f110_scripts.sim package

Submodules

f110_scripts.sim.reactive_planners module

Simulation script to test various reactive planners. Supports: bubble, gap_follower, disparity, and dynamic.

class f110_scripts.sim.reactive_planners.PolicyScheduler(policy_path: str)

Bases: CloudScheduler

CloudScheduler backed by an SB3 PPO policy

reset() → None

No persistent state to reset for a stateless policy.

should_call_cloud(step: int, obs: dict[str, Any], latest_cloud_action: Any | None) → bool

Return True to issue a cloud request on this step.

Parameters:

  • step – The current simulation step (0-based).

  • obs – The current observation dict.

  • latest_cloud_action – The most recent cloud action received (None if no cloud result has arrived yet).

Returns:

Whether to send a new cloud inference request.

f110_scripts.sim.reactive_planners.main() → None

Entry point for running reactive planning simulations.

f110_scripts.sim.reactive_planners.parse_args(args: list[str] | None = None) → Namespace

Registers command-line arguments for reactive simulation experiments.

Parameters:

args (list[str] | None) – If provided, the list is passed to ArgumentParser.parse_args. This is mainly used by tests to avoid interference with pytest’s own arguments.

f110_scripts.sim.tracking_planners module

Simulation script for waypoint tracking with multiple agents. Supports single-agent hybrid control (default) and multi-agent waypoint following.

f110_scripts.sim.tracking_planners.main() → None

Entry point for running multi-agent waypoint tracking simulation.

f110_scripts.sim.tracking_planners.parse_args() → Namespace

Registers command-line arguments for path-tracking simulation experiments.

Module contents