Podcast discussion on Delta Intelligence's generalist humanoid foundation model
This post relays a recommendation to listen to a podcast episode featuring founders of Delta Intelligence, who describe their full-body foundation model capable of long-horizon loco-manipulation at human speed using a delta action space for seamless human intervention. The content serves as an opinion piece promoting the technology rather than reporting independent research results or deployment data.
The author relays a promotional podcast episode discussing Delta Intelligence's generalist humanoid model, noting claims of human-speed operation and contact-rich interaction without independent verification of deployment readiness or specific benchmark metrics.
Source: Chris Paxton — X Robotics · Read original article ↗
Article text · Original source · English
If you are excited by humanoid robotics you owe it to yourself to check out @delta_intelli -- really fluent, natural, contact-rich humanoid whole body loco-manipulation, operating at roughly human speed and in human environments, using one generalist model. Take a look at our podcast with their founders @siyuanhuang95 and @jeasinema on @RoboPapers ->
Delta Intelligence’s Δ₀ is a humanoid full-body foundation model, which can perform long-horizon, whole body loco-manipulation. They show a single, generalist policy which can control a 69-DoF humanoid to perform everyday tasks at nearly human speed — using whole-body human data for large-scale pretraining. @jeasinema and @siyuanhuang95 tell us more about how they achieved this, and about the importance of jointly designing policy and controller. Delta uses a delta action space, for example, which makes it easy to provide human interventions without interrupting the whole body controller: a human operator can correct the robot seamlessly while it works. They show a wide range of impressive humanoid loco manipulation tasks using their generalist model. Learn more on Episode 115 of RoboPapers, with @micoolcho and @chris_j_paxton!
Original source
Delta Intelligence’s Δ₀ is a humanoid full-body foundation model, which can perform long-horizon, whole body loco-manipulation. They show a single, generalist policy which can control a 69-DoF humanoid to perform everyday tasks at nearly human speed — using whole-body human data for large-scale pretraining. @jeasinema and @siyuanhuang95 tell us more about how they achieved this, and about the importance of jointly designing policy and controller. Delta uses a delta action space, for example, which makes it easy to provide human interventions without interrupting the whole body controller: a human operator can correct the robot seemlessly while it works. They show a wide range of impressive humanoid loco manipulation tasks using their generalist model. Learn more on Episode 115 of RoboPapers, with @micoolcho and @chris_j_paxton!
Source：Chris Paxton · x.com