HUG trains a flow-matching model on a new 1M-frame egocentric human grasp dataset to generate retargetable grasps from single RGB-D images, beating baselines by 23-34% on a new 90-object benchmark.
hub
Bunny-visionpro: Real-time bimanual dexterous teleoperation for imitation learning
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
abstract
Teleoperation is a crucial tool for collecting human demonstrations, but controlling robots with bimanual dexterous hands remains a challenge. Existing teleoperation systems struggle to handle the complexity of coordinating two hands for intricate manipulations. We introduce Bunny-VisionPro, a real-time bimanual dexterous teleoperation system that leverages a VR headset. Unlike previous vision-based teleoperation systems, we design novel low-cost devices to provide haptic feedback to the operator, enhancing immersion. Our system prioritizes safety by incorporating collision and singularity avoidance while maintaining real-time performance through innovative designs. Bunny-VisionPro outperforms prior systems on a standard task suite, achieving higher success rates and reduced task completion times. Moreover, the high-quality teleoperation demonstrations improve downstream imitation learning performance, leading to better generalizability. Notably, Bunny-VisionPro enables imitation learning with challenging multi-stage, long-horizon dexterous manipulation tasks, which have rarely been addressed in previous work. Our system's ability to handle bimanual manipulations while prioritizing safety and real-time performance makes it a powerful tool for advancing dexterous manipulation and imitation learning.
hub tools
fields
cs.RO 14representative citing papers
A hardware-free dual-camera capture framework with ChArUco spatial unification and receding-horizon state alignment enables decoupled SE(3) manipulation and SE(2) base trajectories for diffusion policies, yielding 83.8% average success on four long-horizon household tasks.
Dexora is the first open-source VLA system for dual-arm dual-hand high-DoF manipulation, trained on 100K simulated and 10K real teleoperated trajectories with a discriminator-weighted diffusion policy, achieving 66.7% dexterous success versus 51.7% for baselines.
Mana framework achieves zero-shot sim-to-real transfer for grasping and in-hand manipulation of four articulated tools using a coarse-to-fine animation-inspired pipeline.
A wearable interface with a shared dexterous hand module enables retargeting-free teleoperation and matched data collection, yielding policies with 88.75% average success across eight real-robot tasks that generalize and transfer across embodiments.
IGen generates realistic visuomotor training data including actions and temporally coherent visuals from unstructured open-world images via 3D reconstruction and VLM reasoning.
R2RGen introduces a simulator-free three-stage pipeline that parses, augments, and post-processes real pointcloud observation-action pairs to improve spatial generalization in robotic manipulation policies.
EgoVLA pretrains VLA models on egocentric human videos, retargets predicted actions to robots via IK, and fine-tunes on few robot demos to improve bimanual manipulation performance on a new simulation benchmark.
J-PARSE modifies the Jacobian via aspect-ratio thresholding and directional projection to enable stable first-order inverse kinematic velocity control through kinematic singularities in serial manipulators.
AhaRobot delivers 0.7 mm repeatability on a $1000 bimanual platform using dual-motor compensation and a novel 26-faced marker handle that cuts tracking error 80% versus a 6-faced baseline.
Sampling-Based Retargeter (SBR) delivers lower-jitter real-time kinematic hand retargeting and higher task success with less operator fatigue than gradient-based baselines in an 18-person study.
DexTeleop-0 adds a tactile-driven adaptation loop to bimanual dexterous teleoperation that estimates contact points and applies localized force-compliant corrections via operational-space Jacobian updates.
VR-DAgger is a VR-centered human-in-the-loop framework that applies MC dropout uncertainty to select and correct failure segments in diffusion policy rollouts, yielding up to 23 percentage point gains over behavioral cloning and 40% lower per-sample collection time on three dexterous tasks.
An egocentric vision pipeline with MediaPipe hand tracking and damped-least-squares IK achieves 86.7% success on structured pick-and-place for the SO-ARM101 robot but falls to 9.3% in real-world environments with occlusions.
citing papers explorer
-
Human Universal Grasping
HUG trains a flow-matching model on a new 1M-frame egocentric human grasp dataset to generate retargetable grasps from single RGB-D images, beating baselines by 23-34% on a new 90-object benchmark.
-
Mobile UMI: Cross-View Diffusion Policy with Decoupled Kinematics for Mobile Manipulation
A hardware-free dual-camera capture framework with ChArUco spatial unification and receding-horizon state alignment enables decoupled SE(3) manipulation and SE(2) base trajectories for diffusion policies, yielding 83.8% average success on four long-horizon household tasks.
-
Dexora: Open-source VLA for High-DoF Bimanual Dexterity
Dexora is the first open-source VLA system for dual-arm dual-hand high-DoF manipulation, trained on 100K simulated and 10K real teleoperated trajectories with a discriminator-weighted diffusion policy, achieving 66.7% dexterous success versus 51.7% for baselines.
-
Mana: Dexterous Manipulation of Articulated Tools
Mana framework achieves zero-shot sim-to-real transfer for grasping and in-hand manipulation of four articulated tools using a coarse-to-fine animation-inspired pipeline.
-
RealDexUMI: A Wearable Universal Manipulation Interface for Dexterous Robot Learning
A wearable interface with a shared dexterous hand module enables retargeting-free teleoperation and matched data collection, yielding policies with 88.75% average success across eight real-robot tasks that generalize and transfer across embodiments.
-
IGen: Scalable Data Generation for Robot Learning from Open-World Images
IGen generates realistic visuomotor training data including actions and temporally coherent visuals from unstructured open-world images via 3D reconstruction and VLM reasoning.
-
R2RGEN: Real-to-Real 3D Data Generation for Spatially Generalized Manipulation
R2RGen introduces a simulator-free three-stage pipeline that parses, augments, and post-processes real pointcloud observation-action pairs to improve spatial generalization in robotic manipulation policies.
-
EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos
EgoVLA pretrains VLA models on egocentric human videos, retargets predicted actions to robots via IK, and fine-tunes on few robot demos to improve bimanual manipulation performance on a new simulation benchmark.
-
J-PARSE: Jacobian-based Projection Algorithm for Resolving Singularities Effectively in Inverse Kinematic Control of Serial Manipulators
J-PARSE modifies the Jacobian via aspect-ratio thresholding and directional projection to enable stable first-order inverse kinematic velocity control through kinematic singularities in serial manipulators.
-
AhaRobot: A Low-Cost Open-Source Bimanual Mobile Manipulator for Embodied AI
AhaRobot delivers 0.7 mm repeatability on a $1000 bimanual platform using dual-motor compensation and a novel 26-faced marker handle that cuts tracking error 80% versus a 6-faced baseline.
-
Smooth Operator: A Real-Time Sampling-Based Algorithm for Kinematic Hand Retargeting
Sampling-Based Retargeter (SBR) delivers lower-jitter real-time kinematic hand retargeting and higher task success with less operator fatigue than gradient-based baselines in an 18-person study.
-
DexTeleop-0: Force-Aware Bimanual Dexterous Teleoperation with Ego-Centric Perception towards Shared Autonomy
DexTeleop-0 adds a tactile-driven adaptation loop to bimanual dexterous teleoperation that estimates contact points and applies localized force-compliant corrections via operational-space Jacobian updates.
-
VR-DAgger: Immersive VR for Dexterous Data Collection and Uncertainty-Guided On-Policy Correction
VR-DAgger is a VR-centered human-in-the-loop framework that applies MC dropout uncertainty to select and correct failure segments in diffusion policy rollouts, yielding up to 23 percentage point gains over behavioral cloning and 40% lower per-sample collection time on three dexterous tasks.
-
Vision-Based Hand Shadowing for Robotic Manipulation via Inverse Kinematics
An egocentric vision pipeline with MediaPipe hand tracking and damped-least-squares IK achieves 86.7% success on structured pick-and-place for the SO-ARM101 robot but falls to 9.3% in real-world environments with occlusions.