arXiv:2610.17748v1 Announce Type: cross Abstract: Policies trained offline from teleoperated demonstrations can degrade outside their training distribution. This gap is particularly acute in long-hor...
DexPIE is a post‑training framework that improves dexterous manipulation policies using real‑world experience. It introduces a dexterous‑hand‑adapted intervention system and multi‑stage DAgger‑style data collection to enhance exploration, aligns training and inference to reduce distribution shift, and conditions the policy on a continuous optimality indicator for fine‑grained data quality use. In three real‑world tasks, DexPIE boosts success rates by 37.3% over a demonstration‑based baseline, outperforming all other methods and showing stronger robustness.
arXiv:2609.37599v1 Announce Type: cross Abstract: Robot policies are frequently trained from human corrections, yet teleoperating a robot to provide corrections is burdensome, and human demonstrators...
Whole-Body Dexterity (WBD) is a framework that enables robots to use their entire body and appendages as contact surfaces for grasping and manipulating objects. The approach generates a dataset of feasible whole-body grasps, trains reinforcement‑learning experts on a repositioning objective, and distills them into a single policy that relies on proprioception and object geometry. The distilled policy achieves zero‑shot transfer to a real Unitree G1 robot, successfully completing complex tasks such as stowing a box under one arm and moving it from a shelf to a table, with a 90% success rate in real‑world trials.
arXiv:2610.08220v1 Announce Type: cross Abstract: Portable mobile-manipulation demonstrations can help alleviate data scarcity for embodied intelligence, but obtaining reliable, low-cost, and robot-f...
arXiv:2606.22113v2 Announce Type: replace-cross Abstract: Generalizing manipulation policies across robot embodiments remains difficult because standard policies tie the interactions needed for a tas...
HIL-UMI is a policy-guided Universal Manipulation Interface that enables robot‑free, human‑in‑the‑loop post‑training of vision‑language‑action models. By querying the current policy during handheld demonstrations and using an Energy Score to detect out‑of‑distribution states, it selectively collects new data and refines a progress‑based advantage estimator. The updated estimator then drives advantage‑conditioned behavioral cloning, improving performance on long‑horizon and precise manipulation tasks while reducing per‑frame collection time compared to HG‑DAgger.
The paper introduces HiRe-MoMa, a hierarchical residual policy learning framework that fine‑tunes a frozen base policy for mobile manipulation. It uses a policy‑agnostic residual split into mobile‑base and manipulator‑arm heads to reduce gradient interference, and incorporates expert‑guided value alignment to improve sample efficiency with sparse human interventions. Experiments on the TIAGo++ platform show that HiRe‑MoMa boosts task performance after only about 30 minutes of online interaction, regardless of the underlying base policy.
The paper evaluates GPT‑6‑Astra’s performance across 12 robotic benchmarks, showing it achieves unprecedented results when using in‑context learning from training‑set demonstrations. It highlights the benefits and costs of a dual‑system architecture (high‑level reasoning and low‑level control) and identifies practical gaps in real‑world deployment, such as expensive demonstration collection and physical constraints. The authors propose a new benchmark prototype that derives tasks from real‑world needs, omits in‑domain demos, and measures agents against a continuously running world clock.
arXiv:2609.24660v2 Announce Type: cross Abstract: Human demonstrations offer a scalable way to collect manipulation data, but their contacts may be unstable or infeasible when transferred to a robot...
arXiv:2610.07594v1 Announce Type: cross Abstract: Humanoid household manipulation requires the arms to act while the body balances, steps and changes posture. We present BiGym 2.0, an adaptation of B...
arXiv:2608. 15917v1 Announce Type: cross Abstract: Large-scale pre-training has made robot policy fine-tuning increasingly data-efficient, but this progress has largely been driven by datasets and embodiments built around simple parallel-jaw grippers.