Unitree CEO: Robots to Beat Bolt's Speed by Mid-Year

๐กHumanoid robots set to smash Bolt's sprint record by mid-2024 โ robotics benchmark leap.
โก 30-Second TL;DR
What Changed
Wang Xingxing predicts mid-2024 humanoid robot 100m under 10s
Why It Matters
Rapid robotics speed gains highlight embodied AI progress, potentially enabling new applications in dynamic environments like search-and-rescue or sports training. China's lead could intensify global competition in humanoid tech.
What To Do Next
Track Unitree's GitHub or demos for open-source locomotion controllers.
Key Points
- โขWang Xingxing predicts mid-2024 humanoid robot 100m under 10s
- โขSurpassing Bolt's 9.58s record globally, led by China
- โขFollows Zhejiang University's Bolt robot developments
๐ง Deep Insight
Background and context from public sources โ not the original article. 4 sources cited.
๐ Enhanced Key Takeaways
- โขUnitree's H1 V3.0 achieved a Guinness World Record speed of 3.3 m/s (7.38 mph) for full-sized humanoid robots in March 2024, surpassing Boston Dynamics' Atlas at 2.5 m/s (5.59 mph).[1][2]
- โขUnitree H1 is equipped with a depth camera, 3D LiDAR for vision, 5 degrees of freedom in leg joints, 4 in arms, and an advanced powertrain for superior speed and maneuverability.[1]
- โขA newer robot, STAR1 from Robot Era, reached 3.6 m/s (8 mph) across varied terrains like the Gobi Desert with AI processing at 275 TOPS and 12 degrees of freedom, exceeding H1's record using specialized footwear.[4]
๐ Competitor Analysisโธ Show
| Feature | Unitree H1 V3.0 | Boston Dynamics Atlas | Robot Era STAR1 |
|---|---|---|---|
| Top Speed | 3.3 m/s (7.38 mph)[1][2] | 2.5 m/s (5.59 mph)[1] | 3.6 m/s (8 mph)[4] |
| Vision Sensors | Depth camera, 3D LiDAR[1] | Not specified | AI hardware 275 TOPS[4] |
| DOF (Legs/Arms) | 5/4[1] | Not specified | 12 total[4] |
| Terrain Handling | Flat surface, complex terrains[1] | Not specified | Desert, gravel (w/ shoes)[4] |
๐ ๏ธ Technical Deep Dive
- โขH1 V3.0 features an innovative powertrain enabling 3.3 m/s linear walking on flat surfaces, with capabilities for autonomous navigation on complex terrains, jumping, and stair climbing.[1][2]
- โขEquipped with depth camera and 3D LiDAR for vision; leg joints have 5 degrees of freedom (DOF), arms have 4 DOF; initial versions lack hands, using padded arm ends.[1]
- โขPowered for dynamic stability, recovers balance after disturbances like kicks; claims potential speeds up to 11 mph in some demos.[1][2]
๐ฎ Future ImplicationsAI analysis grounded in cited sources
โณ Timeline
๐ Sources (4)
Factual claims are grounded in the sources below. Forward-looking analysis is AI-generated interpretation.
Weekly AI Recap
Read this week's curated digest of top AI events โ
๐Related Updates
AI-curated news aggregator. All content rights belong to original publishers.
Original source: TechNode โ
This is a summary, not the original. Read the source, or get the weekly briefing.
Weekly AI briefing
One email a week. Unsubscribe anytime.