WARP trains a reward model on time-warped successful demonstrations to produce frame-level progress estimates that upweight high-advantage chunks during behavior cloning, maintaining high success rates on suboptimal datasets where vanilla BC fails.
super hub Canonical reference
Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware
Canonical reference. 72% of citing Pith papers cite this work as background.
215
Pith papers citing it
Background
72% of classified citations
abstract
Fine manipulation tasks, such as threading cable ties or slotting a battery, are notoriously difficult for robots because they require precision, careful coordination of contact forces, and closed-loop visual feedback. Performing these tasks typically requires high-end robots, accurate sensors, or careful calibration, which can be expensive and difficult to set up. Can learning enable low-cost and imprecise hardware to perform these fine manipulation tasks? We present a low-cost system that performs end-to-end imitation learning directly from real demonstrations, collected with a custom teleoperation interface. Imitation learning, however, presents its own challenges, particularly in high-precision domains: errors in the policy can compound over time, and human demonstrations can be non-stationary. To address these challenges, we develop a simple yet novel algorithm, Action Chunking with Transformers (ACT), which learns a generative model over action sequences. ACT allows the robot to learn 6 difficult tasks in the real world, such as opening a translucent condiment cup and slotting a battery with 80-90% success, with only 10 minutes worth of demonstrations. Project website: https://tonyzhaozh.github.io/aloha/
hub tools
citation-role summary
background 36
method 8
baseline 4
dataset 1
other 1
citation-polarity summary
claims ledger
- abstract Fine manipulation tasks, such as threading cable ties or slotting a battery, are notoriously difficult for robots because they require precision, careful coordination of contact forces, and closed-loop visual feedback. Performing these tasks typically requires high-end robots, accurate sensors, or careful calibration, which can be expensive and difficult to set up. Can learning enable low-cost and imprecise hardware to perform these fine manipulation tasks? We present a low-cost system that performs end-to-end imitation learning directly from real demonstrations, collected with a custom teleop
authors
co-cited works
representative citing papers
ForesightSafety-VLA creates a diagnostic benchmark for VLA safety with taxonomy across physical, language, and visual risks, showing perception and structure variations cause more safety degradation than language changes in tested models.
X-Tokenizer creates semantic action tokens via asymmetric residual quantization and contrastive pretraining on large trajectory data, outperforming prior methods like FAST on robotic tasks.
ActProbe is an action-space detector that uses temporal consistency error and action chunk magnitude from policy outputs, mapped via LSTM-MLP, to predict failures earlier than baselines across policies and real-robot tasks.
Affordance2Action introduces A2A-Bench, a manipulation-oriented benchmark for scene-level task-conditioned affordance grounding covering single- and multi-region correspondences, plus an annotation pipeline, and reports gaps in existing segmentation and VLM baselines.
DVAC uses denoising variance as an intrinsic signal to adaptively chunk actions in flow-based robot policies, improving success rates and cutting replans on LIBERO, RoboTwin, CALVIN, and real-world tasks.
The paper identifies a deployment safety gap in VLA policies where identical checkpoints can be executable-inequivalent due to action metadata mismatches, supported by a derived closed-form transform and empirical drift measurements on LIBERO benchmarks.
PhAIL provides an open benchmark and distributional evaluation method for real-robot VLA policies using time-to-success CDF, HRT scoring, and KS significance tests.
VLA architectures exhibit architecture-specific failure signatures at the motor-command level, with direction reversal as a universal predictor and velocity monitoring ineffective for continuous models.
Soft RTC uses partially denoised states for overlap tokens and token-wise blending to reduce action delta and jerk by ~9% versus hard RTC while matching solve rates on Kinetix levels.
JOPAT jointly models pixels, point tracks, and actions in a diffusion transformer and reports gains over pixel-only baselines on long-horizon robot tasks with occlusion and off-screen motion.
The paper identifies distinct failure mechanisms: excessive posterior-prior regularization erases mode information in latent policies, while smooth base-to-action maps limit mode coverage in generative policies.
RoboFlow4D is an end-to-end lightweight flow world model that predicts multi-frame 3D flows from visual observations and textual instructions to provide explicit planning for real-time robotic manipulation.
DSSP is a history-conditioned diffusion state space policy that uses SSMs to encode full observation streams with an auxiliary dynamics objective and hierarchical fusion, achieving SOTA results with reduced model size in robot manipulation.
A new speculative inference system speeds up diffusion VLAs to 19.1 ms average latency (3.04x faster) on LIBERO by replacing most full 58 ms inferences with 7.8 ms draft rounds while preserving task performance.
A morphologically equivariant flow matching policy for bimanual robots enforces reflective symmetry to improve sample efficiency and enable zero-shot generalization to mirrored task configurations.
MCF-Proto adds a motion-centric local action frame and prototype parameterization to VLA models, inducing emergent geometric structure and improved robustness from standard demonstrations alone.
Pace-and-Path Correction decomposes a quadratic cost minimization into orthogonal pace and path channels to correct chunked actions in VLA models, raising success rates by up to 28.8% in dynamic settings.
Reducing visual input to one token per frame in VLA world models maintains or improves long-horizon performance on MetaWorld, LIBERO, and real-robot tasks.
PhySPRING uses differentiable GNNs to learn hierarchical coarsened spring-mass topologies and parameters from observations, delivering up to 2.3x speedup on PhysTwin benchmarks and comparable robot policy success rates in zero-shot Real2Sim substitution.
BrickCraft composes reusable visuomotor skills via relative anchoring to partial structures and situated visual manuals to achieve long-horizon interlocking brick assembly from limited demonstrations with generalization to unseen designs.
OA-WAM uses persistent address vectors and dynamic content vectors in object slots to enable addressable world-action prediction, improving robustness on manipulation benchmarks under scene changes.
IAGF-SA adds a physically-grounded channel to shared autonomy by modulating robot impedance to convey intent, improving task performance, agreement, and user experience in three scenarios per user studies.
A 48-camera residential platform delivers real-time occlusion-robust 3D perception and coordinated actuation for multi-human multi-robot interaction in a shared home workspace.
citing papers explorer
-
Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAs
A new speculative inference system speeds up diffusion VLAs to 19.1 ms average latency (3.04x faster) on LIBERO by replacing most full 58 ms inferences with 7.8 ms draft rounds while preserving task performance.
-
Morphologically Equivariant Flow Matching for Bimanual Mobile Manipulation
A morphologically equivariant flow matching policy for bimanual robots enforces reflective symmetry to improve sample efficiency and enable zero-shot generalization to mirrored task configurations.
-
Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models
Pace-and-Path Correction decomposes a quadratic cost minimization into orthogonal pace and path channels to correct chunked actions in VLA models, raising success rates by up to 28.8% in dynamic settings.
-
One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policy
Reducing visual input to one token per frame in VLA world models maintains or improves long-horizon performance on MetaWorld, LIBERO, and real-robot tasks.
-
PhySPRING: Structure-Preserving Reduction of Physics-Informed Twins via GNN
PhySPRING uses differentiable GNNs to learn hierarchical coarsened spring-mass topologies and parameters from observations, delivering up to 2.3x speedup on PhysTwin benchmarks and comparable robot policy success rates in zero-shot Real2Sim substitution.
-
BrickCraft: Visuomotor Skill Composition with Situated Manual Guidance for Long-Horizon Interlocking Brick Assembly
BrickCraft composes reusable visuomotor skills via relative anchoring to partial structures and situated visual manuals to achieve long-horizon interlocking brick assembly from limited demonstrations with generalization to unseen designs.
-
OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation
OA-WAM uses persistent address vectors and dynamic content vectors in object slots to enable addressable world-action prediction, improving robustness on manipulation benchmarks under scene changes.
-
OmniRobotHome: A Multi-Camera Platform for Real-Time Multiadic Human-Robot Interaction
A 48-camera residential platform delivers real-time occlusion-robust 3D perception and coordinated actuation for multi-human multi-robot interaction in a shared home workspace.
-
Atomic-Probe Governance for Skill Updates in Compositional Robot Policies
A cross-version swap protocol reveals dominant skills that swing composition success by up to 50 percentage points, and an atomic probe with selective revalidation governs updates at lower cost than always re-testing full compositions.
-
DiscreteRTC: Discrete Diffusion Policies are Natural Asynchronous Executors
Discrete diffusion policies act as natural asynchronous executors for robotics by treating action generation as iterative unmasking, yielding higher success rates and lower computation than flow-matching real-time chunking in dynamic tasks.
-
VistaBot: View-Robust Robot Manipulation via Spatiotemporal-Aware View Synthesis
VistaBot integrates 4D geometry estimation and spatiotemporal view synthesis into action policies to improve cross-view generalization by 2.6-2.8x on a new VGS metric in simulation and real tasks.
-
ST-BiBench: Benchmarking Multi-Stream Multimodal Coordination in Bimanual Embodied Tasks for MLLMs
ST-BiBench reveals a coordination paradox in which MLLMs show strong high-level strategic reasoning yet fail at fine-grained 16-dimensional bimanual action synthesis and multi-stream fusion.
-
GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization
GuidedVLA improves VLA generalization by supervising individual attention heads with manually defined auxiliary signals for three task-relevant factors.
-
BioProVLA-Agent: An Affordable, Protocol-Driven, Vision-Enhanced VLA-Enabled Embodied Multi-Agent System with Closed-Loop-Capable Reasoning for Biological Laboratory Manipulation
Presents BioProVLA-Agent, a protocol-driven VLA-enabled multi-agent system for embodied biological manipulation with visual state verification and AugSmolVLA augmentation for robustness in wet-lab conditions.
-
When to Trust Imagination: Adaptive Action Execution for World Action Models
A verifier called Future Forward Dynamics Causal Attention enables adaptive action execution in World Action Models, reducing model inferences by 69% and improving success rates in robotic tasks.
-
ConsisVLA-4D: Advancing Spatiotemporal Consistency in Efficient 3D-Perception and 4D-Reasoning for Robotic Manipulation
ConsisVLA-4D adds cross-view semantic alignment, cross-object geometric fusion, and cross-scene dynamic reasoning to VLA models, delivering 21.6% and 41.5% gains plus 2.3x and 2.4x speedups on LIBERO and real-world tasks.
-
BifrostUMI: Bridging Robot-Free Demonstrations and Humanoid Whole-Body Manipulation
BifrostUMI enables robot-free human demonstration capture via VR and wrist cameras to train visuomotor policies that predict keypoint trajectories for transfer to humanoid whole-body control through retargeting.
-
AsyncShield: A Plug-and-Play Edge Adapter for Asynchronous Cloud-based VLA Navigation
AsyncShield restores VLA geometric intent from latency via kinematic pose mapping and uses PPO-Lagrangian to balance tracking with LiDAR safety constraints in a plug-and-play module.
-
RL Token: Bootstrapping Online RL with Vision-Language-Action Models
RL Token enables sample-efficient online RL fine-tuning of large VLAs, delivering up to 3x speed gains and higher success rates on real-robot manipulation tasks within minutes to hours.
-
FingerViP: Learning Real-World Dexterous Manipulation with Fingertip Visual Perception
FingerViP equips each finger with a miniature camera and trains a multi-view diffusion policy that achieves 80.8% success on real-world dexterous tasks previously limited by wrist-camera occlusion.
-
MoRI: Mixture of RL and IL Experts for Long-Horizon Manipulation Tasks
MoRI dynamically mixes RL and IL experts with variance-based switching and IL regularization to reach 97.5% success in four real-world robotic tasks while cutting human intervention by 85.8%.
-
ActiveGlasses: Learning Manipulation with Active Vision from Ego-centric Human Demonstration
ActiveGlasses learns robot manipulation from ego-centric human demos captured with active vision via smart glasses, achieving zero-shot transfer using object-centric point-cloud policies.
-
Multi-View Video Diffusion Policy: A 3D Spatio-Temporal-Aware Video Action Model
MV-VDP jointly predicts multi-view RGB and heatmap videos via diffusion to achieve data-efficient, robust robotic manipulation policies.
-
DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
DreamVLA uses dynamic-region-guided world knowledge prediction, block-wise attention to disentangle information types, and a diffusion transformer for actions, reaching 76.7% success on real robot tasks and 4.44 average length on CALVIN ABC-D.
-
Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations
RIGVid shows that filtered AI-generated videos can serve as effective supervision for complex robotic manipulation tasks without any real demonstrations.
-
FAST: Efficient Action Tokenization for Vision-Language-Action Models
FAST applies discrete cosine transform to robot action sequences for efficient tokenization, enabling autoregressive VLAs to succeed on high-frequency dexterous tasks and scale to 10k hours of data while matching diffusion VLA performance with up to 5x faster training.
-
OpenVLA: An Open-Source Vision-Language-Action Model
OpenVLA achieves 16.5% higher task success than the 55B RT-2-X model across 29 tasks with 7x fewer parameters while enabling effective fine-tuning and quantization without performance loss.
-
Octo: An Open-Source Generalist Robot Policy
Octo is an open-source transformer-based generalist robot policy pretrained on 800k trajectories that serves as an effective initialization for finetuning across diverse robotic platforms.
-
DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
DROID is a new 76k-trajectory in-the-wild robot manipulation dataset spanning 564 scenes and 84 tasks that improves policy performance and generalization when used for training.
-
NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation
NaVid, a video-based VLM trained on 510k navigation and 763k web samples, achieves SOTA VLN performance using only monocular RGB video for next-step action planning in sim and real environments.
-
REAP: Reinforcement-Learning End-to-End Autonomous Parking with Gaussian Splatting Simulator for Real2Sim2Real Transfer
REAP trains an end-to-end SAC policy with behavior cloning and collision penalties inside a 3DGS Real2Sim simulator and transfers it to physical vehicles, succeeding in narrow mechanical parking slots.
-
TAIL-Safe: Task-Agnostic Safety Monitoring for Imitation Learning Policies
TAIL-Safe learns a Lipschitz Q-function from visibility, recognizability, and graspability criteria in a Gaussian Splatting twin to define an empirical safe set for IL policies and recovers unsafe actions via Nagumo-inspired gradient ascent.
-
StableIDM: Stabilizing Inverse Dynamics Model against Manipulator Truncation via Spatio-Temporal Refinement
StableIDM stabilizes inverse dynamics models under manipulator truncation by combining robot-centric masking, directional spatial feature aggregation, and temporal dynamics refinement, yielding 12.1% higher strict action accuracy on AgiBot and 9.7-17.6% gains in real-robot tasks.
-
R3D: Revisiting 3D Policy Learning
A transformer 3D encoder plus diffusion decoder architecture, with 3D-specific augmentations, outperforms prior 3D policy methods on manipulation benchmarks by improving training stability.
-
Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms
A literature survey that unifies fragmented work on attacks, defenses, evaluations, and deployment challenges for Vision-Language-Action models in robotics.
-
3D Generation for Embodied AI and Robotic Simulation: A Survey
The paper surveys 3D generation techniques for embodied AI and robotics, categorizing them into data generation, simulation environments, and sim-to-real bridging while identifying bottlenecks in physical validity and transfer.