-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathindex.html
1551 lines (1303 loc) · 105 KB
/
index.html
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
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
<!DOCTYPE html>
<html>
<head lang="en">
<meta charset="UTF-8">
<meta http-equiv="x-ua-compatible" content="ie=edge">
<title>Learning Task Planning from Multi-Modal Demonstration for Multi-Stage Contact-Rich Manipulation</title>
<meta name="description" content="An in-context learning framework that incorporates tactile and force-torque information from human demonstrations to enhance LLMs' ability to generate plans for new task scenarios. ">
<meta name="viewport" content="width=device-width, initial-scale=1">
<!-- <base href="/"> -->
<link href="https://cdn.jsdelivr.net/npm/[email protected]/dist/css/bootstrap.min.css" rel="stylesheet" integrity="sha384-EVSTQN3/azprG1Anm3QDgpJLIm9Nao0Yz1ztcQTwFspd3yD65VohhpuuCOmLASjC" crossorigin="anonymous">
<link rel="stylesheet" href="//cdnjs.cloudflare.com/ajax/libs/highlight.js/11.6.0/styles/default.min.css">
<link rel="stylesheet" href="css/app.css">
<link rel="stylesheet" href="css/prompt.css">
<link rel="stylesheet" href="css/style_experiments.css">
<link rel="stylesheet" href="css/style_skill_reasoning.css">
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.0.0-beta3/css/all.min.css">
<script src="https://ajax.googleapis.com/ajax/libs/jquery/1.11.3/jquery.min.js"></script>
<script src="//cdnjs.cloudflare.com/ajax/libs/highlight.js/11.6.0/highlight.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/codemirror/5.8.0/codemirror.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/clipboard.js/1.5.3/clipboard.min.js"></script>
<!-- Prism.js CSS (default light theme) -->
<link href="https://cdnjs.cloudflare.com/ajax/libs/prism/1.29.0/themes/prism.min.css" rel="stylesheet" />
<!-- Prism.js script -->
<script src="https://cdnjs.cloudflare.com/ajax/libs/prism/1.29.0/prism.min.js"></script>
<!-- Optionally include language components (e.g., for Python) -->
<script src="https://cdnjs.cloudflare.com/ajax/libs/prism/1.29.0/components/prism-python.min.js"></script>
<script src="js/app_anon.js"></script>
<style>
.nav-pills {
position: relative;
display: inline;
}
.imtip {
position: absolute;
top: 0;
left: 0;
}
</style>
</head>
<body>
<div class="flex-container">
<!-- Cable Mounting Sidebar -->
<div id="cable-experiment-sidebar" class="vertical-nav">
<ul class="nav flex-column">
<li class="nav-item">
<a class="nav-link" href="#cable-experiment-container">Cable Mounting</a>
<ul class="nav flex-column ms-3">
<li class="nav-item">
<a class="nav-link" href="#cable-experiment-container">Framework</a>
<ul class="nav flex-column ms-3">
<li class="nav-item">
<a class="nav-link" href="#cable-experiment-container">1. Pre-processing</a>
</li>
<li class="nav-item">
<a class="nav-link" href="#cable-skill-reasoning-1-container">2. Skill Reasoning</a>
</li>
<li class="nav-item">
<a class="nav-link" href="#cable-condition-reasoning-section">3. Condition Reasoning</a>
</li>
<li class="nav-item">
<a class="nav-link" href="#cable-task-planning-container">4. Task Planning</a>
</li>
</ul>
</li>
<li class="nav-item">
<a class="nav-link" href="#eva-demo-reasoning-cable-container">Eval on Demo Reasoning</a>
</li>
<li class="nav-item">
<a class="nav-link" href="#eva-task-planning-cable-container">Eval on Task Planning</a>
</li>
</ul>
</li>
</ul>
</div>
<!-- Cap Tightening Sidebar -->
<div id="cap-experiment-sidebar" class="vertical-nav" style="display: none;">
<ul class="nav flex-column">
<li class="nav-item">
<a class="nav-link" href="#cap-experiment-container">Cap Tightening</a>
<ul class="nav flex-column ms-3">
<li class="nav-item">
<a class="nav-link" href="#cap-experiment-container">Framework</a>
<ul class="nav flex-column ms-3">
<li class="nav-item">
<a class="nav-link" href="#cap-experiment-container">1. Pre-processing</a>
</li>
<li class="nav-item">
<a class="nav-link" href="#cap-skill-reasoning-1-container">2. Skill Reasoning</a>
</li>
<li class="nav-item">
<a class="nav-link" href="#cap-condition-reasoning-section">3. Condition Reasoning</a>
</li>
<li class="nav-item">
<a class="nav-link" href="#cap-task-planning-container">4. Task Planning</a>
</li>
</ul>
</li>
<li class="nav-item">
<a class="nav-link" href="#eva-demo-reasoning-cap-container">Eval on Demo Reasoning</a>
</li>
<li class="nav-item">
<a class="nav-link" href="#eva-task-planning-cap-container">Eval on Task Planning</a>
</li>
</ul>
</li>
</ul>
</div>
<!-- Main Content -->
<div class="container" id="main">
<div class="row mt-4">
<h2 class="col-md-12 text-center">
<b>Learning Task Planning from Multi-Modal Demonstration</b><br>
<b>for Multi-Stage Contact-Rich Manipulation</b>
</h2>
</div>
<div class="row justify-content-md-center">
<!-- <h4 class="mt-4 mb-2 text-center">
Kejia Chen<sup>*</sup>, Zheng Shen<sup>*</sup>, Yue Zhang, Lingyun Chen, Fan Wu, Zhenshan Bing, Sami Haddadin, Alois Knoll
</h4> -->
<p class="text-justify">
Large Language Models (LLMs) have gained popularity in task planning for long-horizon manipulation tasks.
To enhance the validity of LLM-generated plans, visual demonstrations and online videos have been widely employed to guide the planning process.
However, for manipulation tasks involving subtle movements but rich contact interactions, visual perception alone may be insufficient for the LLM to fully interpret the demonstration.
Additionally, visual data provides limited information on force-related parameters and conditions, which are crucial for effective execution on real robots.
</p>
<p class="text-justify">
We introduce an in-context learning framework that incorporates tactile and force-torque information from human demonstrations to enhance LLMs' ability to generate plans for new task scenarios.
We propose a bootstrapped reasoning pipeline that sequentially integrates each modality into a comprehensive task plan.
This task plan is then used as a reference for planning in new task configurations.
Real-world experiments on two different sequential manipulation tasks demonstrate the effectiveness of our framework in improving LLMs' understanding of multi-modal demonstrations and enhancing the overall planning performance.
</p>
<p style="text-align:center;">
<image src="imgs/overview_simplified.jpg" width="90%">
</p>
<div class="video-container">
<iframe width="90%" height="90%" src="https://www.youtube.com/embed/FFRWuQ1hNHY" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>
</div>
</div>
<h3 class="mt-4 mb-2 text-center">
<b>In-context Learning Framework</b>
</h3>
<h5 class="mt-4 mb-2 text-align:left">
We deploy our framework to two sequential manipulation tasks. <br>
<b style="color: chocolate;">Click on each of the image below to view the corresponding workflow and experiment results.</b>
</h5>
<!-- Container Toggle Button Cable/Cap -->
<div class="button-container clear-fix">
<!-- Cable Mounting Button -->
<div class="btn toggle-btn" id="show-cable-btn">
<div class="btn-content">
<img src="imgs/button/skill_reasoning_cable.jpg" alt="Toggle Cable">
<h5 class="mt-2">
<i class="fas fa-hand-pointer"></i> Cable Mounting
</h5>
</div>
</div>
<!-- Cap Tightening Button -->
<div class="btn toggle-btn" id="show-cap-btn">
<div class="btn-content">
<img src="imgs/button/skill_reasoning_cap.png" alt="Toggle Cap">
<h5 class="mt-2">
<i class="fas fa-hand-pointer"></i> Cap Tightening
</h5>
</div>
</div>
</div>
<!-- Container Cable -->
<div class="container" id="cable-experiment-container" >
<h5 class="mt-4 mb-2 text-left">
<b>1. Pre-processing</b>
</h5>
<hr>
<div class="row" id="cable-preprocessing-container">
<!-- First Container: segmentation-cable-container -->
<div class="col-md-6 border-end" id="segmentation-cable-container">
<h5 class="mt-4 mb-2 text-center">
Segmentation with Object Status
</h5>
<div class="mt-4 col-md-12">
<div class="d-flex justify-content-center">
<img id="img-segmentation" src="imgs/segmentation.png" alt="Segmentation Image" width="70%">
</div>
</div>
<!-- Four videos of tactile signal pattern -->
<div class="row mt-4">
<div class="col-md-3">
<h6 style="text-align: center;">Compression</h6>
<video id="v3" width="100%" preload="metadata" playsinline muted loop autoplay disablePictureInPicture>
<source src="examples/method/compression_21_2024_05_21_26_force_tactile_post.mp4" type="video/mp4">
</video>
<h6 style="text-align: center;"> Object status: grasped</h6>
</div>
<div class="col-md-3">
<h6 style="text-align: center;">Decompression</h6>
<video id="v4" width="100%" preload="metadata" playsinline muted loop autoplay disablePictureInPicture>
<source src="examples/method/decompression_19_2024_05_21_12_force_tactile_post.mp4" type="video/mp4">
</video>
<h6 style="text-align: center;"> Object status: released</h6>
</div>
<div class="col-md-3">
<h6 style="text-align: center;">Linear Force</h6>
<video id="v5" width="100%" preload="metadata" playsinline muted loop autoplay disablePictureInPicture>
<source src="examples/method/linear_force_0_2024_05_21_14_force_tactile_post.mp4" type="video/mp4">
</video>
<h6 style="text-align: center;"> Object status: under a linear force</h6>
</div>
<div class="col-md-3">
<h6 style="text-align: center;">Rotational Force</h6>
<video id="v6" width="100%" preload="metadata" playsinline muted loop autoplay disablePictureInPicture>
<source src="examples/method/rotational_force_11_2024_08_06_1_force_tactile_post.mp4" type="video/mp4">
</video>
<h6 style="text-align: center;"> Object status: under torque</h6>
</div>
</div>
<p>We fine-tune the video classifier <i>TimeSformer</i> with a dataset of labeled tactile videos. Applying this classifier to
the complete demonstration then segments it into events
when new interaction happens.</p>
<div class="card mb-4 mt-4 text-dark bg-light Keyframes-section" id="keyframes-cable-section">
<h6 class="card-header">Key Camera Frames</h6>
<div class="card-body">
<div class="col-md-12" id="keyframes-cable">
<div class="SkillSequenceTextContainer" id="keyframes-cable-container">
<div class="SkillSequenceImageContainer" id="keyframes-cable-container">
<img class="SkillSequenceFrame" id="keyframes-cable-frame" src="examples/experiments/skill_sequence/without_object/" alt="Frame 0" style="width: 90%; height: auto;">
</div>
<div class="SkillSequenceResetContainer" id="keyframes-cable-container">
<button class="btn prevButton" id="keyframes-cable-prevButton">Previous</button>
<button class="btn resetButton" id="keyframes-cable-resetButton">Reset</button>
<button class="btn nextButton" id="keyframes-cable-nextButton">Next</button>
</div>
</div>
</div>
</div>
</div>
</div>
<!-- Second Container: pddl-cable-container -->
<div class="col-md-6" id="pddl-cable-container">
<h5 class="mt-4 mb-2 text-center">
Pre-processing Translation
</h5>
<div class="mt-4 col-md-12">
<div class="d-flex justify-content-center">
<img id="img-translation" src="imgs/translation.png" alt="Transition Image" width="60%">
</div>
</div>
<!-- Cable Skill Lib Container -->
<div class="card mb-4 mt-4 text-dark bg-light" id="cable-skilllib-section">
<h6 class="card-header" style="text-align: left;"><i class="fas fa-user"></i> User Input (Skill Library)</h6>
<div class="card-body" id="cable-skilllib-container" style="font-size: 15px; text-align: left; height: 200px; overflow-y: scroll; border: 0px solid #ccc;">
<!-- The Skill Library will be inserted here by JavaScript -->
</div>
</div>
<!-- Cable Skill Lib User Request Container -->
<div class="card mb-4 mt-4 text-dark bg-light" id="cable-skilllib-user-section">
<h6 class="card-header" style="text-align: left;">
<i class="fas fa-user"></i> User Request
</h6>
<div class="card-body" id="cable-skilllib-user-container" style="font-size: 15px; text-align: left; height: 180px; overflow-y: scroll; border: 0px solid #ccc;">
<!-- The Translate prompt will be inserted here by JavaScript -->
</div>
</div>
<!-- Cable PDDL Container -->
<div class="card mb-4 mt-4 text-dark bg-light" id="cable-pddl-section">
<h6 class="card-header" style="text-align: left;"><i class="fas fa-robot"></i> LLM Response (PDDL Domain)</h6>
<div class="card-body" id="cable-pddl-container" style="font-size: 15px; text-align: left; height: 200px; overflow-y: scroll; border: 0px solid #ccc;">
<!-- The Skill Library will be inserted here by JavaScript -->
</div>
</div>
</div>
</div>
<!-- Cable Skill Reasoning Container -->
<h5 class="mt-4 mb-2 text-left">
<b>2. Skill Reasoning</b>
</h5>
<hr>
<div class="d-flex justify-content-center mt-4">
<img id="img-skill" src="imgs/skill_reasoning.png" alt="Skill Reasoning Image" width="35%">
</div>
<div class="container" id="cable-skill-container" style="width: 90%; margin: 0 auto;">
<div class="request-response-pair-skill-cable" id="cable-skill-reasoning-1-container">
<!-- <h5 class="mt-4 mb-2 text-center"> Step1. Extraction of Demo Skill Sequence</h5> -->
<!-- Task Description -->
<div class="row">
<div class="col-md-6">
<div class="card mb-4 mt-2 text-dark bg-light" id="task-description-section">
<h6 class="card-header" style="text-align: left;">
<i class="fas fa-user"></i> 1. User Input (Demo Task Description)
</h6>
<div class="card-body" id="task-cable-container" style="font-size: 15px; text-align: left; height: 150px; overflow-y: scroll; border: 0px solid #ccc;">
<!-- The Task Description will be inserted here by JavaScript -->
</div>
</div>
</div>
<!-- User Request -->
<div class="col-md-6">
<div class="card mb-4 mt-2 text-dark bg-light" id="user-request-section">
<h6 class="card-header" style="text-align: left;">
<i class="fas fa-user"></i> 1. User Request
</h6>
<div class="card-body" id="user-request-cable-container" style="font-size: 15px; text-align: left; height: 150px; overflow-y: scroll; border: 0px solid #ccc;">
<!-- The User Request will be inserted here by JavaScript -->
</div>
</div>
</div>
</div>
<!-- LLM Response -->
<!-- Demo Skill Sequence -->
<div class="card mb-4 text-dark bg-light" id="skill-sequence-section">
<h6 class="card-header"><i class="fas fa-robot"></i> 1. LLM Response (Demo Skill Sequence)</h6>
<div class="card-body" id="skill-sequence-cable-container" style="font-size: 15px; text-align: left; height: 220px; overflow-y: scroll; border: 1px solid #ccc;">
<!-- The Demo Skill Sequence will be inserted here by JavaScript -->
</div>
</div>
</div>
<div class="request-response-pair-skill-cable" id="cable-skill-reasoning-2-container">
<!-- <h5 class="mt-4 mb-2 text-center"> Step2: Update Skill Sequence with Parameters</h5> -->
<div class="card mb-4 text-dark bg-light" id="user-request-condition-cable-4-section">
<h6 class="card-header" style="text-align: left;">
<i class="fas fa-user"></i> 2. User Request
</h6>
<div class="card-body" id="user-request-condition-cable-4-container" style="font-size: 15px; text-align: left; height: 200px; overflow-y: scroll; border: 0px solid #ccc;">
<!-- The User Request will be inserted here by JavaScript -->
</div>
</div>
<!-- Demo Plan -->
<div class="card mb-4 text-dark bg-light" id="demo-plan-section">
<h6 class="card-header"> <i class="fas fa-robot"></i> 2. LLM Response (Demo Skill Sequence)</h6>
<div class="card-body" id="demo-plan-cable-container" style="font-size: 15px; text-align: left; height: 200px; overflow-y: scroll; border: 1px solid #ccc;">
<!-- The Demo Plan will be inserted here by JavaScript -->
</div>
</div>
</div>
<!-- Prev and Next Request Buttons -->
<div style="display: flex; justify-content: center; margin-top: 20px;">
<button id="cable-skill-prev-request-btn" class="btn prevButton_cable_skill" style="flex: 0.2; margin-left: 15px; margin-right: 20px; padding: 2px; font-size: 12px; height:30px; border: 1px solid #000; border-radius: 5px; ">Prev Request</button>
<button id="cable-skill-next-request-btn" class="btn nextButton_cable_skill" style="flex: 0.2; margin-left: 20px; margin-right: 15px; padding: 2px; font-size: 12px; height:30px; border: 1px solid #000; border-radius: 5px; ">Next Request</button>
</div>
</div>
<br>
<!-- Cable Condition Reasoning Container -->
<h5 class="mt-4 mb-2 text-left">
<b>3. Condition Reasoning</b>
</h5>
<hr>
<div class="container" id="cable-condition-reasoning-section">
<div class="d-flex justify-content-center">
<div class="d-flex justify-content-center mt-4">
<img id="img-condition" src="imgs/condition_reasoning.png" alt="Condition Reasoning Image" width="35%">
</div>
</div>
<div class="row" id="cable-condition-reasoning-container">
<!-- First Container: pre/post-condition-cable-container -->
<div class="container" id="prepost-condition-cable-container" style="width: 90%; margin: 0 auto;">
<!-- Request/Response Containers -->
<div class="request-response-container">
<!-- First User Request and Response -->
<div class="request-response-pair" id="request-response-1">
<div class="card mb-4 mt-4 text-dark bg-light" id="user-request-condition-cable-section">
<h6 class="card-header" style="text-align: left;">
<i class="fas fa-user"></i> 1. User Request
</h6>
<div class="card-body" id="user-request-condition-cable-1-container" style="font-size: 15px; text-align: left; height: 200px; overflow-y: scroll; border: 0px solid #ccc;">
<!-- Content -->
</div>
</div>
<div class="card mb-4 mt-4 text-dark bg-light" id="LLM-response-condition-cable-1-section">
<h6 class="card-header"><i class="fas fa-robot"></i> 1. LLM Response</h6>
<div class="card-body" id="LLM-response-condition-cable-1-container" style="font-size: 15px; text-align: left; height: 400px; overflow-y: scroll; border: 0px solid #ccc;">
<!-- Content -->
</div>
</div>
</div>
<!-- Second User Request and Response -->
<div class="request-response-pair" id="request-response-2" style="display: none;">
<div class="card mb-4 mt-4 text-dark bg-light" id="user-request-condition-cable-section">
<h6 class="card-header" style="text-align: left;">
<i class="fas fa-user"></i> 2. User Request
</h6>
<div class="card-body" id="user-request-condition-cable-2-container" style="font-size: 15px; text-align: left; height: 200px; overflow-y: scroll; border: 0px solid #ccc;">
<!-- Content -->
</div>
</div>
<div class="card mb-4 mt-4 text-dark bg-light" id="LLM-response-condition-cable-2-section">
<h6 class="card-header"><i class="fas fa-robot"></i> 2. LLM Response</h6>
<div class="card-body" id="LLM-response-condition-cable-2-container" style="font-size: 15px; text-align: left; height: 400px; overflow-y: scroll; border: 0px solid #ccc;">
<!-- Content -->
</div>
</div>
</div>
<!-- Third User Request and Response -->
<div class="request-response-pair" id="request-response-3" style="display: none;">
<div class="card mb-4 mt-4 text-dark bg-light" id="user-request-condition-cable-section">
<h6 class="card-header" style="text-align: left;">
<i class="fas fa-user"></i> 3. User Request（Skill F/T Signals）
</h6>
<div class="card-body" id="user-request-condition-cable-3-container" style="font-size: 15px; text-align: left; height: 200px; overflow-y: scroll; border: 0px solid #ccc;">
<!-- Content -->
</div>
</div>
<div class="card mb-4 mt-4 text-dark bg-light" id="LLM-response-condition-cable-3-section">
<h6 class="card-header"><i class="fas fa-robot"></i> 3. LLM Response (Demo Task Plan)</h6>
<div class="card-body" id="LLM-response-condition-cable-3-container" style="font-size: 15px; text-align: left; height: 400px; overflow-y: scroll; border: 0px solid #ccc;">
<!-- Content -->
</div>
</div>
</div>
</div>
<!-- Prev and Next Request Buttons -->
<div style="display: flex; justify-content: center; margin-top: 20px;">
<button id="cable-condition-prev-request-btn" class="btn prevButton_cable" style="flex: 0.2; margin-left: 15px; margin-right: 20px; padding: 2px; font-size: 12px; height:30px; border: 1px solid #000; border-radius: 5px; ">Prev Request</button>
<button id="cable-condition-next-request-btn" class="btn nextButton_cable" style="flex: 0.2; margin-left: 15px; margin-right: 20px; padding: 2px; font-size: 12px; height:30px; border: 1px solid #000; border-radius: 5px; ">Next Request</button>
</div>
</div>
</div>
</div>
<!-- Cable Task Planning Container -->
<h5 class="mt-4 mb-2 text-left">
<b>4. Task Planning</b>
</h5>
<hr>
<div class="container" id="cable-task-planning-container">
<div class="d-flex justify-content-center">
<div class="d-flex justify-content-center mt-4">
<img id="img-task" src="imgs/task_planning.png" alt="Task Planning Image" width="35%">
</div>
</div>
<div class="container" id="cable-new-plan-container" style="width: 90%; margin: 0 auto;">
<div class="row">
<!-- User Request and Response -->
<div class="col-md-5">
<div class="card mb-4 text-dark bg-light" id="user-request-task-cable-section">
<h6 class="card-header" style="text-align: left;">
<i class="fas fa-user"></i> User Request
</h6>
<div class="card-body" id="task-planning-user-request-cable-container" style="font-size: 15px; text-align: left; height: 250px; overflow-y: scroll; border: 0px solid #ccc;">
<!-- Content -->
</div>
</div>
</div>
<div class="col-md-7">
<!-- Demo Task Plan -->
<div class="card mb-4 mt-2 text-dark bg-light" id="demo-task-plan-cable-section">
<h6 class="card-header"><i class="fas fa-user"></i> User Input (Demo Task Plan)</h6>
<div class="card-body" id="demo-task-plan-cable-container" style="font-size: 15px; text-align: left; height: 250px; overflow-y: scroll; border: 0px solid #ccc;">
<!-- The Task Plan Description will be inserted here by JavaScript -->
</div>
</div>
</div>
</div>
<div class="card mb-4 mt-2 text-dark bg-light" id="LLM-response-task-cable-1-section-new">
<h6 class="card-header"><i class="fas fa-robot"></i> LLM Response (New Task Plan)</h6>
<div class="card-body" id="task-planning-new-cable-container" style="font-size: 15px; text-align: left; height: 300px; overflow-y: scroll; border: 0px solid #ccc;">
<!-- Content -->
</div>
</div>
</div>
</div>
<br><br>
<div class="container" id="eva-demo-reasoning-cable-container">
<h3 class="mt-4 mb-2 text-center">
<b>Evaluation on Demonstration Reasoning</b>
</h3>
<div class="mt-4">
<p>We present real-world experiments to evaluate the effectiveness of our demonstration reasoning pipeline and planning results for new tasks. This evaluation is conducted through ablation study: by disabling or replacing certain parts in our framework, we design the following control groups.</p>
<div class="mt-4" style="padding-left: 30px;">
<p><b>A. Transition Frames Without Object Status:</b> Key frames in our demonstration reasoning pipeline are replaced by frames at key timestamps but without status annotation.</p>
<p><b>B. Uniform Sampled Frames Without Object Status:</b> Frames are sampled uniformly from video, again without status annotation.</p>
<p><b>C. Conditions Without F/T Signals:</b> Force/torque signals are excluded from the demonstration reasoning pipeline, so the success conditions remain as initially generated by the LLM without any updates.</p>
<p><b>D. Without Demonstrations:</b> No demonstration data is provided and the LLM generates the plan solely based on its prior knowledge.</p>
</div>
</div>
<h5 class="mt-4 mb-2 text-left">
<b>Skill Sequences</b>
</h5>
<hr>
<div class="container d-flex flex-row justify-content-between">
<!-- Skill Sequence Full Demo -->
<div class="card mb-4 mt-4 text-dark bg-light skill-section border-end" id="full-demo-section" style="flex: 1; margin-right: 10px;">
<h6 class="card-header">Full Demo</h6>
<div class="card-body">
<!-- Content of Full Demo Section -->
<h6 class="text-center">Keyframes and Reasoning</h6>
<div class="col-md-12" id="skill-sequence-full-demo">
<div class="SkillSequenceTextContainer" id="full-demo-text-container">
<div class="SkillSequenceImageContainer" id="full-demo-image-container">
<img class="SkillSequenceFrame" id="full-demo-frame" src="examples/experiments/skill_sequence/full_demo/frame_0.png" alt="Frame 0" style="width: 100%; height: auto; max-width: 400px;">
</div>
<div class="SkillSequenceResetContainer" id="full-demo-reset-container">
<button class="btn prevButton" id="full-demo-prevButton">Previous</button>
<button class="btn resetButton" id="full-demo-resetButton">Reset</button>
<button class="btn nextButton" id="full-demo-nextButton">Next</button>
</div>
<br>
<h6 id="full-demo-skill">Skill: move_object clip8</h6>
<h6 id="full-demo-reasoning">Because one of the robots is moving the cable towards the position of clip 8.</h6>
</div>
</div>
<!-- <h6 class="mt-4 text-center">Demo Task Plan</h6> -->
<div class="DemoPlanTextContainer" id="full-demo-plan-text-container" style="font-size: 15px; text-align: left; height: 250px; overflow-y: scroll; border: 0px solid #ccc;">
<pre style="background-color: #ffffff00; overflow: visible; white-space: pre-wrap; word-wrap: break-word;" style="background-color: #ffffff; overflow: visible; white-space: pre-wrap; word-wrap: break-word;"><code class="language-python" id="full-demo-plan" ></code></pre>
</div>
</div>
</div>
<!-- Skill Sequence Without Object -->
<div class="card mb-4 mt-4 text-dark bg-light skill-section border-end" id="without-object-section" style="flex: 1; margin-right: 10px;">
<h6 class="card-header">Transition Frames Without Object Status</h6>
<div class="card-body">
<!-- Content of Without Object Section -->
<h6 class="text-center">Keyframes and Reasoning</h6>
<div class="col-md-12" id="skill-sequence-without-object">
<div class="SkillSequenceTextContainer" id="without-object-text-container">
<div class="SkillSequenceImageContainer" id="without-object-image-container">
<img class="SkillSequenceFrame" id="without-object-frame" src="examples/experiments/skill_sequence/without_object/frame_0.png" alt="Frame 0" style="width: 100%; height: auto; max-width: 400px;">
</div>
<div class="SkillSequenceResetContainer" id="without-object-reset-container">
<button class="btn prevButton" id="without-object-prevButton">Previous</button>
<button class="btn resetButton" id="without-object-resetButton">Reset</button>
<button class="btn nextButton" id="without-object-nextButton">Next</button>
</div>
<br>
<h6 id="without-object-skill">Skill: move_object clip8</h6>
<h6 id="without-object-reasoning">Because the robot on the right is moving the cable towards the position of clip8.</h6>
</div>
</div>
<!-- <h6 class="mt-4 text-center">Demo Task Plan</h6> -->
<div class="DemoPlanTextContainer" id="without-object-plan-text-container" style="font-size: 15px; text-align: left; height: 250px; overflow-y: scroll; border: 0px solid #ccc;">
<pre style="background-color: #ffffff00; overflow: visible; white-space: pre-wrap; word-wrap: break-word;" style="background-color: #ffffff; overflow: visible; white-space: pre-wrap; word-wrap: break-word;"><code class="language-python" id="without-object-plan"></code></pre>
</div>
</div>
</div>
<!-- Skill Sequence Raw Video -->
<div class="card mb-4 mt-4 text-dark bg-light skill-section" id="raw-video-section" style="flex: 1;">
<h6 class="card-header">Uniform Sampling Without Object Status</h6>
<div class="card-body">
<!-- Content of Raw Video Section -->
<h6 class="text-center">Keyframes and Reasoning</h6>
<div class="col-md-12" id="skill-sequence-raw-video">
<div class="SkillSequenceTextContainer" id="raw-video-text-container">
<div class="SkillSequenceImageContainer" id="raw-video-image-container">
<img class="SkillSequenceFrame" id="raw-video-frame" src="examples/experiments/skill_sequence/raw_video/frame_0.png" alt="Frame 0" style="width: 100%; height: auto; max-width: 400px;">
</div>
<div class="SkillSequenceResetContainer" id="raw-video-reset-container">
<button class="btn prevButton" id="raw-video-prevButton">Previous</button>
<button class="btn resetButton" id="raw-video-resetButton">Reset</button>
<button class="btn nextButton" id="raw-video-nextButton">Next</button>
</div>
<br>
<h6 id="raw-video-skill">Skill: move_object cable</h6>
<h6 id="raw-video-reasoning">Because the cable is being moved towards the position of clip8.</h6>
</div>
</div>
<!-- <h6 class="mt-4 text-center">Demo Task Plan</h6> -->
<div class="DemoPlanTextContainer" id="raw-video-plan-text-container" style="font-size: 15px; text-align: left; height: 250px; overflow-y: scroll; border: 0px solid #ffffff;">
<pre style="background-color:#ffffff00; overflow: visible; white-space: pre-wrap; word-wrap: break-word;"><code class="language-python" id="raw-video-plan"></code></pre>
</div>
</div>
</div>
</div>
<div class="container" id="post-condition-cable-container">
<h5 class="mt-4 mb-2 text-left">
<b>Transition Conditions</b>
</h5>
<hr>
<!--
<div class="card mb-4 mt-4 text-dark bg-light">
<h6 class="card-header">Initial Skill Library</h6>
<div class="card-body" id="original-skilllib-cap" style="font-size: 15px; text-align: left; height: 200px; overflow-y: scroll; border: 0px solid #ccc;">
</div>
</div>
-->
<div class="card mb-4 mt-4 text-dark bg-light">
<h6 class="card-header">Updated Stretch Skill</h6>
<div class="card-body">
<div class="container d-flex flex-row justify-content-between">
<!-- Image section on the left -->
<div class="mb-4 mt-4 text-dark skill-section" id="image-section" style="flex: 1; margin-right: 10px;">
<img src="imgs/stretch_ft.jpg" alt="F/T Measurement" style="width: 90%; height: auto; display: block;">
</div>
<!-- Code section on the right -->
<div class="skill_update" style="flex: 1;">
<!-- With F/T Sensor Code Section (Initially Visible) -->
<div class="card mb-4 mt-4 text-dark bg-light skill-section border-end" id="stretch_w_ft_container">
<h6 class="card-header">With F/T Sensor</h6>
<div class="card-body" id="stretch_w_ft" style="font-size: 15px; text-align: left; border: 0px solid #ccc;"></div>
</div>
<!-- Without F/T Sensor Code Section (Initially Hidden) -->
<!-- <div class="card-header" id="stretch_wo_ft_container" style="display: none;">
<h6 class="card-header">Without F/T Sensor</h6>
<div class="card-body" id="stretch_wo_ft" style="font-size: 15px; text-align: left; border: 0px solid #ccc;"></div>
</div> -->
<div class="card mb-4 mt-4 text-dark bg-light skill-section border-end" id="stretch_wo_ft_container" style="display: none;">
<h6 class="card-header">Without F/T Sensor</h6>
<div class="card-body" id="stretch_wo_ft" style="font-size: 15px; text-align: left; border: 0px solid #ccc;">
</div>
</div>
<!-- Buttons to toggle views -->
<div class="d-flex justify-content-center mb-3">
<button id="beforeBtn_stretch_cable" class="btn prevButton_transition" onclick="showBefore_stretch_cable()">Before</button>
<button id="afterBtn_stretch_cable" class="btn nextButton_transition" onclick="showAfter_stretch_cable()">After</button>
</div>
</div>
</div>
</div>
</div>
<div class="card mb-4 mt-4 text-dark bg-light">
<h6 class="card-header ">Updated Insert Skill</h6>
<div class="card-body">
<div class="container d-flex flex-row justify-content-between" style="flex: 1 1 50%;">
<!-- Image section on the left with two images -->
<div class="mb-4 mt-4 text-dark skill-section" id="image-section" style="flex: 1; margin-right: 10px;">
<div class="row">
<img src="imgs/insert_c_clip_ft.jpg" alt="F/T Measurement C-Clip" style="width: 95%; height: auto;">
<img src="imgs/insert_u_clip_ft.jpg" alt="F/T Measurement U-Clip" style="width: 95%; height: auto;">
</div>
</div>
<!-- Code section on the right -->
<div class="skill_update" style="flex: 1;">
<!-- With F/T Sensor Code Section -->
<div class="card mb-4 mt-4 text-dark bg-light skill-section border-end" id="insert_w_ft_container" style="width: 580px; height: auto;">
<h6 class="card-header">With F/T Sensor</h6>
<div class="card-body" id="insert_w_ft" style="font-size: 15px; text-align: left; height: auto; overflow-y: auto; border: 0px solid #ccc;"></div>
</div>
<!-- Without F/T Sensor Code Section (Initially Hidden) -->
<div class="card mb-4 mt-4 text-dark bg-light skill-section border-end" id="insert_wo_ft_container" style="width: 580px;display: none;">
<h6 class="card-header">Without F/T Sensor</h6>
<div class="card-body" id="insert_wo_ft" style="font-size: 15px; text-align: left; height: auto; overflow-y: auto; border: 0px solid #ccc;"></div>
</div>
<!-- Buttons to toggle views -->
<div class="d-flex justify-content-center mb-3">
<button id="beforeBtn_insert_cable" class="btn prevButton_transition" onclick="showBefore_insert_cable()">Before</button>
<button id="afterBtn_insert_cable" class="btn nextButton_transition" onclick="showAfter_insert_cable()">After</button>
</div>
</div>
</div>
</div>
</div>
<div class="card mb-4 mt-4 text-dark bg-light">
<h6 class="card-header ">Success Rate</h6>
<div class="card-body">
<!-- <iframe src="examples/evaluation_skill_condition_cable.html" style="width:80%; height:250px; border:none; display: block; margin: 0 auto;"></iframe> -->
<img src="imgs/cable_evaluation/condition_success_rate.png" alt="condition success" style="width: 40%; height: auto; display: block; margin: 0 auto;">
</div>
</div>
</div>
<br><br>
<div class="container" id="eva-task-planning-cable-container">
<h3 class="mt-4 mb-2 text-center">
<b>Evaluation on Task Planning</b>
</h3>
<!-- <div class="card mb-4 mt-4 text-dark bg-light">
<h6 class="card-header ">Plan in New Scenerios</h6>
<div class="card-body text-center">
<img src="imgs/new_plan_cable_config.jpg" alt="new plan" style="width: 75%; height: auto;">
</div>
</div> -->
<div class="card mb-4 mt-4 text-dark bg-light">
<h6 class="card-header ">New Task Plan</h6>
<div class="card-body">
<!-- First row -->
<div class="container d-flex flex-row justify-content-between">
<!-- Full Demo -->
<div class="card mb-4 mt-4 text-dark bg-light skill-section border-end" id="full-demo-section" style="flex: 1; margin-right: 10px;">
<h6 class="card-header">Full Demo</h6>
<!-- Video section -->
<div class="video-container">
<video autoplay muted controls style="width: 100%;">
<source src="imgs/full_annotation.mp4" type="video/mp4">
</video>
</div>
<!-- <div class="card-body DemoPlanTextContainer" id="new-task-plan-cable-1-container" style="font-size: 15px; text-align: left; height: 200px; overflow: auto; border: 0px solid #ccc;">
<pre style="background-color: #f8f9fa; overflow: visible; white-space: pre-wrap; word-wrap: break-word;" style="background-color: #f8f9fa; overflow: visible; white-space: pre-wrap; word-wrap: break-word;"><code class="language-python" id="new-task-plan-cable-1"></code></pre>
</div> -->
</div>
<!-- Uniform Sampled Frames Without Object -->
<div class="card mb-4 mt-4 text-dark bg-light skill-section border-end" id="without-object-section" style="flex: 1; margin-right: 10px;">
<h6 class="card-header"> A. Without Status / B. Uniform Sampled</h6>
<!-- Video section -->
<div class="video-container">
<video autoplay muted controls style="width: 100%;">
<source src="imgs/without_object_annotation.mp4" type="video/mp4">
</video>
</div>
<!-- <div class="card-body DemoPlanTextContainer" id="new-task-plan-cable-2-container" style="font-size: 15px; text-align: left; height: 200px; overflow-y: auto; border: 0px solid #ccc;">
<pre style="background-color: #f8f9fa; overflow: visible; white-space: pre-wrap; word-wrap: break-word;" style="background-color: #f8f9fa; overflow: visible; white-space: pre-wrap; word-wrap: break-word;"><code class="language-python" id="new-task-plan-cable-2"></code></pre>
</div> -->
</div>
</div>
<!-- Second row -->
<div class="container d-flex flex-row justify-content-between">
<!-- Without F/T Signal -->
<div class="card mb-4 mt-4 text-dark bg-light skill-section border-end" id="without-object-section" style="flex: 1; margin-right: 10px;">
<h6 class="card-header"> C. Without F/T Signal</h6>
<!-- Video section -->
<div class="video-container">
<video autoplay muted controls style="width: 100%;">
<source src="imgs/no_ft_annotation.mp4" type="video/mp4">
</video>
</div>
<!-- <div class="card-body DemoPlanTextContainer" id="new-task-plan-cable-3-container" style="font-size: 15px; text-align: left; height: 200px; overflow-y: scroll; border: 0px solid #ccc;">
<pre style="background-color: #f8f9fa; overflow: visible; white-space: pre-wrap; word-wrap: break-word;" style="background-color: #f8f9fa; overflow: visible; white-space: pre-wrap; word-wrap: break-word;"><code class="language-python" id="new-task-plan-cable-3"></code></pre>
</div> -->
</div>
<!-- Without Any Demo -->
<div class="card mb-4 mt-4 text-dark bg-light skill-section border-end" id="without-object-section" style="flex: 1; margin-right: 10px;">
<h6 class="card-header"> D. Without Any Demo</h6>
<!-- Video section -->
<div class="video-container">
<video autoplay muted controls style="width: 100%;">
<source src="imgs/no_demo_annotation.mp4" type="video/mp4">
</video>
</div>
<!-- <div class="card-body DemoPlanTextContainer" id="new-task-plan-cable-4-container" style="font-size: 15px; text-align: left; height: 200px; overflow-y: scroll; border: 0px solid #ccc;">
<pre style="background-color: #f8f9fa; overflow: visible; white-space: pre-wrap; word-wrap: break-word;" style="background-color: #f8f9fa; overflow: visible; white-space: pre-wrap; word-wrap: break-word;"><code class="language-python" id="new-task-plan-cable-4"></code></pre>
</div> -->
</div>
</div>
</div>
</div>
<div class="card mb-4 mt-4 text-dark bg-light">
<h6 class="card-header ">Success Rate</h6>
<div class="card-body">
<!-- <iframe src="examples/evaluation_task_planning_cable.html" style="width:80%; height:295px; border:none; display: block; margin: 0 auto;"></iframe> -->
<img src="imgs/cable_evaluation/overall_success_rate.png" alt="all success" style="width: 50%; height: auto; display: block; margin: 0 auto;">
</div>
</div>
</div>
</div>
</div>
<!-- Container Cap -->
<div class="container" id="cap-experiment-container" style="display: none;">
<h5 class="mt-4 mb-2 text-left">
<b>1. Pre-processing</b>
</h5>
<hr>
<div class="row" id="cap-preprocessing-container">
<!-- First Container: segmentation-cap-container -->
<div class="col-md-6 border-end" id="segmentation-cap-container">
<h5 class="mt-4 mb-2 text-center">
Segmentation with Object Status
</h5>
<div class="mt-4 col-md-12">
<div class="d-flex justify-content-center">
<img id="img-segmentation" src="imgs/segmentation.png" alt="Segmentation Image" width="70%">
</div>
</div>
<!-- Four videos of tactile signal pattern -->
<div class="row mt-4">
<div class="col-md-3">
<h6 style="text-align: center;">Compression</h6>
<video id="v3" width="100%" preload="metadata" playsinline muted loop autoplay disablePictureInPicture>
<source src="examples/method/compression_21_2024_05_21_26_force_tactile_post.mp4" type="video/mp4">
</video>
<h6 style="text-align: center;"> Object status: grasped</h6>
</div>
<div class="col-md-3">
<h6 style="text-align: center;">Decompression</h6>
<video id="v4" width="100%" preload="metadata" playsinline muted loop autoplay disablePictureInPicture>
<source src="examples/method/decompression_19_2024_05_21_12_force_tactile_post.mp4" type="video/mp4">
</video>
<h6 style="text-align: center;"> Object status: released</h6>
</div>
<div class="col-md-3">
<h6 style="text-align: center;">Linear Force</h6>
<video id="v5" width="100%" preload="metadata" playsinline muted loop autoplay disablePictureInPicture>
<source src="examples/method/linear_force_0_2024_05_21_14_force_tactile_post.mp4" type="video/mp4">
</video>
<h6 style="text-align: center;"> Object status: under a linear force</h6>
</div>
<div class="col-md-3">
<h6 style="text-align: center;">Rotational Force</h6>
<video id="v6" width="100%" preload="metadata" playsinline muted loop autoplay disablePictureInPicture>
<source src="examples/method/rotational_force_11_2024_08_06_1_force_tactile_post.mp4" type="video/mp4">
</video>
<h6 style="text-align: center;"> Object status: under torque</h6>
</div>
</div>
<p>We fine-tune the video classifier <i>TimeSformer</i> with a dataset of labeled tactile videos. Applying this classifier to
the complete demonstration then segments it into events
when new interaction happens.</p>
<div class="card mb-4 mt-4 text-dark bg-light Keyframes-section" id="keyframes-cap-section">
<h6 class="card-header">Key Camera Frames</h6>
<div class="card-body">
<div class="col-md-12" id="keyframes-cap">
<div class="SkillSequenceTextContainer" id="keyframes-cap-container">
<div class="SkillSequenceImageContainer" id="keyframes-cap-container">
<img class="SkillSequenceFrame" id="keyframes-cap-frame" src="examples/experiments/skill_sequence/without_object/" alt="Frame 0" style="width: 90%; height: auto;">
</div>
<div class="SkillSequenceResetContainer" id="keyframes-cap-container">
<button class="btn prevButton" id="keyframes-cap-prevButton">Previous</button>
<button class="btn resetButton" id="keyframes-cap-resetButton">Reset</button>
<button class="btn nextButton" id="keyframes-cap-nextButton">Next</button>
</div>
</div>
</div>
</div>
</div>
</div>
<!-- Second Container: pddl-cap-container -->
<div class="col-md-6" id="pddl-cap-container">
<h5 class="mt-4 mb-2 text-center">
Pre-processing Translation
</h5>
<div class="mt-4 col-md-12">
<div class="d-flex justify-content-center">
<img id="img-translation" src="imgs/translation.png" alt="Transition Image" width="60%">
</div>
</div>
<!-- cap Skill Lib Container -->
<div class="card mb-4 mt-4 text-dark bg-light" id="cap-skilllib-section">
<h6 class="card-header" style="text-align: left;"><i class="fas fa-user"></i> User Input (Skill Library)</h6>
<div class="card-body" id="cap-skilllib-container" style="font-size: 15px; text-align: left; height: 200px; overflow-y: scroll; border: 0px solid #ccc;">
<!-- The Skill Library will be inserted here by JavaScript -->
</div>
</div>
<!-- cap Skill Lib User Request Container -->
<div class="card mb-4 mt-4 text-dark bg-light" id="cap-skilllib-user-section">
<h6 class="card-header" style="text-align: left;">
<i class="fas fa-user"></i> User Request
</h6>
<div class="card-body" id="cap-skilllib-user-container" style="font-size: 15px; text-align: left; height: 180px; overflow-y: scroll; border: 0px solid #ccc;">
<!-- The Translate prompt will be inserted here by JavaScript -->
</div>
</div>
<!-- cap PDDL Container -->
<div class="card mb-4 mt-4 text-dark bg-light" id="cap-pddl-section">
<h6 class="card-header" style="text-align: left;"><i class="fas fa-robot"></i> LLM Response (PDDL Domain)</h6>
<div class="card-body" id="cap-pddl-container" style="font-size: 15px; text-align: left; height: 200px; overflow-y: scroll; border: 0px solid #ccc;">
<!-- The Skill Library will be inserted here by JavaScript -->
</div>
</div>
</div>
</div>
<!-- cap Skill Reasoning Container -->
<h5 class="mt-4 mb-2 text-left">
<b>2. Skill Reasoning</b>
</h5>
<hr>
<div class="d-flex justify-content-center mt-4">
<img id="img-skill" src="imgs/skill_reasoning.png" alt="Skill Reasoning Image" width="35%">
</div>
<div class="container" id="cap-skill-container" style="width: 90%; margin: 0 auto;">
<div class="request-response-pair-skill-cap" id="cap-skill-reasoning-1-container">
<!-- <h5 class="mt-4 mb-2 text-center"> Step1. Extraction of Demo Skill Sequence</h5> -->
<!-- Task Description -->
<div class="row">
<div class="col-md-6">
<div class="card mb-4 mt-2 text-dark bg-light" id="task-description-section">
<h6 class="card-header" style="text-align: left;">
<i class="fas fa-user"></i> 1. User Input (Demo Task Description)
</h6>
<div class="card-body" id="task-cap-container" style="font-size: 15px; text-align: left; height: 150px; overflow-y: scroll; border: 0px solid #ccc;">
<!-- The Task Description will be inserted here by JavaScript -->
</div>
</div>
</div>