storm_kit.mpc.rollout.simple_reacher module

class SimpleReacher(exp_params, tensor_args={'device': 'cpu', 'dtype': torch.float32})[source]

Bases: object

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

cost_fn(state_dict, action_batch, no_coll=False, horizon_cost=True, return_dist=False)[source]
current_cost(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(goal_state=None)[source]

Updates the goal targets for the cost functions. goal_state: n_dofs goal_ee_pos: 3 goal_ee_rot: 3,3 goal_ee_quat: 4