MCZhi / GameFormer-Planner

[ICCV & CVPR Workshop] Learning-enabled Interactive Prediction and Planning Framework for Autonomous Vehicles
https://mczhi.github.io/GameFormer/
MIT License
155 stars 19 forks source link

the problem about 'closed_loop_nonreactive_agents', 'closed_loop_reactive_agents' #23

Open 942411526 opened 3 weeks ago

942411526 commented 3 weeks ago

Dear authors, thanks for your great work. There are a problem when we test the closed loop.

Iteration 148: 0.668 s Running ego_jerk with error: window_length must be odd. Running simulation: 0%| | 0/140 [01:20<?, ?it/s] Traceback (most recent call last): File "/home/yx/github_pr/DTPP/nuplan-devkit/nuplan/planning/metrics/metric_engine.py", line 112, in compute_metric_results metric_results[metric.name] = metric.compute(history, scenario=scenario) File "/home/yx/github_pr/DTPP/nuplan-devkit/nuplan/planning/metrics/evaluation_metrics/common/ego_jerk.py", line 30, in compute metric_statistics: List[MetricStatistics] = self._compute_statistics( File "/home/yx/github_pr/DTPP/nuplan-devkit/nuplan/planning/metrics/evaluation_metrics/base/within_bound_metric_base.py", line 97, in _compute_statistics ego_pose_values = extract_function(ego_pose_states, **extract_function_params) File "/home/yx/github_pr/DTPP/nuplan-devkit/nuplan/planning/metrics/utils/state_extractors.py", line 237, in extract_ego_jerk ego_acceleration = extract_ego_acceleration(ego_states=ego_states, acceleration_coordinate=acceleration_coordinate) File "/home/yx/github_pr/DTPP/nuplan-devkit/nuplan/planning/metrics/utils/state_extractors.py", line 214, in extract_ego_acceleration acceleration = savgol_filter( File "/home/yx/anaconda3/envs/nuplan/lib/python3.9/site-packages/scipy/signal/_savitzky_golay.py", line 335, in savgol_filter coeffs = savgol_coeffs(window_length, polyorder, deriv=deriv, delta=delta) File "/home/yx/anaconda3/envs/nuplan/lib/python3.9/site-packages/scipy/signal/_savitzky_golay.py", line 102, in savgol_coeffs raise ValueError("window_length must be odd.") ValueError: window_length must be odd.

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/home/yx/github_pr/Gamebaseline/run_nuplan_test.py", line 224, in main(args) File "/home/yx/github_pr/Gamebaseline/run_nuplan_test.py", line 204, in main build_simulation(experiment_name, planner, scenarios, output_dir, simulation_dir, metric_dir) File "/home/yx/github_pr/Gamebaseline/run_nuplan_test.py", line 118, in build_simulation report = simulation_runner.run() File "/home/yx/github_pr/DTPP/nuplan-devkit/nuplan/planning/simulation/runner/simulations_runner.py", line 128, in run self.simulation.callback.on_simulation_end(self.simulation.setup, self.planner, self.simulation.history) File "/home/yx/github_pr/DTPP/nuplan-devkit/nuplan/planning/simulation/callback/multi_callback.py", line 68, in on_simulation_end callback.on_simulation_end(setup, planner, history) File "/home/yx/github_pr/DTPP/nuplan-devkit/nuplan/planning/simulation/callback/metric_callback.py", line 102, in on_simulation_end run_metric_engine( File "/home/yx/github_pr/DTPP/nuplan-devkit/nuplan/planning/simulation/callback/metric_callback.py", line 24, in run_metric_engine metric_files = metric_engine.compute(history, scenario=scenario, planner_name=planner_name) File "/home/yx/github_pr/DTPP/nuplan-devkit/nuplan/planning/metrics/metric_engine.py", line 133, in compute all_metrics_results = self.compute_metric_results(history=history, scenario=scenario) File "/home/yx/github_pr/DTPP/nuplan-devkit/nuplan/planning/metrics/metric_engine.py", line 119, in compute_metric_results raise RuntimeError(f"Metric Engine failed with: {e}") RuntimeError: Metric Engine failed with: window_length must be odd.

I don't know how to deal this problem

942411526 commented 3 weeks ago

open loop is fine