OpenBMB’s 0.9B MiniCPM-RobotTrack brings offline vision-language tracking to Unitree Go2
CyberRobooo · x · 2026-07-24
MiniCPM-RobotTrack targets offline tracking on Unitree Go2
OpenBMB’s MiniCPM-RobotTrack is a compact 0.9B end-to-end vision-language tracking model natively adapted to Unitree Go2 Edu.
- Runs fully locally and offline, reducing latency, privacy risk, and reliability issues
- Can keep tracking even after the network disconnects
- Reported to work well in dynamic and ambiguous scenarios such as patrol, escort, and disaster relief
- The benchmark chart shows it outperforming larger baselines on multiple tracking metrics
Related event: OpenBMB Open-Sources MiniCPM-Robot for Offline Embodied AI(10 posts)→
More from Embodied
- π0.5 study: raising demos from 10 to 438 lifts Place Ball in Bowl success from 7% to 83% — stingning · 2026-10-27
- GPT-6 Astra controls dexterous hands zero-shot at just 5.2% success in 500 trials — stingning · 2026-10-27
- HandsOn benchmark: 66 verified tasks and 18,000 human demos for dexterous manipulation — stingning · 2026-10-27
- DexPort: a handheld interface with a real robot hand for dexterous-hand data collection — pabbeel · 2026-10-27
- ROS names Alejandro Hernández Cordero new project lead, eyes 2027 release — ___Mufasaa · 2026-10-27
- ROS Meetup coming to Google's NYC office Oct 29 with speakers from Tangent, Cohesive Robotics, Intrinsic — kscottz · 2026-10-27