VQV Signal

ROBOTS & HARDWARE WATCH TECHNICAL

RoboSkills adds agent that generates humanoid and character motion with object contact

According to a post on X by @gengchen, the team behind a motion-generation skill in RoboSkills released it. Given text, images or video, an agent selects motion models, builds the scene and objects, retargets motion to a character or humanoid robot, and refines poses, timing and contacts using rendered feedback. A fixed workflow that does not use an agent is also available for motion without object interaction. The post was surfaced by Scobleizer News Pulse, and the source snippet does not give further figures or benchmarks.

Source: Scobleizer News Pulse (X) · x.com Found via Robert Scoble’s Scobleizer News Pulse · a post on X, not independently verified Published 2026-11-03T01:45:00+00:00 Detected 2026-11-03T06:27:22+00:00
View original source

According to a post on X by @gengchen, the team behind a motion-generation skill in RoboSkills released it. Given text, images or video, an agent selects motion models, builds the scene and objects, retargets motion to a character or humanoid robot, and refines poses, timing and contacts using rendered feedback. A fixed workflow that does not use an agent is also available for motion without object interaction. The post was surfaced by Scobleizer News Pulse, and the source snippet does not give further figures or benchmarks.

AI-assisted summary based on the listed source.

@gengchen's team released a motion-generation skill in RoboSkills: given text, images or video, an agent picks motion models, builds the scene and objects, retargets to a character or humanoid robot and refines poses, timing and contacts from rendered feedback. A fixed agent-free workflow is also available for...

Builders working on animation, simulation or humanoid robotics could use this to produce motion with object contact from text, images or video instead of authoring it by hand. The source describes the benefit as cheaper motion authoring, but it does not provide cost or performance data to confirm that claim. Watch for independent tests of output quality and for wider availability beyond the initial release.

Hardware and robotics watchers may want to track whether this becomes a product, benchmark, or deployment signal.

Signal Strength 91% Technical label WATCH Public Interest 42 Category ROBOTS & HARDWARE Reader Depth TECHNICAL

Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.

Public Interest components
Recognizable Entity Score 0 Practical Impact Score 18 Novelty Interest Score 94 Consequence Score 30 Curiosity Score 100 Shareability Score 48

VQV surfaced this signal because it is recent, relevant to Robotics, connected to Scobleizer News Pulse (X).