القائمة
Predict where a projectile will land using kinematic equations with estimated gravity to intercept aerial passes in game AI simulations
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Memory-efficient Keras generator that streams sharded CSV files in chunks, renders strokes to images on-the-fly, and yields batches for training on datasets too large for memory
Stack 1D convolutions for local feature extraction before bidirectional LSTMs to classify variable-length stroke sequences into hundreds of doodle categories
Partition a large dataset into N balanced shards using integer key modulo arithmetic for reproducible, class-interleaved splits across CSV files
Normalize raw stroke coordinates to 0-255 range, resample at uniform arc-length spacing, then apply Ramer-Douglas-Peucker simplification
Render stroke sequences to grayscale images with temporal intensity encoding where earlier strokes are brighter and later strokes fade to encode drawing order
Score each face in a video as anomalous by computing L2 distance from the embedding centroid of all faces, then convert to probability via logistic function
| name | tabular-ball-landing-prediction |
| description | Predict where a projectile will land using kinematic equations with estimated gravity to intercept aerial passes in game AI simulations |
In physics-based game AI, aerial balls follow parabolic trajectories. Instead of chasing the ball's current position, compute where it will land using kinematic equations and run to the intercept point. This requires estimating the game's gravity constant from observation logs, then solving for landing time and applying horizontal velocity.
import numpy as np
GRAVITY = 0.098 # estimated from environment observation logs
PICK_HEIGHT = 0.5 # height at which a player can control the ball
def predict_landing(ball_pos, ball_dir):
z0 = ball_pos[2]
vz = ball_dir[2]
vx, vy = ball_dir[0], ball_dir[1]
discriminant = (vz / GRAVITY) ** 2 - 2 * (PICK_HEIGHT - z0) / GRAVITY
if discriminant < 0:
return ball_pos[:2] # ball won't reach pick height
t = vz / GRAVITY + np.sqrt(discriminant)
land_x = ball_pos[0] + vx * t
land_y = ball_pos[1] + vy * t
return [land_x, land_y]
delta_vz per step)x + vx * tball_direction[2] changes; typically constant