mradermacher/AlphaSpace-1.5B-v0.2-GGUF
2B • Updated
• 52
Search is not available for this dataset
Source_Obj stringlengths 50 69 | Target_Obj stringlengths 50 69 | Thinking stringlengths 734 827 | Object stringlengths 114 285 | instruction stringlengths 30 79 | solution sequencelengths 7 7 | Conversation listlengths 2 2 |
|---|---|---|---|---|---|---|
[{"<|green|><|triangular prism|>": ["<|1-17|><|local-3-0|>", 30]}] | [{"<|red|><|container|>": ["<|3-11|><|local-1-2|>", 3]}] | LOCATE OBJECTS:
Target Object: <|green|><|triangular prism|> found at <|1-17|><|local-3-0|> with height 30
Target Placement Location: <|red|><|container|> at <|3-11|><|local-1-2|> with height 3
PLAN ACTIONS:
Step 1: Move above source_object at source_pos with > source height.
Step 2: Position the gripper at the base of the source_object on the table surface.
Step 3: Close gripper at the same position to pick up source_object.
Step 4: Lift source_object at source_pos to height > target height.
Step 5: Move to target_object location at target_pos: <|3-11|><|local-1-2|> at the same height as stage 4.
Step 6: Move on top of target_object location at target_pos with height target_height cause the container is empty.
Step 7: Open gripper to drop the <|green|><|triangular prism|> into <|red|><|container|>.
| [{"red-container": [13, 46, 3]}, {"blue-cube": [27, 35, 20]}, {"green-triangular prism": [7, 68, 30]}, {"yellow-container": [44, 14, 25]}, {"green-container": [54, 27, 21]}] | Pick up the triangular prism and place it into the red container | [
[
7,
68,
40,
0,
60,
90,
1
],
[
7,
68,
0,
0,
60,
90,
1
],
[
7,
68,
0,
0,
60,
90,
0
],
[
7,
68,
40,
0,
60,
90,
0
],
[
13,
46,
40,
0,
60,
90,
0
],
[
13,
... | [
{
"content": "You are a spatial reasoning assistant for a Franka Panda robot with a parallel gripper. Your task is to generate precise action sequences to accomplish object manipulation tasks.\n\n## INPUT ENVIRONMENT:\n- The workspace is a table surface represented as a 100x100 discrete grid, divided into a 25x... |
[{"<|maroon|><|cylinder|>": ["<|18-8|><|local-2-0|>", 5]}] | [{"<|rose|><|moon|>": ["<|2-23|><|local-2-2|>", 5]}] | LOCATE OBJECTS:
Target Object: <|maroon|><|cylinder|> found at <|18-8|><|local-2-0|> with height 5
Target Placement Location: <|rose|><|moon|> at <|2-23|><|local-2-2|> with height 5
PLAN ACTIONS:
Step 1: Move above source_object at source_pos with > source height.
Step 2: Position the gripper at the base of the source_object on the table surface.
Step 3: Close gripper at the same position to pick up source_object.
Step 4: Lift source_object at source_pos to height > target height.
Step 5: Move to target_object location at target_pos: <|2-23|><|local-2-2|> at the same height as stage 4.
Step 6: Move on top of target_object location at target_pos with height target_height + 1 to avoid collision.
Step 7: Open gripper to finish the task.
| [{"rose-cube": [69, 45, 2]}, {"maroon-cylinder": [74, 32, 5]}, {"magenta-cylinder": [10, 87, 8]}, {"gray-triangular prism": [62, 11, 3]}, {"rose-moon": [10, 94, 5]}] | Stack the maroon cylinder on top of the rose moon | [
[
74,
32,
15,
0,
60,
90,
1
],
[
74,
32,
0,
0,
60,
90,
1
],
[
74,
32,
0,
0,
60,
90,
0
],
[
74,
32,
15,
0,
60,
90,
0
],
[
10,
94,
15,
0,
60,
90,
0
],
[
10... | [
{
"content": "You are a spatial reasoning assistant for a Franka Panda robot with a parallel gripper. Your task is to generate precise action sequences to accomplish object manipulation tasks.\n\n## INPUT ENVIRONMENT:\n- The workspace is a table surface represented as a 100x100 discrete grid, divided into a 25x... |
[{"<|blue|><|star|>": ["<|12-13|><|local-3-0|>", 13]}] | [{"<|yellow|><|container|>": ["<|18-11|><|local-0-2|>", 13]}] | LOCATE OBJECTS:
Target Object: <|blue|><|star|> found at <|12-13|><|local-3-0|> with height 13
Target Placement Location: <|yellow|><|container|> at <|18-11|><|local-0-2|> with height 13
PLAN ACTIONS:
Step 1: Move above source_object at source_pos with > source height.
Step 2: Position the gripper at the base of the source_object on the table surface.
Step 3: Close gripper at the same position to pick up source_object.
Step 4: Lift source_object at source_pos to height > target height.
Step 5: Move to target_object location at target_pos: <|18-11|><|local-0-2|> at the same height as stage 4.
Step 6: Move on top of target_object location at target_pos with height target_height cause the container is empty.
Step 7: Open gripper to drop the <|blue|><|star|> into <|yellow|><|container|>.
| [{"yellow-container": [72, 46, 13]}, {"black-star": [45, 29, 24]}, {"rose-cube": [67, 20, 9]}, {"green-star": [44, 82, 26]}, {"cyan-container": [24, 73, 8]}, {"navy-container": [96, 27, 29]}, {"blue-star": [51, 52, 13]}] | Pick up the blue star and place it into the yellow container | [
[
51,
52,
23,
0,
60,
90,
1
],
[
51,
52,
0,
0,
60,
90,
1
],
[
51,
52,
0,
0,
60,
90,
0
],
[
51,
52,
23,
0,
60,
90,
0
],
[
72,
46,
23,
0,
60,
90,
0
],
[
72... | [
{
"content": "You are a spatial reasoning assistant for a Franka Panda robot with a parallel gripper. Your task is to generate precise action sequences to accomplish object manipulation tasks.\n\n## INPUT ENVIRONMENT:\n- The workspace is a table surface represented as a 100x100 discrete grid, divided into a 25x... |
[{"<|white|><|cube|>": ["<|20-17|><|local-1-1|>", 24]}] | [{"<|cyan|><|cylinder|>": ["<|21-24|><|local-0-0|>", 2]}] | LOCATE OBJECTS:
Target Object: <|white|><|cube|> found at <|20-17|><|local-1-1|> with height 24
Target Placement Location: <|cyan|><|cylinder|> at <|21-24|><|local-0-0|> with height 2
PLAN ACTIONS:
Step 1: Move above source_object at source_pos with > source height.
Step 2: Position the gripper at the base of the source_object on the table surface.
Step 3: Close gripper at the same position to pick up source_object.
Step 4: Lift source_object at source_pos to height > target height.
Step 5: Move to target_object location at target_pos: <|21-24|><|local-0-0|> at the same height as stage 4.
Step 6: Move on top of target_object location at target_pos with height target_height + 1 to avoid collision.
Step 7: Open gripper to finish the task.
| [{"white-cube": [81, 69, 24]}, {"violet-star": [86, 23, 19]}, {"blue-container": [56, 4, 5]}, {"violet-moon": [26, 90, 16]}, {"cyan-cylinder": [84, 96, 2]}, {"rose-triangular prism": [81, 75, 5]}] | Stack the cube on top of the cylinder | [
[
81,
69,
34,
0,
60,
90,
1
],
[
81,
69,
0,
0,
60,
90,
1
],
[
81,
69,
0,
0,
60,
90,
0
],
[
81,
69,
34,
0,
60,
90,
0
],
[
84,
96,
34,
0,
60,
90,
0
],
[
84... | [
{
"content": "You are a spatial reasoning assistant for a Franka Panda robot with a parallel gripper. Your task is to generate precise action sequences to accomplish object manipulation tasks.\n\n## INPUT ENVIRONMENT:\n- The workspace is a table surface represented as a 100x100 discrete grid, divided into a 25x... |
[{"<|magenta|><|star|>": ["<|21-0|><|local-1-0|>", 7]}] | [{"<|white|><|container|>": ["<|15-14|><|local-2-0|>", 10]}] | LOCATE OBJECTS:
Target Object: <|magenta|><|star|> found at <|21-0|><|local-1-0|> with height 7
Target Placement Location: <|white|><|container|> at <|15-14|><|local-2-0|> with height 10
PLAN ACTIONS:
Step 1: Move above source_object at source_pos with > source height.
Step 2: Position the gripper at the base of the source_object on the table surface.
Step 3: Close gripper at the same position to pick up source_object.
Step 4: Lift source_object at source_pos to height > target height.
Step 5: Move to target_object location at target_pos: <|15-14|><|local-2-0|> at the same height as stage 4.
Step 6: Move on top of target_object location at target_pos with height target_height cause the container is empty.
Step 7: Open gripper to drop the <|magenta|><|star|> into <|white|><|container|>.
| [{"white-container": [62, 56, 10]}, {"green-star": [61, 13, 11]}, {"maroon-cylinder": [65, 45, 5]}, {"rose-container": [29, 39, 28]}, {"magenta-star": [85, 0, 7]}, {"silver-container": [43, 45, 17]}] | Pick up the magenta star and place it into the white container | [
[
85,
0,
17,
0,
60,
90,
1
],
[
85,
0,
0,
0,
60,
90,
1
],
[
85,
0,
0,
0,
60,
90,
0
],
[
85,
0,
17,
0,
60,
90,
0
],
[
62,
56,
17,
0,
60,
90,
0
],
[
62,
... | [
{
"content": "You are a spatial reasoning assistant for a Franka Panda robot with a parallel gripper. Your task is to generate precise action sequences to accomplish object manipulation tasks.\n\n## INPUT ENVIRONMENT:\n- The workspace is a table surface represented as a 100x100 discrete grid, divided into a 25x... |
[{"<|red|><|triangular prism|>": ["<|6-22|><|local-2-1|>", 22]}] | [{"<|purple|><|container|>": ["<|13-5|><|local-3-3|>", 16]}] | LOCATE OBJECTS:
Target Object: <|red|><|triangular prism|> found at <|6-22|><|local-2-1|> with height 22
Target Placement Location: <|purple|><|container|> at <|13-5|><|local-3-3|> with height 16
PLAN ACTIONS:
Step 1: Move above source_object at source_pos with > source height.
Step 2: Position the gripper at the base of the source_object on the table surface.
Step 3: Close gripper at the same position to pick up source_object.
Step 4: Lift source_object at source_pos to height > target height.
Step 5: Move to target_object location at target_pos: <|13-5|><|local-3-3|> at the same height as stage 4.
Step 6: Move on top of target_object location at target_pos with height target_height cause the container is empty.
Step 7: Open gripper to drop the <|red|><|triangular prism|> into <|purple|><|container|>.
| [{"red-triangular prism": [26, 89, 22]}, {"magenta-cylinder": [61, 97, 21]}, {"teal-triangular prism": [22, 44, 6]}, {"purple-container": [55, 23, 16]}, {"maroon-moon": [43, 62, 27]}, {"magenta-moon": [51, 56, 28]}, {"rose-container": [65, 24, 23]}] | Pick up the red triangular prism and place it into the purple container | [
[
26,
89,
32,
0,
60,
90,
1
],
[
26,
89,
0,
0,
60,
90,
1
],
[
26,
89,
0,
0,
60,
90,
0
],
[
26,
89,
32,
0,
60,
90,
0
],
[
55,
23,
32,
0,
60,
90,
0
],
[
55... | [
{
"content": "You are a spatial reasoning assistant for a Franka Panda robot with a parallel gripper. Your task is to generate precise action sequences to accomplish object manipulation tasks.\n\n## INPUT ENVIRONMENT:\n- The workspace is a table surface represented as a 100x100 discrete grid, divided into a 25x... |
[{"<|lime|><|star|>": ["<|17-3|><|local-1-2|>", 16]}] | [{"<|olive|><|star|>": ["<|23-4|><|local-0-2|>", 23]}] | LOCATE OBJECTS:
Target Object: <|lime|><|star|> found at <|17-3|><|local-1-2|> with height 16
Target Placement Location: <|olive|><|star|> at <|23-4|><|local-0-2|> with height 23
PLAN ACTIONS:
Step 1: Move above source_object at source_pos with > source height.
Step 2: Position the gripper at the base of the source_object on the table surface.
Step 3: Close gripper at the same position to pick up source_object.
Step 4: Lift source_object at source_pos to height > target height.
Step 5: Move to target_object location at target_pos: <|23-4|><|local-0-2|> at the same height as stage 4.
Step 6: Move on top of target_object location at target_pos with height target_height + 1 to avoid collision.
Step 7: Open gripper to finish the task.
| [{"olive-star": [92, 18, 23]}, {"blue-cube": [3, 77, 29]}, {"lime-star": [69, 14, 16]}, {"azure-cylinder": [53, 92, 23]}, {"blue-moon": [37, 43, 28]}] | Stack the lime star on top of the olive star | [
[
69,
14,
26,
0,
60,
90,
1
],
[
69,
14,
0,
0,
60,
90,
1
],
[
69,
14,
0,
0,
60,
90,
0
],
[
69,
14,
26,
0,
60,
90,
0
],
[
92,
18,
26,
0,
60,
90,
0
],
[
92... | [
{
"content": "You are a spatial reasoning assistant for a Franka Panda robot with a parallel gripper. Your task is to generate precise action sequences to accomplish object manipulation tasks.\n\n## INPUT ENVIRONMENT:\n- The workspace is a table surface represented as a 100x100 discrete grid, divided into a 25x... |
[{"<|cyan|><|cube|>": ["<|16-11|><|local-3-3|>", 18]}] | [{"<|olive|><|triangular prism|>": ["<|16-9|><|local-0-1|>", 11]}] | LOCATE OBJECTS:
Target Object: <|cyan|><|cube|> found at <|16-11|><|local-3-3|> with height 18
Target Placement Location: <|olive|><|triangular prism|> at <|16-9|><|local-0-1|> with height 11
PLAN ACTIONS:
Step 1: Move above source_object at source_pos with > source height.
Step 2: Position the gripper at the base of the source_object on the table surface.
Step 3: Close gripper at the same position to pick up source_object.
Step 4: Lift source_object at source_pos to height > target height.
Step 5: Move to target_object location at target_pos: <|16-9|><|local-0-1|> at the same height as stage 4.
Step 6: Move on top of target_object location at target_pos with height target_height + 1 to avoid collision.
Step 7: Open gripper to finish the task.
| [{"olive-triangular prism": [64, 37, 11]}, {"cyan-cube": [67, 47, 18]}, {"rose-star": [84, 69, 10]}, {"olive-cylinder": [31, 80, 28]}, {"gray-triangular prism": [29, 89, 9]}, {"white-star": [86, 2, 13]}] | Stack the olive triangular prism and the cyan cube in sequence. | [
[
67,
47,
28,
0,
60,
90,
1
],
[
67,
47,
0,
0,
60,
90,
1
],
[
67,
47,
0,
0,
60,
90,
0
],
[
67,
47,
28,
0,
60,
90,
0
],
[
64,
37,
28,
0,
60,
90,
0
],
[
64... | [
{
"content": "You are a spatial reasoning assistant for a Franka Panda robot with a parallel gripper. Your task is to generate precise action sequences to accomplish object manipulation tasks.\n\n## INPUT ENVIRONMENT:\n- The workspace is a table surface represented as a 100x100 discrete grid, divided into a 25x... |
[{"<|rose|><|moon|>": ["<|22-12|><|local-0-1|>", 4]}] | [{"<|white|><|container|>": ["<|14-15|><|local-1-1|>", 15]}] | LOCATE OBJECTS:
Target Object: <|rose|><|moon|> found at <|22-12|><|local-0-1|> with height 4
Target Placement Location: <|white|><|container|> at <|14-15|><|local-1-1|> with height 15
PLAN ACTIONS:
Step 1: Move above source_object at source_pos with > source height.
Step 2: Position the gripper at the base of the source_object on the table surface.
Step 3: Close gripper at the same position to pick up source_object.
Step 4: Lift source_object at source_pos to height > target height.
Step 5: Move to target_object location at target_pos: <|14-15|><|local-1-1|> at the same height as stage 4.
Step 6: Move on top of target_object location at target_pos with height target_height cause the container is empty.
Step 7: Open gripper to drop the <|rose|><|moon|> into <|white|><|container|>.
| [{"white-container": [57, 61, 15]}, {"red-triangular prism": [16, 30, 2]}, {"rose-moon": [88, 49, 4]}, {"magenta-cylinder": [81, 82, 5]}, {"maroon-cylinder": [27, 59, 24]}, {"rose-container": [53, 8, 14]}, {"lime-container": [12, 16, 10]}] | Pick up the rose moon and place it into the white container | [
[
88,
49,
14,
0,
60,
90,
1
],
[
88,
49,
0,
0,
60,
90,
1
],
[
88,
49,
0,
0,
60,
90,
0
],
[
88,
49,
14,
0,
60,
90,
0
],
[
57,
61,
15,
0,
60,
90,
0
],
[
57... | [
{
"content": "You are a spatial reasoning assistant for a Franka Panda robot with a parallel gripper. Your task is to generate precise action sequences to accomplish object manipulation tasks.\n\n## INPUT ENVIRONMENT:\n- The workspace is a table surface represented as a 100x100 discrete grid, divided into a 25x... |
[{"<|silver|><|cube|>": ["<|15-5|><|local-3-2|>", 3]}] | [{"<|azure|><|container|>": ["<|22-13|><|local-0-1|>", 30]}] | LOCATE OBJECTS:
Target Object: <|silver|><|cube|> found at <|15-5|><|local-3-2|> with height 3
Target Placement Location: <|azure|><|container|> at <|22-13|><|local-0-1|> with height 30
PLAN ACTIONS:
Step 1: Move above source_object at source_pos with > source height.
Step 2: Position the gripper at the base of the source_object on the table surface.
Step 3: Close gripper at the same position to pick up source_object.
Step 4: Lift source_object at source_pos to height > target height.
Step 5: Move to target_object location at target_pos: <|22-13|><|local-0-1|> at the same height as stage 4.
Step 6: Move on top of target_object location at target_pos with height target_height cause the container is empty.
Step 7: Open gripper to drop the <|silver|><|cube|> into <|azure|><|container|>.
| [{"azure-container": [88, 53, 30]}, {"yellow-star": [73, 11, 27]}, {"silver-cube": [63, 22, 3]}, {"white-container": [21, 43, 25]}, {"yellow-container": [74, 45, 10]}, {"lime-moon": [78, 20, 20]}] | Pick up the cube and place it into the azure container | [
[
63,
22,
13,
0,
60,
90,
1
],
[
63,
22,
0,
0,
60,
90,
1
],
[
63,
22,
0,
0,
60,
90,
0
],
[
63,
22,
14,
0,
60,
90,
0
],
[
88,
53,
14,
0,
60,
90,
0
],
[
88... | [
{
"content": "You are a spatial reasoning assistant for a Franka Panda robot with a parallel gripper. Your task is to generate precise action sequences to accomplish object manipulation tasks.\n\n## INPUT ENVIRONMENT:\n- The workspace is a table surface represented as a 100x100 discrete grid, divided into a 25x... |
[{"<|maroon|><|triangular prism|>": ["<|6-16|><|local-0-1|>", 15]}] | [{"<|yellow|><|container|>": ["<|18-13|><|local-0-3|>", 2]}] | LOCATE OBJECTS:
Target Object: <|maroon|><|triangular prism|> found at <|6-16|><|local-0-1|> with height 15
Target Placement Location: <|yellow|><|container|> at <|18-13|><|local-0-3|> with height 2
PLAN ACTIONS:
Step 1: Move above source_object at source_pos with > source height.
Step 2: Position the gripper at the base of the source_object on the table surface.
Step 3: Close gripper at the same position to pick up source_object.
Step 4: Lift source_object at source_pos to height > target height.
Step 5: Move to target_object location at target_pos: <|18-13|><|local-0-3|> at the same height as stage 4.
Step 6: Move on top of target_object location at target_pos with height target_height cause the container is empty.
Step 7: Open gripper to drop the <|maroon|><|triangular prism|> into <|yellow|><|container|>.
| [{"yellow-container": [72, 55, 2]}, {"azure-cylinder": [10, 77, 11]}, {"purple-cube": [7, 64, 6]}, {"purple-container": [89, 49, 12]}, {"maroon-triangular prism": [24, 65, 15]}, {"azure-star": [18, 52, 16]}] | Pick up the triangular prism and place it into the yellow container | [
[
24,
65,
25,
0,
60,
90,
1
],
[
24,
65,
0,
0,
60,
90,
1
],
[
24,
65,
0,
0,
60,
90,
0
],
[
24,
65,
25,
0,
60,
90,
0
],
[
72,
55,
25,
0,
60,
90,
0
],
[
72... | [
{
"content": "You are a spatial reasoning assistant for a Franka Panda robot with a parallel gripper. Your task is to generate precise action sequences to accomplish object manipulation tasks.\n\n## INPUT ENVIRONMENT:\n- The workspace is a table surface represented as a 100x100 discrete grid, divided into a 25x... |
[{"<|navy|><|star|>": ["<|23-1|><|local-2-3|>", 23]}] | [{"<|gray|><|container|>": ["<|16-19|><|local-1-3|>", 21]}] | LOCATE OBJECTS:
Target Object: <|navy|><|star|> found at <|23-1|><|local-2-3|> with height 23
Target Placement Location: <|gray|><|container|> at <|16-19|><|local-1-3|> with height 21
PLAN ACTIONS:
Step 1: Move above source_object at source_pos with > source height.
Step 2: Position the gripper at the base of the source_object on the table surface.
Step 3: Close gripper at the same position to pick up source_object.
Step 4: Lift source_object at source_pos to height > target height.
Step 5: Move to target_object location at target_pos: <|16-19|><|local-1-3|> at the same height as stage 4.
Step 6: Move on top of target_object location at target_pos with height target_height cause the container is empty.
Step 7: Open gripper to drop the <|navy|><|star|> into <|gray|><|container|>.
| [{"navy-star": [94, 7, 23]}, {"navy-cube": [85, 89, 23]}, {"green-container": [37, 22, 4]}, {"gray-container": [65, 79, 21]}, {"maroon-container": [6, 73, 5]}] | Pick up the star and place it into the gray container | [
[
94,
7,
33,
0,
60,
90,
1
],
[
94,
7,
0,
0,
60,
90,
1
],
[
94,
7,
0,
0,
60,
90,
0
],
[
94,
7,
33,
0,
60,
90,
0
],
[
65,
79,
33,
0,
60,
90,
0
],
[
65,
... | [
{
"content": "You are a spatial reasoning assistant for a Franka Panda robot with a parallel gripper. Your task is to generate precise action sequences to accomplish object manipulation tasks.\n\n## INPUT ENVIRONMENT:\n- The workspace is a table surface represented as a 100x100 discrete grid, divided into a 25x... |
End of preview. Expand
in Data Studio
- Downloads last month
- 105
Size of downloaded dataset files:
794 MB
Size of the auto-converted Parquet files:
794 MB
Number of rows:
360,000