forked from AGiannoutsos/car_racer_gym
-
Notifications
You must be signed in to change notification settings - Fork 0
/
car_racing.py
899 lines (801 loc) · 34.3 KB
/
car_racing.py
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
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
import sys, math
import numpy as np
import Box2D
from Box2D.b2 import (edgeShape, circleShape, fixtureDef, polygonShape, revoluteJointDef, contactListener)
import gym
from gym import spaces
from gym.envs.box2d.car_dynamics import Car
from gym.utils import colorize, seeding, EzPickle
import pyglet
from pyglet import gl
# Easiest continuous control task to learn from pixels, a top-down racing environment.
# Discrete control is reasonable in this environment as well, on/off discretization is
# fine.
#
# State consists of STATE_W x STATE_H pixels.
#
# Reward is -0.1 every frame and +1000/N for every track tile visited, where N is
# the total number of tiles visited in the track. For example, if you have finished in 732 frames,
# your reward is 1000 - 0.1*732 = 926.8 points.
#
# Game is solved when agent consistently gets 900+ points. Track generated is random every episode.
#
# Episode finishes when all tiles are visited. Car also can go outside of PLAYFIELD, that
# is far off the track, then it will get -100 and die.
#
# Some indicators shown at the bottom of the window and the state RGB buffer. From
# left to right: true speed, four ABS sensors, steering wheel position and gyroscope.
#
# To play yourself (it's rather fast for humans), type:
#
# python gym/envs/box2d/car_racing.py
#
# Remember it's powerful rear-wheel drive car, don't press accelerator and turn at the
# same time.
#
# Created by Oleg Klimov. Licensed on the same terms as the rest of OpenAI Gym.
STATE_W = 96 # less than Atari 160x192
STATE_H = 96
VIDEO_W = 600
VIDEO_H = 400
WINDOW_W = 1000
WINDOW_H = 800
SCALE = 6.0 # Track scale
TRACK_RAD = 900/SCALE # Track is heavily morphed circle with this radius
PLAYFIELD = 2000/SCALE # Game over boundary
FPS = 50 # Frames per second
ZOOM = 2.7 # Camera zoom
ZOOM_FOLLOW = True # Set to False for fixed view (don't use zoom)
TRACK_DETAIL_STEP = 21/SCALE
TRACK_TURN_RATE = 0.31
TRACK_WIDTH = 40/SCALE
BORDER = 8/SCALE
BORDER_MIN_COUNT = 4
ROAD_COLOR = [0.4, 0.4, 0.4]
class FrictionDetector(contactListener):
def __init__(self, env):
contactListener.__init__(self)
self.env = env
def BeginContact(self, contact):
self._contact(contact, True)
def EndContact(self, contact):
self._contact(contact, False)
def _contact(self, contact, begin):
tile = None
obj = None
u1 = contact.fixtureA.body.userData
u2 = contact.fixtureB.body.userData
if u1 and "road_friction" in u1.__dict__:
tile = u1
obj = u2
if u2 and "road_friction" in u2.__dict__:
tile = u2
obj = u1
if not tile:
return
tile.color[0] = ROAD_COLOR[0]
tile.color[1] = ROAD_COLOR[1]
tile.color[2] = ROAD_COLOR[2]
if not obj or "tiles" not in obj.__dict__:
return
if begin:
obj.tiles.add(tile)
# print tile.road_friction, "ADD", len(obj.tiles)
if not tile.road_visited:
tile.road_visited = True
self.env.reward += 1000.0/len(self.env.track)
self.env.tile_visited_count += 1
else:
obj.tiles.remove(tile)
# print tile.road_friction, "DEL", len(obj.tiles) -- should delete to zero when on grass (this works)
##########################################################################################
##########################################################################################
#########################Discrete action space Car racing###############################
##########################################################################################
##########################################################################################
class CarRacingDiscrete(gym.Env, EzPickle):
metadata = {
'render.modes': ['human', 'rgb_array', 'state_pixels'],
'video.frames_per_second' : FPS
}
def __init__(self, total_episode_steps=1000 ,verbose=1):
EzPickle.__init__(self)
self.seed()
self.contactListener_keepref = FrictionDetector(self)
self.world = Box2D.b2World((0,0), contactListener=self.contactListener_keepref)
self.viewer = None
self.invisible_state_window = None
self.invisible_video_window = None
self.road = None
self.car = None
self.reward = 0.0
self.prev_reward = 0.0
self.verbose = verbose
self.fd_tile = fixtureDef(
shape = polygonShape(vertices=
[(0, 0),(1, 0),(1, -1),(0, -1)]))
# discrete car racer
# self.action_space = spaces.Box( np.array([-1,0,0]), np.array([+1,+1,+1]), dtype=np.float32) # steer, gas, brake
self.action_space = spaces.Discrete(5)
self.actions = [np.array([-1,0,0], dtype=np.float32),
np.array([1,0,0], dtype=np.float32),
np.array([0,1,0], dtype=np.float32),
np.array([0,0,0.8], dtype=np.float32),
np.array([0,0,0], dtype=np.float32)] # left right, gas, brake, nothing
self.total_episode_steps = total_episode_steps
self.current_steps = 0
self.observation_space = spaces.Box(low=0, high=255, shape=(STATE_W, STATE_H, 3), dtype=np.uint8)
def seed(self, seed=None):
self.np_random, seed = seeding.np_random(seed)
return [seed]
def _destroy(self):
if not self.road:
return
for t in self.road:
self.world.DestroyBody(t)
self.road = []
self.car.destroy()
def _create_track(self):
CHECKPOINTS = 12
# Create checkpoints
checkpoints = []
for c in range(CHECKPOINTS):
alpha = 2*math.pi*c/CHECKPOINTS + self.np_random.uniform(0, 2*math.pi*1/CHECKPOINTS)
rad = self.np_random.uniform(TRACK_RAD/3, TRACK_RAD)
if c==0:
alpha = 0
rad = 1.5*TRACK_RAD
if c==CHECKPOINTS-1:
alpha = 2*math.pi*c/CHECKPOINTS
self.start_alpha = 2*math.pi*(-0.5)/CHECKPOINTS
rad = 1.5*TRACK_RAD
checkpoints.append( (alpha, rad*math.cos(alpha), rad*math.sin(alpha)) )
# print "\n".join(str(h) for h in checkpoints)
# self.road_poly = [ ( # uncomment this to see checkpoints
# [ (tx,ty) for a,tx,ty in checkpoints ],
# (0.7,0.7,0.9) ) ]
self.road = []
# Go from one checkpoint to another to create track
x, y, beta = 1.5*TRACK_RAD, 0, 0
dest_i = 0
laps = 0
track = []
no_freeze = 2500
visited_other_side = False
while True:
alpha = math.atan2(y, x)
if visited_other_side and alpha > 0:
laps += 1
visited_other_side = False
if alpha < 0:
visited_other_side = True
alpha += 2*math.pi
while True: # Find destination from checkpoints
failed = True
while True:
dest_alpha, dest_x, dest_y = checkpoints[dest_i % len(checkpoints)]
if alpha <= dest_alpha:
failed = False
break
dest_i += 1
if dest_i % len(checkpoints) == 0:
break
if not failed:
break
alpha -= 2*math.pi
continue
r1x = math.cos(beta)
r1y = math.sin(beta)
p1x = -r1y
p1y = r1x
dest_dx = dest_x - x # vector towards destination
dest_dy = dest_y - y
proj = r1x*dest_dx + r1y*dest_dy # destination vector projected on rad
while beta - alpha > 1.5*math.pi:
beta -= 2*math.pi
while beta - alpha < -1.5*math.pi:
beta += 2*math.pi
prev_beta = beta
proj *= SCALE
if proj > 0.3:
beta -= min(TRACK_TURN_RATE, abs(0.001*proj))
if proj < -0.3:
beta += min(TRACK_TURN_RATE, abs(0.001*proj))
x += p1x*TRACK_DETAIL_STEP
y += p1y*TRACK_DETAIL_STEP
track.append( (alpha,prev_beta*0.5 + beta*0.5,x,y) )
if laps > 4:
break
no_freeze -= 1
if no_freeze==0:
break
# print "\n".join([str(t) for t in enumerate(track)])
# Find closed loop range i1..i2, first loop should be ignored, second is OK
i1, i2 = -1, -1
i = len(track)
while True:
i -= 1
if i==0:
return False # Failed
pass_through_start = track[i][0] > self.start_alpha and track[i-1][0] <= self.start_alpha
if pass_through_start and i2==-1:
i2 = i
elif pass_through_start and i1==-1:
i1 = i
break
if self.verbose == 1:
print("Track generation: %i..%i -> %i-tiles track" % (i1, i2, i2-i1))
assert i1!=-1
assert i2!=-1
track = track[i1:i2-1]
first_beta = track[0][1]
first_perp_x = math.cos(first_beta)
first_perp_y = math.sin(first_beta)
# Length of perpendicular jump to put together head and tail
well_glued_together = np.sqrt(
np.square( first_perp_x*(track[0][2] - track[-1][2]) ) +
np.square( first_perp_y*(track[0][3] - track[-1][3]) ))
if well_glued_together > TRACK_DETAIL_STEP:
return False
# Red-white border on hard turns
border = [False]*len(track)
for i in range(len(track)):
good = True
oneside = 0
for neg in range(BORDER_MIN_COUNT):
beta1 = track[i-neg-0][1]
beta2 = track[i-neg-1][1]
good &= abs(beta1 - beta2) > TRACK_TURN_RATE*0.2
oneside += np.sign(beta1 - beta2)
good &= abs(oneside) == BORDER_MIN_COUNT
border[i] = good
for i in range(len(track)):
for neg in range(BORDER_MIN_COUNT):
border[i-neg] |= border[i]
# Create tiles
for i in range(len(track)):
alpha1, beta1, x1, y1 = track[i]
alpha2, beta2, x2, y2 = track[i-1]
road1_l = (x1 - TRACK_WIDTH*math.cos(beta1), y1 - TRACK_WIDTH*math.sin(beta1))
road1_r = (x1 + TRACK_WIDTH*math.cos(beta1), y1 + TRACK_WIDTH*math.sin(beta1))
road2_l = (x2 - TRACK_WIDTH*math.cos(beta2), y2 - TRACK_WIDTH*math.sin(beta2))
road2_r = (x2 + TRACK_WIDTH*math.cos(beta2), y2 + TRACK_WIDTH*math.sin(beta2))
vertices = [road1_l, road1_r, road2_r, road2_l]
self.fd_tile.shape.vertices = vertices
t = self.world.CreateStaticBody(fixtures=self.fd_tile)
t.userData = t
c = 0.01*(i%3)
t.color = [ROAD_COLOR[0] + c, ROAD_COLOR[1] + c, ROAD_COLOR[2] + c]
t.road_visited = False
t.road_friction = 1.0
t.fixtures[0].sensor = True
self.road_poly.append(( [road1_l, road1_r, road2_r, road2_l], t.color ))
self.road.append(t)
if border[i]:
side = np.sign(beta2 - beta1)
b1_l = (x1 + side* TRACK_WIDTH *math.cos(beta1), y1 + side* TRACK_WIDTH *math.sin(beta1))
b1_r = (x1 + side*(TRACK_WIDTH+BORDER)*math.cos(beta1), y1 + side*(TRACK_WIDTH+BORDER)*math.sin(beta1))
b2_l = (x2 + side* TRACK_WIDTH *math.cos(beta2), y2 + side* TRACK_WIDTH *math.sin(beta2))
b2_r = (x2 + side*(TRACK_WIDTH+BORDER)*math.cos(beta2), y2 + side*(TRACK_WIDTH+BORDER)*math.sin(beta2))
self.road_poly.append(( [b1_l, b1_r, b2_r, b2_l], (1,1,1) if i%2==0 else (1,0,0) ))
self.track = track
return True
def reset(self):
self.current_steps = 0
self._destroy()
self.reward = 0.0
self.prev_reward = 0.0
self.tile_visited_count = 0
self.t = 0.0
self.road_poly = []
while True:
success = self._create_track()
if success:
break
if self.verbose == 1:
print("retry to generate track (normal if there are not many of this messages)")
self.car = Car(self.world, *self.track[0][1:4])
return self.step(None)[0]
def step(self, action):
self.current_steps += 1
# car racer discrete
if action is not None:
action = self.actions[action]
self.car.steer(-action[0])
self.car.gas(action[1])
self.car.brake(action[2])
self.car.step(1.0/FPS)
self.world.Step(1.0/FPS, 6*30, 2*30)
self.t += 1.0/FPS
self.state = self.render("state_pixels")
step_reward = 0
done = False
if action is not None: # First step without action, called from reset()
self.reward -= 0.1
# We actually don't want to count fuel spent, we want car to be faster.
# self.reward -= 10 * self.car.fuel_spent / ENGINE_POWER
self.car.fuel_spent = 0.0
step_reward = self.reward - self.prev_reward
self.prev_reward = self.reward
if self.tile_visited_count==len(self.track):
done = True
x, y = self.car.hull.position
if abs(x) > PLAYFIELD or abs(y) > PLAYFIELD:
done = True
step_reward = -100
if self.current_steps > self.total_episode_steps:
done = True
if self.current_steps > self.total_episode_steps:
done = True
return self.state, step_reward, done, {}
def render(self, mode='human'):
assert mode in ['human', 'state_pixels', 'rgb_array']
if self.viewer is None:
from gym.envs.classic_control import rendering
self.viewer = rendering.Viewer(WINDOW_W, WINDOW_H)
self.score_label = pyglet.text.Label('0000', font_size=36,
x=20, y=WINDOW_H*2.5/40.00, anchor_x='left', anchor_y='center',
color=(255,255,255,255))
self.transform = rendering.Transform()
if "t" not in self.__dict__: return # reset() not called yet
zoom = 0.1*SCALE*max(1-self.t, 0) + ZOOM*SCALE*min(self.t, 1) # Animate zoom first second
zoom = 0.1*SCALE*0 + ZOOM*SCALE*1 # Animate zoom first second
zoom_state = ZOOM*SCALE*STATE_W/WINDOW_W
zoom_video = ZOOM*SCALE*VIDEO_W/WINDOW_W
scroll_x = self.car.hull.position[0]
scroll_y = self.car.hull.position[1]
angle = -self.car.hull.angle
vel = self.car.hull.linearVelocity
if np.linalg.norm(vel) > 0.5:
angle = math.atan2(vel[0], vel[1])
self.transform.set_scale(zoom, zoom)
self.transform.set_translation(
WINDOW_W/2 - (scroll_x*zoom*math.cos(angle) - scroll_y*zoom*math.sin(angle)),
WINDOW_H/4 - (scroll_x*zoom*math.sin(angle) + scroll_y*zoom*math.cos(angle)) )
self.transform.set_rotation(angle)
self.car.draw(self.viewer, mode!="state_pixels")
arr = None
win = self.viewer.window
win.switch_to()
win.dispatch_events()
win.clear()
t = self.transform
if mode=='rgb_array':
VP_W = VIDEO_W
VP_H = VIDEO_H
elif mode == 'state_pixels':
VP_W = STATE_W
VP_H = STATE_H
else:
pixel_scale = 1
if hasattr(win.context, '_nscontext'):
pixel_scale = win.context._nscontext.view().backingScaleFactor() # pylint: disable=protected-access
VP_W = int(pixel_scale * WINDOW_W)
VP_H = int(pixel_scale * WINDOW_H)
gl.glViewport(0, 0, VP_W, VP_H)
t.enable()
self.render_road()
for geom in self.viewer.onetime_geoms:
geom.render()
self.viewer.onetime_geoms = []
t.disable()
self.render_indicators(WINDOW_W, WINDOW_H)
if mode == 'human':
win.flip()
return self.viewer.isopen
image_data = pyglet.image.get_buffer_manager().get_color_buffer().get_image_data()
arr = np.fromstring(image_data.get_data(), dtype=np.uint8, sep='')
arr = arr.reshape(VP_H, VP_W, 4)
arr = arr[::-1, :, 0:3]
return arr
def close(self):
if self.viewer is not None:
self.viewer.close()
self.viewer = None
def render_road(self):
gl.glBegin(gl.GL_QUADS)
gl.glColor4f(0.4, 0.8, 0.4, 1.0)
gl.glVertex3f(-PLAYFIELD, +PLAYFIELD, 0)
gl.glVertex3f(+PLAYFIELD, +PLAYFIELD, 0)
gl.glVertex3f(+PLAYFIELD, -PLAYFIELD, 0)
gl.glVertex3f(-PLAYFIELD, -PLAYFIELD, 0)
gl.glColor4f(0.4, 0.9, 0.4, 1.0)
k = PLAYFIELD/20.0
for x in range(-20, 20, 2):
for y in range(-20, 20, 2):
gl.glVertex3f(k*x + k, k*y + 0, 0)
gl.glVertex3f(k*x + 0, k*y + 0, 0)
gl.glVertex3f(k*x + 0, k*y + k, 0)
gl.glVertex3f(k*x + k, k*y + k, 0)
for poly, color in self.road_poly:
gl.glColor4f(color[0], color[1], color[2], 1)
for p in poly:
gl.glVertex3f(p[0], p[1], 0)
gl.glEnd()
def render_indicators(self, W, H):
gl.glBegin(gl.GL_QUADS)
s = W/40.0
h = H/40.0
gl.glColor4f(0,0,0,1)
gl.glVertex3f(W, 0, 0)
gl.glVertex3f(W, 5*h, 0)
gl.glVertex3f(0, 5*h, 0)
gl.glVertex3f(0, 0, 0)
def vertical_ind(place, val, color):
gl.glColor4f(color[0], color[1], color[2], 1)
gl.glVertex3f((place+0)*s, h + h*val, 0)
gl.glVertex3f((place+1)*s, h + h*val, 0)
gl.glVertex3f((place+1)*s, h, 0)
gl.glVertex3f((place+0)*s, h, 0)
def horiz_ind(place, val, color):
gl.glColor4f(color[0], color[1], color[2], 1)
gl.glVertex3f((place+0)*s, 4*h , 0)
gl.glVertex3f((place+val)*s, 4*h, 0)
gl.glVertex3f((place+val)*s, 2*h, 0)
gl.glVertex3f((place+0)*s, 2*h, 0)
true_speed = np.sqrt(np.square(self.car.hull.linearVelocity[0]) + np.square(self.car.hull.linearVelocity[1]))
vertical_ind(5, 0.02*true_speed, (1,1,1))
vertical_ind(7, 0.01*self.car.wheels[0].omega, (0.0,0,1)) # ABS sensors
vertical_ind(8, 0.01*self.car.wheels[1].omega, (0.0,0,1))
vertical_ind(9, 0.01*self.car.wheels[2].omega, (0.2,0,1))
vertical_ind(10,0.01*self.car.wheels[3].omega, (0.2,0,1))
horiz_ind(20, -10.0*self.car.wheels[0].joint.angle, (0,1,0))
horiz_ind(30, -0.8*self.car.hull.angularVelocity, (1,0,0))
gl.glEnd()
self.score_label.text = "%04i" % self.reward
self.score_label.draw()
##########################################################################################
##########################################################################################
#########################Continuous action space Car racing###############################
##########################################################################################
##########################################################################################
class CarRacing(gym.Env, EzPickle):
metadata = {
'render.modes': ['human', 'rgb_array', 'state_pixels'],
'video.frames_per_second' : FPS
}
def __init__(self, total_episode_steps=1000 ,verbose=1):
EzPickle.__init__(self)
self.seed()
self.contactListener_keepref = FrictionDetector(self)
self.world = Box2D.b2World((0,0), contactListener=self.contactListener_keepref)
self.viewer = None
self.invisible_state_window = None
self.invisible_video_window = None
self.road = None
self.car = None
self.reward = 0.0
self.prev_reward = 0.0
self.verbose = verbose
self.fd_tile = fixtureDef(
shape = polygonShape(vertices=
[(0, 0),(1, 0),(1, -1),(0, -1)]))
# discrete car racer
self.action_space = spaces.Box( np.array([-1,0,0]), np.array([+1,+1,+1]), dtype=np.float32) # steer, gas, brake
# self.action_space = spaces.Discrete(5)
# self.actions = [np.array([-1,0,0], dtype=np.float32),
# np.array([1,0,0], dtype=np.float32),
# np.array([0,1,0], dtype=np.float32),
# np.array([0,0,0.8], dtype=np.float32),
# np.array([0,0,0], dtype=np.float32)] # left right, gas, brake, nothing
self.total_episode_steps = total_episode_steps
self.current_steps = 0
self.observation_space = spaces.Box(low=0, high=255, shape=(STATE_W, STATE_H, 3), dtype=np.uint8)
def seed(self, seed=None):
self.np_random, seed = seeding.np_random(seed)
return [seed]
def _destroy(self):
if not self.road:
return
for t in self.road:
self.world.DestroyBody(t)
self.road = []
self.car.destroy()
def _create_track(self):
CHECKPOINTS = 12
# Create checkpoints
checkpoints = []
for c in range(CHECKPOINTS):
alpha = 2*math.pi*c/CHECKPOINTS + self.np_random.uniform(0, 2*math.pi*1/CHECKPOINTS)
rad = self.np_random.uniform(TRACK_RAD/3, TRACK_RAD)
if c==0:
alpha = 0
rad = 1.5*TRACK_RAD
if c==CHECKPOINTS-1:
alpha = 2*math.pi*c/CHECKPOINTS
self.start_alpha = 2*math.pi*(-0.5)/CHECKPOINTS
rad = 1.5*TRACK_RAD
checkpoints.append( (alpha, rad*math.cos(alpha), rad*math.sin(alpha)) )
# print "\n".join(str(h) for h in checkpoints)
# self.road_poly = [ ( # uncomment this to see checkpoints
# [ (tx,ty) for a,tx,ty in checkpoints ],
# (0.7,0.7,0.9) ) ]
self.road = []
# Go from one checkpoint to another to create track
x, y, beta = 1.5*TRACK_RAD, 0, 0
dest_i = 0
laps = 0
track = []
no_freeze = 2500
visited_other_side = False
while True:
alpha = math.atan2(y, x)
if visited_other_side and alpha > 0:
laps += 1
visited_other_side = False
if alpha < 0:
visited_other_side = True
alpha += 2*math.pi
while True: # Find destination from checkpoints
failed = True
while True:
dest_alpha, dest_x, dest_y = checkpoints[dest_i % len(checkpoints)]
if alpha <= dest_alpha:
failed = False
break
dest_i += 1
if dest_i % len(checkpoints) == 0:
break
if not failed:
break
alpha -= 2*math.pi
continue
r1x = math.cos(beta)
r1y = math.sin(beta)
p1x = -r1y
p1y = r1x
dest_dx = dest_x - x # vector towards destination
dest_dy = dest_y - y
proj = r1x*dest_dx + r1y*dest_dy # destination vector projected on rad
while beta - alpha > 1.5*math.pi:
beta -= 2*math.pi
while beta - alpha < -1.5*math.pi:
beta += 2*math.pi
prev_beta = beta
proj *= SCALE
if proj > 0.3:
beta -= min(TRACK_TURN_RATE, abs(0.001*proj))
if proj < -0.3:
beta += min(TRACK_TURN_RATE, abs(0.001*proj))
x += p1x*TRACK_DETAIL_STEP
y += p1y*TRACK_DETAIL_STEP
track.append( (alpha,prev_beta*0.5 + beta*0.5,x,y) )
if laps > 4:
break
no_freeze -= 1
if no_freeze==0:
break
# print "\n".join([str(t) for t in enumerate(track)])
# Find closed loop range i1..i2, first loop should be ignored, second is OK
i1, i2 = -1, -1
i = len(track)
while True:
i -= 1
if i==0:
return False # Failed
pass_through_start = track[i][0] > self.start_alpha and track[i-1][0] <= self.start_alpha
if pass_through_start and i2==-1:
i2 = i
elif pass_through_start and i1==-1:
i1 = i
break
if self.verbose == 1:
print("Track generation: %i..%i -> %i-tiles track" % (i1, i2, i2-i1))
assert i1!=-1
assert i2!=-1
track = track[i1:i2-1]
first_beta = track[0][1]
first_perp_x = math.cos(first_beta)
first_perp_y = math.sin(first_beta)
# Length of perpendicular jump to put together head and tail
well_glued_together = np.sqrt(
np.square( first_perp_x*(track[0][2] - track[-1][2]) ) +
np.square( first_perp_y*(track[0][3] - track[-1][3]) ))
if well_glued_together > TRACK_DETAIL_STEP:
return False
# Red-white border on hard turns
border = [False]*len(track)
for i in range(len(track)):
good = True
oneside = 0
for neg in range(BORDER_MIN_COUNT):
beta1 = track[i-neg-0][1]
beta2 = track[i-neg-1][1]
good &= abs(beta1 - beta2) > TRACK_TURN_RATE*0.2
oneside += np.sign(beta1 - beta2)
good &= abs(oneside) == BORDER_MIN_COUNT
border[i] = good
for i in range(len(track)):
for neg in range(BORDER_MIN_COUNT):
border[i-neg] |= border[i]
# Create tiles
for i in range(len(track)):
alpha1, beta1, x1, y1 = track[i]
alpha2, beta2, x2, y2 = track[i-1]
road1_l = (x1 - TRACK_WIDTH*math.cos(beta1), y1 - TRACK_WIDTH*math.sin(beta1))
road1_r = (x1 + TRACK_WIDTH*math.cos(beta1), y1 + TRACK_WIDTH*math.sin(beta1))
road2_l = (x2 - TRACK_WIDTH*math.cos(beta2), y2 - TRACK_WIDTH*math.sin(beta2))
road2_r = (x2 + TRACK_WIDTH*math.cos(beta2), y2 + TRACK_WIDTH*math.sin(beta2))
vertices = [road1_l, road1_r, road2_r, road2_l]
self.fd_tile.shape.vertices = vertices
t = self.world.CreateStaticBody(fixtures=self.fd_tile)
t.userData = t
c = 0.01*(i%3)
t.color = [ROAD_COLOR[0] + c, ROAD_COLOR[1] + c, ROAD_COLOR[2] + c]
t.road_visited = False
t.road_friction = 1.0
t.fixtures[0].sensor = True
self.road_poly.append(( [road1_l, road1_r, road2_r, road2_l], t.color ))
self.road.append(t)
if border[i]:
side = np.sign(beta2 - beta1)
b1_l = (x1 + side* TRACK_WIDTH *math.cos(beta1), y1 + side* TRACK_WIDTH *math.sin(beta1))
b1_r = (x1 + side*(TRACK_WIDTH+BORDER)*math.cos(beta1), y1 + side*(TRACK_WIDTH+BORDER)*math.sin(beta1))
b2_l = (x2 + side* TRACK_WIDTH *math.cos(beta2), y2 + side* TRACK_WIDTH *math.sin(beta2))
b2_r = (x2 + side*(TRACK_WIDTH+BORDER)*math.cos(beta2), y2 + side*(TRACK_WIDTH+BORDER)*math.sin(beta2))
self.road_poly.append(( [b1_l, b1_r, b2_r, b2_l], (1,1,1) if i%2==0 else (1,0,0) ))
self.track = track
return True
def reset(self):
self.current_steps = 0
self._destroy()
self.reward = 0.0
self.prev_reward = 0.0
self.tile_visited_count = 0
self.t = 0.0
self.road_poly = []
while True:
success = self._create_track()
if success:
break
if self.verbose == 1:
print("retry to generate track (normal if there are not many of this messages)")
self.car = Car(self.world, *self.track[0][1:4])
return self.step(None)[0]
def step(self, action):
self.current_steps += 1
# car racer discrete
if action is not None:
self.car.steer(-action[0])
self.car.gas(action[1])
self.car.brake(action[2])
self.car.step(1.0/FPS)
self.world.Step(1.0/FPS, 6*30, 2*30)
self.t += 1.0/FPS
self.state = self.render("state_pixels")
step_reward = 0
done = False
if action is not None: # First step without action, called from reset()
self.reward -= 0.1
# We actually don't want to count fuel spent, we want car to be faster.
# self.reward -= 10 * self.car.fuel_spent / ENGINE_POWER
self.car.fuel_spent = 0.0
step_reward = self.reward - self.prev_reward
self.prev_reward = self.reward
if self.tile_visited_count==len(self.track):
done = True
x, y = self.car.hull.position
if abs(x) > PLAYFIELD or abs(y) > PLAYFIELD:
done = True
step_reward = -100
if self.current_steps > self.total_episode_steps:
done = True
if self.current_steps > self.total_episode_steps:
done = True
return self.state, step_reward, done, {}
def render(self, mode='human'):
assert mode in ['human', 'state_pixels', 'rgb_array']
if self.viewer is None:
from gym.envs.classic_control import rendering
self.viewer = rendering.Viewer(WINDOW_W, WINDOW_H)
self.score_label = pyglet.text.Label('0000', font_size=36,
x=20, y=WINDOW_H*2.5/40.00, anchor_x='left', anchor_y='center',
color=(255,255,255,255))
self.transform = rendering.Transform()
if "t" not in self.__dict__: return # reset() not called yet
zoom = 0.1*SCALE*max(1-self.t, 0) + ZOOM*SCALE*min(self.t, 1) # Animate zoom first second
zoom = 0.1*SCALE*0 + ZOOM*SCALE*1 # Animate zoom first second
zoom_state = ZOOM*SCALE*STATE_W/WINDOW_W
zoom_video = ZOOM*SCALE*VIDEO_W/WINDOW_W
scroll_x = self.car.hull.position[0]
scroll_y = self.car.hull.position[1]
angle = -self.car.hull.angle
vel = self.car.hull.linearVelocity
if np.linalg.norm(vel) > 0.5:
angle = math.atan2(vel[0], vel[1])
self.transform.set_scale(zoom, zoom)
self.transform.set_translation(
WINDOW_W/2 - (scroll_x*zoom*math.cos(angle) - scroll_y*zoom*math.sin(angle)),
WINDOW_H/4 - (scroll_x*zoom*math.sin(angle) + scroll_y*zoom*math.cos(angle)) )
self.transform.set_rotation(angle)
self.car.draw(self.viewer, mode!="state_pixels")
arr = None
win = self.viewer.window
win.switch_to()
win.dispatch_events()
win.clear()
t = self.transform
if mode=='rgb_array':
VP_W = VIDEO_W
VP_H = VIDEO_H
elif mode == 'state_pixels':
VP_W = STATE_W
VP_H = STATE_H
else:
pixel_scale = 1
if hasattr(win.context, '_nscontext'):
pixel_scale = win.context._nscontext.view().backingScaleFactor() # pylint: disable=protected-access
VP_W = int(pixel_scale * WINDOW_W)
VP_H = int(pixel_scale * WINDOW_H)
gl.glViewport(0, 0, VP_W, VP_H)
t.enable()
self.render_road()
for geom in self.viewer.onetime_geoms:
geom.render()
self.viewer.onetime_geoms = []
t.disable()
self.render_indicators(WINDOW_W, WINDOW_H)
if mode == 'human':
win.flip()
return self.viewer.isopen
image_data = pyglet.image.get_buffer_manager().get_color_buffer().get_image_data()
arr = np.fromstring(image_data.get_data(), dtype=np.uint8, sep='')
arr = arr.reshape(VP_H, VP_W, 4)
arr = arr[::-1, :, 0:3]
return arr
def close(self):
if self.viewer is not None:
self.viewer.close()
self.viewer = None
def render_road(self):
gl.glBegin(gl.GL_QUADS)
gl.glColor4f(0.4, 0.8, 0.4, 1.0)
gl.glVertex3f(-PLAYFIELD, +PLAYFIELD, 0)
gl.glVertex3f(+PLAYFIELD, +PLAYFIELD, 0)
gl.glVertex3f(+PLAYFIELD, -PLAYFIELD, 0)
gl.glVertex3f(-PLAYFIELD, -PLAYFIELD, 0)
gl.glColor4f(0.4, 0.9, 0.4, 1.0)
k = PLAYFIELD/20.0
for x in range(-20, 20, 2):
for y in range(-20, 20, 2):
gl.glVertex3f(k*x + k, k*y + 0, 0)
gl.glVertex3f(k*x + 0, k*y + 0, 0)
gl.glVertex3f(k*x + 0, k*y + k, 0)
gl.glVertex3f(k*x + k, k*y + k, 0)
for poly, color in self.road_poly:
gl.glColor4f(color[0], color[1], color[2], 1)
for p in poly:
gl.glVertex3f(p[0], p[1], 0)
gl.glEnd()
def render_indicators(self, W, H):
gl.glBegin(gl.GL_QUADS)
s = W/40.0
h = H/40.0
gl.glColor4f(0,0,0,1)
gl.glVertex3f(W, 0, 0)
gl.glVertex3f(W, 5*h, 0)
gl.glVertex3f(0, 5*h, 0)
gl.glVertex3f(0, 0, 0)
def vertical_ind(place, val, color):
gl.glColor4f(color[0], color[1], color[2], 1)
gl.glVertex3f((place+0)*s, h + h*val, 0)
gl.glVertex3f((place+1)*s, h + h*val, 0)
gl.glVertex3f((place+1)*s, h, 0)
gl.glVertex3f((place+0)*s, h, 0)
def horiz_ind(place, val, color):
gl.glColor4f(color[0], color[1], color[2], 1)
gl.glVertex3f((place+0)*s, 4*h , 0)
gl.glVertex3f((place+val)*s, 4*h, 0)
gl.glVertex3f((place+val)*s, 2*h, 0)
gl.glVertex3f((place+0)*s, 2*h, 0)
true_speed = np.sqrt(np.square(self.car.hull.linearVelocity[0]) + np.square(self.car.hull.linearVelocity[1]))
vertical_ind(5, 0.02*true_speed, (1,1,1))
vertical_ind(7, 0.01*self.car.wheels[0].omega, (0.0,0,1)) # ABS sensors
vertical_ind(8, 0.01*self.car.wheels[1].omega, (0.0,0,1))
vertical_ind(9, 0.01*self.car.wheels[2].omega, (0.2,0,1))
vertical_ind(10,0.01*self.car.wheels[3].omega, (0.2,0,1))
horiz_ind(20, -10.0*self.car.wheels[0].joint.angle, (0,1,0))
horiz_ind(30, -0.8*self.car.hull.angularVelocity, (1,0,0))
gl.glEnd()
self.score_label.text = "%04i" % self.reward
self.score_label.draw()