REVIEW 9 cited by
DexterityGen: Foundation Controller for Unprecedented Dexterity
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Teaching robots dexterous manipulation skills, such as tool use, presents a significant challenge. Current approaches can be broadly categorized into two strategies: human teleoperation (for imitation learning) and sim-to-real reinforcement learning. The first approach is difficult as it is hard for humans to produce safe and dexterous motions on a different embodiment without touch feedback. The second RL-based approach struggles with the domain gap and involves highly task-specific reward engineering on complex tasks. Our key insight is that RL is effective at learning low-level motion primitives, while humans excel at providing coarse motion commands for complex, long-horizon tasks. Therefore, the optimal solution might be a combination of both approaches. In this paper, we introduce DexterityGen (DexGen), which uses RL to pretrain large-scale dexterous motion primitives, such as in-hand rotation or translation. We then leverage this learned dataset to train a dexterous foundational controller. In the real world, we use human teleoperation as a prompt to the controller to produce highly dexterous behavior. We evaluate the effectiveness of DexGen in both simulation and real world, demonstrating that it is a general-purpose controller that can realize input dexterous manipulation commands and significantly improves stability by 10-100x measured as duration of holding objects across diverse tasks. Notably, with DexGen we demonstrate unprecedented dexterous skills including diverse object reorientation and dexterous tool use such as pen, syringe, and screwdriver for the first time.
Forward citations
Cited by 9 Pith papers
-
UniCross: Unified Cross-Skill Dexterous Manipulation Synthesis
Grasping, relocation, in-hand rotation, and translation share one relational state/action/reward structure, so ten expert policies distill into one cross-skill controller that chains and generalizes in simulation.
-
Towards Human-level Dexterous Teleoperation
A single-stage RL co-tracking controller trained on consecutive human-derived hand–object subgoals achieves ~75% real-robot success on long-horizon dexterous teleoperation where baselines fail.
-
Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?
Task-agnostic RL play pretraining on diverse objects yields a reusable dexterous prior that makes sparse-reward assembly learning ~33× more sample-efficient and enables zero-shot sim-to-real transfer on tight insertio...
-
PTLD: Sim-to-real Privileged Tactile Latent Distillation for Dexterous Manipulation
PTLD distills real privileged tactile data into a state estimator to boost sim-to-real performance of proprioceptive dexterous manipulation policies, yielding 182% improvement on in-hand rotation and 57% on reorientat...
-
Scaling Cross-Embodiment World Models for Dexterous Manipulation
A single particle-based world model trained on many simulated robot hands and real human hands can plan dexterous manipulation on robot hands it never trained on.
-
TypeTele: Releasing Dexterity in Teleoperation by Dexterous Manipulation Types
A type-guided teleoperation system that selects predefined dexterous hand poses with a language model outperforms retargeting-based teleoperation on nine real-world tasks and improves imitation learning success.
-
FlashBack: Consistency Model-Accelerated Shared Autonomy
Consistency model distillation enables one-step denoising of user actions for shared autonomy, achieving faster assistance than DDPM-based methods with comparable or better task success.
-
The Latent Color Subspace: Emergent Order in High-Dimensional Chaos
FLUX.1’s VAE latent space contains an interpretable Hue–Saturation–Lightness structure that enables training-free color prediction and control via closed-form latent edits.
-
Going with the Flow: Koopman Behavioral Models as Pseudo Planners for Visuo-Motor Dexterity
A single learned linear Koopman model over coupled visual and proprioceptive states generates full-horizon dexterous manipulation plans and triggers replanning when its own visual predictions diverge from reality.
Discussion (0). Continue with ORCID to comment.