REVIEW 16 cited by
RaC: Robot Learning for Long-Horizon Tasks by Scaling Recovery and Correction
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
RaC: Robot Learning for Long-Horizon Tasks by Scaling Recovery and Correction
read the original abstract
Modern paradigms for robot imitation train expressive policy architectures on large amounts of human demonstration data. Yet performance on contact-rich, deformable-object, and long-horizon tasks plateau far below perfect execution, even with thousands of expert demonstrations. This is due to the inefficiency of existing ``expert'' data collection procedures based on human teleoperation. To address this issue, we introduce RaC, a new phase of training on human-in-the-loop rollouts after imitation learning pre-training. In RaC, we fine-tune a robotic policy on human intervention trajectories that illustrate recovery and correction behaviors. Specifically, during a policy rollout, human operators intervene when failure appears imminent, first rewinding the robot back to a familiar, in-distribution state and then providing a corrective segment that completes the current sub-task. Training on this data composition expands the robotic skill repertoire to include retry and adaptation behaviors, which we show are crucial for boosting both efficiency and robustness on long-horizon tasks. Across three real-world bimanual control tasks: shirt hanging, airtight container lid sealing, takeout box packing, and a simulated assembly task, RaC outperforms the prior state-of-the-art using 10$\times$ less data collection time and samples. We also show that RaC enables test-time scaling: the performance of the trained RaC policy scales linearly in the number of recovery maneuvers it exhibits. Videos of the learned policy are available at https://rac-scaling-robot.github.io/.
Forward citations
Cited by 16 Pith papers
-
Closing the Lab-to-Store Gap: A Data-Efficient Post-Training and Experience-Driven Learning VLA Framework for Retail Humanoids
On a real humanoid restocking chips, a data-efficient post-training pipeline raised success from 0% to 32%, one experience-driven refinement pass to 42%, and a second pass dropped it to 22%.
-
EgoRecovery: Acquiring Failure Recovery Ability Through Human Recovery Demonstration
EgoRecovery co-trains robot recovery policies from egocentric human recovery videos by sharing a gated corrective-intent bottleneck, raising average closed-loop recovery success from 52.5% (robot-only) to 85% on four ...
-
VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon
VLA-Corrector adds a detect-and-correct inference layer using a latent vision monitor and online gradient guidance to enable adaptive action horizons in chunked VLA policies.
-
ReGuide: From Test-Time Guidance to Self-Improving Diffusion Policies
ReGuide is a self-improving framework that uses phase-conditioned guidance to generate corrective rollouts and absorbs successful ones back into diffusion policy training, yielding 1.3-7.7x success gains on Robomimic tasks.
-
Set-Supervised Diffusion Policy: Learning Action-Chunking Diffusion through Corrections
SDP constructs sets of desired action-chunks from human correction pairs and trains diffusion policies to align with those sets, yielding better performance and robustness than standard behavior cloning on robotic tasks.
-
Hand-in-the-Loop: Improving VLA Policies for Dexterous Manipulation via Seamless Hand-Arm Intervention
HandITL blends human intent with policy execution to eliminate gesture jumps in dexterous VLA interventions, cutting jitter by 99.8%, grasp failures by 87.5%, and yielding 19% better refined policies.
-
Hand-in-the-Loop: Improving VLA Policies for Dexterous Manipulation via Seamless Hand-Arm Intervention
HandITL enables seamless human intervention in VLA policies for bimanual dexterous manipulation, cutting jitter by 99.8% and improving refined policies by 19% over standard teleoperation.
-
UniSteer: Unified Noise Steering for Efficient Human-Guided VLA Adaptation
By inverting a frozen flow-matching robot policy with fixed-point iteration, UniSteer converts human corrections into noise-space supervision and lifts real-world VLA adaptation success from 20% to 90% in about 66 min...
-
UniSteer: Unified Noise Steering for Efficient Human-Guided VLA Adaptation
UniSteer unifies human corrective actions and noise-space RL for VLA adaptation by inverting actions to noise targets, raising success rates from 20% to 90% in 66 minutes across four real-world manipulation tasks.
-
TAMEn: Tactile-Aware Manipulation Engine for Closed-Loop Data Collection in Contact-Rich Tasks
TAMEn supplies a cross-morphology wearable interface and pyramid-structured visuo-tactile data regime that raises bimanual manipulation success rates from 34% to 75% via closed-loop collection.
-
ARM: Advantage Reward Modeling for Long-Horizon Manipulation
ARM trains reward models on Progressive/Regressive/Stagnant labels to enable adaptive reweighting in offline RL, reaching 99.4% success on towel-folding with minimal human intervention.
-
RISE: Self-Improving Robot Policy with Compositional World Model
RISE combines a controllable dynamics model and progress value model into a closed-loop self-improving pipeline that updates robot policies entirely in imagination, reporting over 35% absolute gains on three real-world tasks.
-
$\pi^{*}_{0.6}$: a VLA That Learns From Experience
RECAP enables a generalist VLA to self-improve via advantage-conditioned RL on mixed real-world data, more than doubling throughput and halving failure rates on hard manipulation tasks.
-
DexPIE: Stable Dexterous Policy Improvement from Real-World Experience
DexPIE improves dexterous manipulation success rates by 37% over demo policies via real-world experience collection with adapted intervention, multi-stage DAgger, asynchronous relative-action inference, and optimality...
-
DeMaVLA: A Vision-Language-Action Foundation Model for Generalizable Deformable Manipulation
DeMaVLA is a VLA foundation model using a pruned action expert and flow matching, pre-trained on 5000 hours of real demonstrations and post-trained on multi-task folding data with human-in-the-loop correction, reporti...
-
FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement
FAR combines failure-contrastive preference adaptation with action perturbations for test-time recovery and continual policy improvement, reporting 17.6% and 11.7% success gains over diffusion policies in simulation a...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.