EXOKERN1 commited on
Commit
c0495db
·
verified ·
1 Parent(s): edd4095

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -5
README.md CHANGED
@@ -2,7 +2,7 @@
2
  title: EXOKERN
3
  emoji: ⚡
4
  colorFrom: blue
5
- colorTo: purple
6
  sdk: static
7
  pinned: false
8
  short_description: The Data Engine for Physical AI
@@ -10,42 +10,58 @@ short_description: The Data Engine for Physical AI
10
 
11
  # EXOKERN — The Data Engine for Physical AI
12
 
13
- **Contact-rich. Sensor-annotated. Industrially validated.**
14
 
15
- We produce high-fidelity force/torque manipulation datasets for enterprise robotics, humanoid robot manufacturers, and research institutions.
16
 
17
  ## 🎯 The Problem
18
 
19
  Over 95% of existing robotics datasets lack force/torque sensor data. Vision-only approaches fail at contact-rich tasks like insertion, assembly, and manipulation — where precise haptic feedback is critical.
20
 
 
 
21
  ## 💡 Our Solution
22
 
23
  EXOKERN provides industrially calibrated **6-axis force/torque (wrench) data** alongside standard observations, enabling robots to learn manipulation skills that require physical contact understanding.
24
 
 
 
 
 
 
 
 
 
25
  ## 📦 Datasets
26
 
27
  | Dataset | Task | F/T Data | Status |
28
  |---------|------|----------|--------|
29
  | [contactbench-forge-peginsert-v0](https://huggingface.co/datasets/EXOKERN/contactbench-forge-peginsert-v0) | Peg-in-Hole Insertion | ✅ 6-axis Wrench | Available |
30
 
 
 
31
  ## 🔧 What Makes Our Data Different
32
 
33
  - **Force/Torque annotations** on every frame (Fx, Fy, Fz, Mx, My, Mz)
34
  - **LeRobot v3.0 compatible** — plug directly into policy training pipelines
35
  - **Industrially relevant tasks** — insertion, assembly, contact-rich manipulation
36
  - **Calibrated sensors** — not estimated, not vision-derived, directly measured
 
 
37
 
38
  ## 🏗️ Built With
39
 
40
  - NVIDIA Isaac Lab for high-fidelity physics simulation
41
  - LeRobot v3.0 format for interoperability
42
- - Franka Emika Panda (7-DOF) robot platform
 
43
 
44
  ## 📬 Contact
45
 
46
  - 🌐 Website: [exokern.com](https://exokern.com)
47
  - 🤗 HuggingFace: [huggingface.co/EXOKERN](https://huggingface.co/EXOKERN)
 
48
 
49
  ---
50
 
51
- *EXOKERN — Where Force Meets Intelligence*
 
2
  title: EXOKERN
3
  emoji: ⚡
4
  colorFrom: blue
5
+ colorTo: red
6
  sdk: static
7
  pinned: false
8
  short_description: The Data Engine for Physical AI
 
10
 
11
  # EXOKERN — The Data Engine for Physical AI
12
 
13
+ **Contact-rich. Sensor-annotated. Industrially validated. EU AI Act ready.**
14
 
15
+ We produce high-fidelity force/torque manipulation datasets for enterprise robotics, humanoid robot manufacturers, and research institutions — with full data provenance and compliance documentation.
16
 
17
  ## 🎯 The Problem
18
 
19
  Over 95% of existing robotics datasets lack force/torque sensor data. Vision-only approaches fail at contact-rich tasks like insertion, assembly, and manipulation — where precise haptic feedback is critical.
20
 
21
+ Starting August 2026, the EU AI Act requires documented data provenance for AI training data. Most existing datasets cannot meet this standard.
22
+
23
  ## 💡 Our Solution
24
 
25
  EXOKERN provides industrially calibrated **6-axis force/torque (wrench) data** alongside standard observations, enabling robots to learn manipulation skills that require physical contact understanding.
26
 
27
+ ### Capture → Anchor → Ship
28
+
29
+ | Phase | What We Do | Output |
30
+ |-------|-----------|--------|
31
+ | **01 Capture** | Operators generate specific contact forces incl. systematic failures in calibrated environments | Raw data + Failure Taxonomy + QC Report |
32
+ | **02 Anchor** | Real friction logs calibrate simulation. Physics parameters validated against F/T measurements | Calibrated Sim Assets (MJCF/USD/JSON) |
33
+ | **03 Ship** | ML-ready exports in all major formats — clean, tagged, quality-certified | RLDS, HDF5, Zarr, MCAP, LeRobot v3.0 |
34
+
35
  ## 📦 Datasets
36
 
37
  | Dataset | Task | F/T Data | Status |
38
  |---------|------|----------|--------|
39
  | [contactbench-forge-peginsert-v0](https://huggingface.co/datasets/EXOKERN/contactbench-forge-peginsert-v0) | Peg-in-Hole Insertion | ✅ 6-axis Wrench | Available |
40
 
41
+ > 🗺️ *More contact-rich datasets in development — including assembly, grasping, and deformable object manipulation. Commercial Contact Skill Packs available for enterprise customers.*
42
+
43
  ## 🔧 What Makes Our Data Different
44
 
45
  - **Force/Torque annotations** on every frame (Fx, Fy, Fz, Mx, My, Mz)
46
  - **LeRobot v3.0 compatible** — plug directly into policy training pipelines
47
  - **Industrially relevant tasks** — insertion, assembly, contact-rich manipulation
48
  - **Calibrated sensors** — not estimated, not vision-derived, directly measured
49
+ - **Full data provenance** — capture methodology, operator ID, QC reports, EU AI Act compliant
50
+ - **Sim-anchoring** — calibrated simulation assets bridge the Sim2Real gap
51
 
52
  ## 🏗️ Built With
53
 
54
  - NVIDIA Isaac Lab for high-fidelity physics simulation
55
  - LeRobot v3.0 format for interoperability
56
+ - Franka FR3 (7-DOF) robot platform
57
+ - Bota Systems SensONE 6-axis F/T sensor
58
 
59
  ## 📬 Contact
60
 
61
  - 🌐 Website: [exokern.com](https://exokern.com)
62
  - 🤗 HuggingFace: [huggingface.co/EXOKERN](https://huggingface.co/EXOKERN)
63
+ - 📧 Enterprise inquiries: info@exokern.com
64
 
65
  ---
66
 
67
+ *EXOKERN — Bridging the Haptic Data Gap in Physical AI*