storm_kit.mpc.rollout.arm_base module

class ArmBase(exp_params, tensor_args={'device': 'cpu', 'dtype': torch.float32}, world_params=None)[source]

Bases: storm_kit.mpc.rollout.rollout_base.RolloutBase

This rollout function is for reaching a cartesian pose for a robot

Todo: 1. Update exp_params to be kwargs

cost_fn(state_dict, action_batch, no_coll=False, horizon_cost=True)[source]
current_cost(current_state, no_coll=True)[source]
get_ee_pose(current_state)[source]
rollout_fn(start_state, act_seq)[source]

Return sequence of costs and states encountered by simulating a batch of action sequences

Parameters

action_seq (torch.Tensor [num_particles, horizon, d_act]) –

update_params(retract_state=None)[source]

Updates the goal targets for the cost functions.