Files
guadaloop_lev_control/RL Testing/Use of AI.txt
2025-12-12 08:56:30 -06:00

121 lines
5.8 KiB
Plaintext

[1]. Tool: Gemini
Prompt: Could you please set up my RL training environment to load the URDF file I created for my maglev pod and
put a track above it? This should all be done in PyBullet simulation, using the maglev_predictor and
mag_lev_coil files I have provided. The agent should have access to an observation space with 4 gap
heights and 4 gap height velocities from the sim, and should be able to output 4 PWM values as actions.
Output:
# --- 1. Define Action & Observation Spaces ---
# Action: 4 PWM duty cycles between -1 and 1 (4 independent coils)
# [front_left, front_right, back_left, back_right] corresponding to +Y and -Y ends of each U-yoke
self.action_space = spaces.Box(low=-1, high=1, shape=(4,), dtype=np.float32)
# Observation: 4 normalized noisy sensor gap heights + 4 normalized velocities
# Gaps normalized by 0.030m, velocities by 0.1 m/s
self.observation_space = spaces.Box(low=-5.0, high=5.0, shape=(8,), dtype=np.float32)
# --- 2. Setup Physics & Actuators ---
self.dt = 1./240. # PyBullet default timestep
self.coil_front_L = MagLevCoil(1.1, 0.0025, 12, 10.2) # From your specs
self.coil_front_R = MagLevCoil(1.1, 0.0025, 12, 10.2)
self.coil_back_L = MagLevCoil(1.1, 0.0025, 12, 10.2)
self.coil_back_R = MagLevCoil(1.1, 0.0025, 12, 10.2)
# Sensor noise parameters
self.sensor_noise_std = 0.0001 # 0.1mm standard deviation
# Normalization constants for observations
self.gap_scale = 0.015 # Normalize gaps by +-15mm max expected deviation from middle
self.velocity_scale = 0.1 # Normalize velocities by 0.1 m/s max expected velocity
# Maglev force/torque predictor
self.predictor = MaglevPredictor()
# Connect to PyBullet (DIRECT is faster for training, GUI for debugging)
self.client = p.connect(p.GUI if use_gui else p.DIRECT)
p.setAdditionalSearchPath(pybullet_data.getDataPath())
# Store references
self.trackId = None
self.podId = None
self.collision_local_positions = []
self.yoke_indices = [] # For force application
self.yoke_labels = []
self.sensor_indices = [] # For gap height measurement
self.sensor_labels = []
# For velocity calculation
self.prev_sensor_gaps = None
def reset(self, seed=None, options=None):
# Reset PyBullet simulation
p.resetSimulation(physicsClientId=self.client)
p.setGravity(0, 0, -9.81, physicsClientId=self.client)
p.setTimeStep(self.dt, physicsClientId=self.client)
# Create the maglev track (inverted system - track above, pod hangs below)
# Track bottom surface at Z=0
track_collision = p.createCollisionShape(
shapeType=p.GEOM_BOX,
halfExtents=[1.0, 0.2, 0.010],
physicsClientId=self.client
)
track_visual = p.createVisualShape(
shapeType=p.GEOM_BOX,
halfExtents=[1.0, 0.2, 0.010],
rgbaColor=[0.3, 0.3, 0.3, 0.8],
physicsClientId=self.client
)
self.trackId = p.createMultiBody(
baseMass=0, # Static
baseCollisionShapeIndex=track_collision,
baseVisualShapeIndex=track_visual,
basePosition=[0, 0, 0.010], # Track center at Z=10mm, bottom at Z=0
physicsClientId=self.client
)
p.changeDynamics(self.trackId, -1,
lateralFriction=0.3,
restitution=0.1,
physicsClientId=self.client)
start_pos = [0, 0, start_z]
start_orientation = p.getQuaternionFromEuler([0, 0, 0])
self.podId = p.loadURDF(urdf_path, start_pos, start_orientation, physicsClientId=self.client)
[2]. Tool: Gemini
Prompt:
Output:
# Parse collision shapes to identify yokes and sensors
collision_shapes = p.getCollisionShapeData(self.podId, -1, physicsClientId=self.client)
self.collision_local_positions = []
self.yoke_indices = []
self.yoke_labels = []
self.sensor_indices = []
self.sensor_labels = []
# Expected heights for detection
expected_yoke_sensor_z = 0.08585 # Yokes and sensors always at this height
expected_bolt_z = 0.08585 + self.initial_gap_mm / 1000.0 # Bolts at gap-dependent height
for i, shape in enumerate(collision_shapes):
shape_type = shape[2]
local_pos = shape[5]
self.collision_local_positions.append(local_pos)
# Check if at sensor/yoke height (Z ≈ 0.08585m) - NOT bolts
if abs(local_pos[2] - expected_yoke_sensor_z) < 0.001:
if shape_type == p.GEOM_BOX:
# Yokes are BOX type at the four corners (size 0.0254)
self.yoke_indices.append(i)
x_pos = "Front" if local_pos[0] > 0 else "Back"
y_pos = "Left" if local_pos[1] > 0 else "Right"
self.yoke_labels.append(f"{x_pos}_{y_pos}")
elif shape_type == p.GEOM_CYLINDER or shape_type == p.GEOM_MESH:
# Sensors: distinguish by position pattern
if abs(local_pos[0]) < 0.06 or abs(local_pos[1]) < 0.02:
self.sensor_indices.append(i)
if abs(local_pos[0]) < 0.001: # Center sensors (X ≈ 0)
label = "Center_Right" if local_pos[1] > 0 else "Center_Left"
else: # Front/back sensors (Y ≈ 0)
label = "Front" if local_pos[0] > 0 else "Back"
self.sensor_labels.append(label)