyze_progress | ( | file_path | ) |
| def analyze_robot_effort | ( | file_path, | |
| mask, | |||
progress_start_time = None, |
|||
output_figure_path = "robot_effort_over_time.png" |
|||
| ) |
| def classify_action | ( | row, | |
| mask | |||
| ) |
| def compute_duration | ( | row | ) |
| def generate_plots | ( | solve_effort, | |
| progress, | |||
| output_figure_path, | |||
| mask | |||
| ) |
| def getCameraExtrinsics | ( | ) |
| def label_at_pixel | ( | x_coord, | |
| y_coord, | |||
| mask | |||
| ) |
| def main | ( | args | ) |
| def normalize_timestamp | ( | timestamp, | |
| reference_time | |||
| ) |
| def parse_arguments | ( | ) |
| def robot_estimate | ( | perf_model_file, | |
| effort_file, | |||
| mask | |||
| ) |
| def arguments = parse_arguments() |
| home = str(Path.home()) |
| manCfg = ROSConfig() |
| manipulation_cfg_file = os.path.join(mary_autonomy, "config", "manipulation.yaml") |
| mary_autonomy = rpkg.get_path("mary_autonomy") |
| maryCalPath = rpkg.get_path("mary_calibrate") |
| string PERF_MODEL = home + "/visman/mary_ws/src/Mary_ROS/ros/analysis/performance.yaml" |
| string PROGRESS = home + "visman/Research_Data/Nihit_trial/Direct_Place_Tending/trial_1/progress_20260505_140920.csv" |
| rpkg = rospkg.RosPack() |
| int SOLUTION_LABEL = 5 |
| string SOLVE_EFFORT = home + "/visman/mary_ws/src/Mary_ROS/ros/analysis/trial_1/solve_effort_20260505_140920.csv" |
| string TEND = home + "/visman/Research_Data/Nihit_trial/Direct_Place_Tending/trial_1/tending_times_20260505_140920.csv" |
| int UNORGANIZED_LABEL = 6 |
| zoneDet = regact.imageRegions.load(zoneFile) |
| zoneFile = os.path.join(maryCalPath, "config", manCfg.perception.sort) |
| list ZONES = [i for i in range(1, SOLUTION_LABEL)] |
| zones_mask = zoneDet.imRegions |