SpeedTuning/scripted_policy.py at main · DaivdYuan/SpeedTuning · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
import numpy as np
from pyquaternion import Quaternion

from sim_tasks import normalize_task_name


class BasePolicy:
    def __init__(self, inject_noise=False):
        self.inject_noise = inject_noise
        self.step_count = 0
        self.left_trajectory = None
        self.right_trajectory = None

    def reset(self):
        self.step_count = 0
        self.left_trajectory = None
        self.right_trajectory = None

    def generate_trajectory(self, ts_first):
        raise NotImplementedError

    @staticmethod
    def interpolate(curr_waypoint, next_waypoint, t):
        t_frac = (t - curr_waypoint["t"]) / (next_waypoint["t"] - curr_waypoint["t"] + 1e-8)
        curr_xyz = curr_waypoint['xyz']
        curr_quat = curr_waypoint['quat']
        curr_grip = curr_waypoint['gripper']
        next_xyz = next_waypoint['xyz']
        next_quat = next_waypoint['quat']
        next_grip = next_waypoint['gripper']
        xyz = curr_xyz + (next_xyz - curr_xyz) * t_frac
        quat = curr_quat + (next_quat - curr_quat) * t_frac
        gripper = curr_grip + (next_grip - curr_grip) * t_frac
        return xyz, quat, gripper

    def __call__(self, ts, step_inc=1):
        if step_inc <= 0:
            raise ValueError("step_inc must be positive")

        # generate trajectory at first timestep, then open-loop execution
        if self.step_count == 0:
            self.generate_trajectory(ts)

        curr_left_waypoint, next_left_waypoint = self._waypoint_pair(
            self.left_trajectory, self.step_count
        )
        curr_right_waypoint, next_right_waypoint = self._waypoint_pair(
            self.right_trajectory, self.step_count
        )

        # interpolate between waypoints to obtain current pose and gripper command
        left_xyz, left_quat, left_gripper = self.interpolate(
            curr_left_waypoint, next_left_waypoint, self.step_count
        )
        right_xyz, right_quat, right_gripper = self.interpolate(
            curr_right_waypoint, next_right_waypoint, self.step_count
        )

        # Inject noise
        if self.inject_noise:
            scale = 0.01
            left_xyz = left_xyz + np.random.uniform(-scale, scale, left_xyz.shape)
            right_xyz = right_xyz + np.random.uniform(-scale, scale, right_xyz.shape)

        action_left = np.concatenate([left_xyz, left_quat, [left_gripper]])
        action_right = np.concatenate([right_xyz, right_quat, [right_gripper]])

        self.step_count += step_inc
        return np.concatenate([action_left, action_right])

    @staticmethod
    def _waypoint_pair(trajectory, timestep):
        """Find a safe interpolation bracket, including at the final waypoint."""

        if not trajectory or len(trajectory) < 2:
            raise ValueError("A scripted trajectory must contain at least two waypoints")
        if timestep >= trajectory[-1]["t"]:
            return trajectory[-1], trajectory[-1]
        for current, following in zip(trajectory[:-1], trajectory[1:]):
            if current["t"] <= timestep < following["t"]:
                return current, following
        return trajectory[0], trajectory[1]


class PickAndTransferPolicy(BasePolicy):

    def generate_trajectory(self, ts_first):
        init_mocap_pose_right = ts_first.observation['mocap_pose_right']
        init_mocap_pose_left = ts_first.observation['mocap_pose_left']

        box_info = np.array(ts_first.observation['env_state'])
        box_xyz = box_info[:3]
        box_quat = box_info[3:]
        # print(f"Generate trajectory for {box_xyz=}")

        gripper_pick_quat = Quaternion(init_mocap_pose_right[3:])
        gripper_pick_quat = gripper_pick_quat * Quaternion(axis=[0.0, 1.0, 0.0], degrees=-60)

        meet_left_quat = Quaternion(axis=[1.0, 0.0, 0.0], degrees=90)

        meet_xyz = np.array([0, 0.5, 0.25])

        self.left_trajectory = [
            {"t": 0, "xyz": init_mocap_pose_left[:3], "quat": init_mocap_pose_left[3:], "gripper": 0}, # sleep
            {"t": 100, "xyz": meet_xyz + np.array([-0.1, 0, -0.02]), "quat": meet_left_quat.elements, "gripper": 1}, # approach meet position
            {"t": 260, "xyz": meet_xyz + np.array([0.02, 0, -0.02]), "quat": meet_left_quat.elements, "gripper": 1}, # move to meet position
            {"t": 310, "xyz": meet_xyz + np.array([0.02, 0, -0.02]), "quat": meet_left_quat.elements, "gripper": 0}, # close gripper
            {"t": 360, "xyz": meet_xyz + np.array([-0.1, 0, -0.02]), "quat": np.array([1, 0, 0, 0]), "gripper": 0}, # move left
            {"t": 400, "xyz": meet_xyz + np.array([-0.1, 0, -0.02]), "quat": np.array([1, 0, 0, 0]), "gripper": 0}, # stay
        ]

        self.right_trajectory = [
            {"t": 0, "xyz": init_mocap_pose_right[:3], "quat": init_mocap_pose_right[3:], "gripper": 0}, # sleep
            {"t": 90, "xyz": box_xyz + np.array([0, 0, 0.08]), "quat": gripper_pick_quat.elements, "gripper": 1}, # approach the cube
            {"t": 130, "xyz": box_xyz + np.array([0., 0, -0.015]), "quat": gripper_pick_quat.elements, "gripper": 1}, # go down
            {"t": 170, "xyz": box_xyz + np.array([0, 0, -0.015]), "quat": gripper_pick_quat.elements, "gripper": 0}, # close gripper
            {"t": 200, "xyz": meet_xyz + np.array([0.05, 0, 0]), "quat": gripper_pick_quat.elements, "gripper": 0}, # approach meet position
            {"t": 220, "xyz": meet_xyz, "quat": gripper_pick_quat.elements, "gripper": 0}, # move to meet position
            {"t": 310, "xyz": meet_xyz, "quat": gripper_pick_quat.elements, "gripper": 1}, # open gripper
            {"t": 360, "xyz": meet_xyz + np.array([0.1, 0, 0]), "quat": gripper_pick_quat.elements, "gripper": 1}, # move to right
            {"t": 400, "xyz": meet_xyz + np.array([0.1, 0, 0]), "quat": gripper_pick_quat.elements, "gripper": 1}, # stay
        ]

class PickAndTransferTeaBagPolicy(BasePolicy):

    def generate_trajectory(self, ts_first):
        init_mocap_pose_right = ts_first.observation['mocap_pose_right']
        init_mocap_pose_left = ts_first.observation['mocap_pose_left']

        box_info = np.array(ts_first.observation['env_state'])

        box_xyz = box_info[:3]
        box_quat = box_info[3:]
        #print(f"Generate trajectory for {box_xyz=}")

        gripper_pick_quat_org = Quaternion(init_mocap_pose_right[3:])
        gripper_pick_quat = gripper_pick_quat_org * Quaternion(axis=[0.0, 1.0, 0.0], degrees=-90)
        gripper_move_quat = gripper_pick_quat_org * Quaternion(axis=[0.0, 1.0, 0.0], degrees=-20)

        meet_left_quat = Quaternion(axis=[1.0, 0.0, 0.0], degrees=90)

        meet_xyz = np.array([-0.1, 0.6, 0.30])


        self.left_trajectory = [
            {"t": 0, "xyz": init_mocap_pose_left[:3], "quat": init_mocap_pose_left[3:], "gripper": 0}, # sleep
            {"t": 500, "xyz": init_mocap_pose_left[:3], "quat": np.array([1, 0, 0, 0]), "gripper": 0}, # stay
        ]

        '''
        # Old policy, oscillation is a problem
        self.right_trajectory = [
            {"t": 0, "xyz": init_mocap_pose_right[:3], "quat": init_mocap_pose_right[3:], "gripper": 0}, # sleep
            {"t": 50, "xyz": box_xyz + np.array([0, 0, 0.08]), "quat": gripper_pick_quat.elements, "gripper": 1}, # approach the cube
            {"t": 70, "xyz": box_xyz + np.array([0.005, 0, -0.03]), "quat": gripper_pick_quat.elements, "gripper": 1}, # go down
            {"t": 100, "xyz": box_xyz + np.array([0.005, 0, -0.03]), "quat": gripper_pick_quat.elements, "gripper": 0}, # close gripper
            {"t": 170, "xyz": meet_xyz + np.array([0.05, 0, 0]), "quat": gripper_move_quat.elements, "gripper": 0}, # approach meet position
            {"t": 200, "xyz": meet_xyz, "quat": gripper_move_quat.elements, "gripper": 0}, # move to meet position
            {"t": 420, "xyz": meet_xyz, "quat": gripper_move_quat.elements, "gripper": 0},  # open gripper
            {"t": 460, "xyz": meet_xyz, "quat": gripper_move_quat.elements, "gripper": 1}, # open gripper
            {"t": 500, "xyz": meet_xyz + np.array([0.1, 0, 0]), "quat": gripper_pick_quat.elements, "gripper": 1},
        ]
        '''

        self.right_trajectory = [
            {"t": 0, "xyz": init_mocap_pose_right[:3], "quat": init_mocap_pose_right[3:], "gripper": 0}, # sleep
            {"t": 50, "xyz": box_xyz + np.array([0, 0, 0.08]), "quat": gripper_pick_quat.elements, "gripper": 1}, # approach the cube
            {"t": 70, "xyz": box_xyz + np.array([0.005, 0, -0.03]), "quat": gripper_pick_quat.elements, "gripper": 1}, # go down
            {"t": 100, "xyz": box_xyz + np.array([0.005, 0, -0.03]), "quat": gripper_pick_quat.elements, "gripper": 0}, # close gripper
            {"t": 150, "xyz": box_xyz + np.array([0.1, 0, 0.1]), "quat": gripper_pick_quat.elements, "gripper": 0}, # vertical align
            {"t": 250, "xyz": box_xyz + np.array([0.1, 0, 0.3]), "quat": gripper_move_quat.elements, "gripper": 0}, # rise up
            {"t": 400, "xyz": meet_xyz, "quat": gripper_move_quat.elements, "gripper": 0}, # move to meet position
            {"t": 420, "xyz": meet_xyz, "quat": gripper_move_quat.elements, "gripper": 0},  # open gripper
            {"t": 450, "xyz": meet_xyz, "quat": gripper_move_quat.elements, "gripper": 1}, # open gripper
            {"t": 500, "xyz": init_mocap_pose_right[:3], "quat": gripper_move_quat.elements, "gripper": 1},
        ]

class InsertionPolicy(BasePolicy):

    def generate_trajectory(self, ts_first):
        init_mocap_pose_right = ts_first.observation['mocap_pose_right']
        init_mocap_pose_left = ts_first.observation['mocap_pose_left']

        peg_info = np.array(ts_first.observation['env_state'])[:7]
        peg_xyz = peg_info[:3]
        peg_quat = peg_info[3:]

        socket_info = np.array(ts_first.observation['env_state'])[7:]
        socket_xyz = socket_info[:3]
        socket_quat = socket_info[3:]

        gripper_pick_quat_right = Quaternion(init_mocap_pose_right[3:])
        gripper_pick_quat_right = gripper_pick_quat_right * Quaternion(axis=[0.0, 1.0, 0.0], degrees=-60)

        gripper_pick_quat_left = Quaternion(init_mocap_pose_right[3:])
        gripper_pick_quat_left = gripper_pick_quat_left * Quaternion(axis=[0.0, 1.0, 0.0], degrees=60)

        meet_xyz = np.array([0, 0.5, 0.15])
        lift_right = 0.00715

        self.left_trajectory = [
            {"t": 0, "xyz": init_mocap_pose_left[:3], "quat": init_mocap_pose_left[3:], "gripper": 0}, # sleep
            {"t": 120, "xyz": socket_xyz + np.array([0, 0, 0.08]), "quat": gripper_pick_quat_left.elements, "gripper": 1}, # approach the cube
            {"t": 170, "xyz": socket_xyz + np.array([0, 0, -0.03]), "quat": gripper_pick_quat_left.elements, "gripper": 1}, # go down
            {"t": 220, "xyz": socket_xyz + np.array([0, 0, -0.03]), "quat": gripper_pick_quat_left.elements, "gripper": 0}, # close gripper
            {"t": 285, "xyz": meet_xyz + np.array([-0.1, 0, 0]), "quat": gripper_pick_quat_left.elements, "gripper": 0}, # approach meet position
            {"t": 340, "xyz": meet_xyz + np.array([-0.05, 0, 0]), "quat": gripper_pick_quat_left.elements,"gripper": 0},  # insertion
            {"t": 400, "xyz": meet_xyz + np.array([-0.05, 0, 0]), "quat": gripper_pick_quat_left.elements, "gripper": 0},  # insertion
        ]

        self.right_trajectory = [
            {"t": 0, "xyz": init_mocap_pose_right[:3], "quat": init_mocap_pose_right[3:], "gripper": 0}, # sleep
            {"t": 120, "xyz": peg_xyz + np.array([0, 0, 0.08]), "quat": gripper_pick_quat_right.elements, "gripper": 1}, # approach the cube
            {"t": 170, "xyz": peg_xyz + np.array([0, 0, -0.03]), "quat": gripper_pick_quat_right.elements, "gripper": 1}, # go down
            {"t": 220, "xyz": peg_xyz + np.array([0, 0, -0.03]), "quat": gripper_pick_quat_right.elements, "gripper": 0}, # close gripper
            {"t": 285, "xyz": meet_xyz + np.array([0.1, 0, lift_right]), "quat": gripper_pick_quat_right.elements, "gripper": 0}, # approach meet position
            {"t": 340, "xyz": meet_xyz + np.array([0.05, 0, lift_right]), "quat": gripper_pick_quat_right.elements, "gripper": 0},  # insertion
            {"t": 400, "xyz": meet_xyz + np.array([0.05, 0, lift_right]), "quat": gripper_pick_quat_right.elements, "gripper": 0},  # insertion

        ]


POLICY_CLASSES = {
    "pick_and_place": PickAndTransferPolicy,
    "insertion": InsertionPolicy,
    "tea_bag": PickAndTransferTeaBagPolicy,
}


def make_scripted_policy(task_name, inject_noise=False):
    """Construct the matching historical scripted policy for a sim task."""

    return POLICY_CLASSES[normalize_task_name(task_name)](inject_noise=inject_noise)