Devanthro Robody: version history

Current record →

Nothing is deleted from the index. Every change to this record is kept: a full copy of each version since 6 Sep 2026, 05:24 UTC, and the field-by-field updates applied before that. See every robot from Devanthro.

Versions · 3 recorded

Version 375 · 18 Sep 2026, 02:01 UTC · score then 38.7
- ai model: Proprietary physical AI and imitation learning trained on real-world teleoperation episodes → Imitation learning and behavior cloning pipeline trained from human teleoperation episodes
- form factor: bipedal → wheeled-base
- onboard compute: NVIDIA Jetson Orin + Jetson Orin Nano → Dual Nvidia Jetson AGX Orin and Jetson Orin Nano
Changed by: Update Robody (confirmed: ai_model, onboard_compute, form_factor) (research agent)
Version 263 · 15 Sep 2026, 04:28 UTC · score then 38.7

No field changed; the score was recalculated.

Changed by a direct correction or a scoring update, not a research proposal.
First recorded version · 6 Sep 2026, 05:24 UTC · score then 38.7

The record as it stood when full copies began to be kept.

Earlier changes · 2, before full copies were kept

Update Robody · 2026-09-02 22:46 UTC · published automatically
- autonomy level: supervised-autonomy → teleoperated
- form factor: wheeled-base → bipedal
- deployments: updated
Update Robody · 2026-08-23 01:04 UTC · research agent
- autonomy level: teleoperated → supervised-autonomy
- ai model: AI automation for routine tasks combined with human VR teleoperation over 5G → Proprietary physical AI and imitation learning trained on real-world teleoperation episodes
- onboard compute: — → NVIDIA Jetson Orin + Jetson Orin Nano
- height (cm): — → 165
- weight (kg): — → 60
- total dof: 28 → 17
- hand dof per hand: — → 1
- dexterous hands: — → False
- deployments: updated
- first unveiled year: 2024 → 2023