(prompt, model, num_output, temperature=1)

(image_path)

(self, image)

(self, instruction)

(self, actions)

(self, actions, landmarks, history_traj)

(final_vp, nav_history, shortest_distances, eval_cache, instruction, scanId, des_vp, gt_path)

(dataset)

(shortest_distances, goal_id, path)

(self, image, scene_questions, img_tags)

(dataset_name, ram_path)

(self, direction_list, observation, next_vp)

(self, start_vp, direction_list, instruction, landmarks, scene_questions, nav_history)

(self, direction_idx, instruction, landmarks, navigable_vps, navigable_vps_elevation, scene_questions, history

(self, current_step, instruction, actions, landmarks, history_traj, estimation, observation)

(self, nav_history)

(self, next_vp, thought, curr_observe, nav_history, landmarks)

(self, curr_observe, landmarks)

(self, thought)

(self, fused_pred_thought, observation, instruction)

(self, predictions, thoughts)

(self, ram_path, current_rgb_path="current_view.jpg", view_record_path="cache_files/view_cache.json")

(self, num_predictions=5, num_retry=5)