Sampling planner does not work

[purewater0901]

Hello. I was trying to run the sampling based planner in the code, but I got an error.

Command

python scripts/evaluate.py --results_root_dir results/ --dataset_path home/yutaka/ml_data/nuscenes/v1.0-mini/ --env nusc --ckpt_yaml /home/yutaka/nvidia_simulator/tbsim/evaluation/BITS_example.yaml --eval_class HAASplineSampling --agent_eval_class=HierAgentAware --render

Output Error

Traceback (most recent call last):
  File "scripts/evaluate.py", line 432, in <module>
    run_evaluation(
  File "scripts/evaluate.py", line 150, in run_evaluation
    stats, info, renderings, adjust_plans, trace = rollout_episodes(
  File "/home/yutaka/nvidia_simulator/tbsim/tbsim/utils/env_utils.py", line 286, in rollout_episodes
    action = policy.get_action(obs_torch, step_index=counter)
  File "/home/yutaka/nvidia_simulator/tbsim/tbsim/policies/wrappers.py", line 269, in get_action
    ego_action, ego_action_info = self.ego_policy.get_action(
  File "/home/yutaka/nvidia_simulator/tbsim/tbsim/policies/wrappers.py", line 237, in get_action
    action, action_info = self.policy.get_action(obs, **kwargs)
  File "/home/yutaka/nvidia_simulator/tbsim/tbsim/policies/hardcoded.py", line 739, in get_action
    lanes = TensorUtils.to_numpy(obs_dict["ego_lanes"][i])
KeyError: 'ego_lanes'

I guess we need to add ego_lanes in the observation dictionary, but I'm not sure how to do it. Does anyone know how to include the ego_lanes in the observation dictionary?