arXiv AI
Jun 16
MimicIK: Real-Time Generative Inverse Kinematics from Teleoperation with FK Consistency
arXiv:2606. 15148v1 Announce Type: cross Abstract: Inverse kinematics (IK) remains a critical bottleneck for real-time robot manipulation.
MorphIK: Morphology-Conditioned Neural Inverse Kinematics for Unknown Robots
MorphIK is a flow‑matching neural model that learns inverse kinematics for revolute‑joint kinematic chains it has never seen during training. Using a transformer to encode a robot’s morphology and target pose, the model generates pose solutions from noise and can be fine‑tuned with optimization to achieve sub‑centimeter accuracy. It also efficiently samples the robot’s null space, producing diverse configurations for the same pose.
Related stories
arXiv Machine Learning
Jun 9
RAM: Reachability Across Morphologies
arXiv:2606. 09108v1 Announce Type: cross Abstract: Many stages of the robotic lifecycle, from morphology synthesis to operation, rely fundamentally on the reachable workspace.
arXiv AI
Jul 17
ConFlow: Constraints-Guided Learning with Flow Matching for Motion Generation
arXiv:2607. 14424v1 Announce Type: cross Abstract: In recent years Flow Matching has become a prominent method for generative modeling robot motion generation.
arXiv Machine Learning
Jun 17
Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models
arXiv:2606. 17846v1 Announce Type: cross Abstract: Foundation models in language and multimodality achieve strong generalization by aligning heterogeneous data under a unified formulation and training at scale.
arXiv AI
Aug 18
Flow Motion Policy: Manipulator Motion Planning with Flow Matching Models
arXiv:2604. 07084v2 Announce Type: replace-cross Abstract: Open-loop end-to-end neural motion planners have recently been proposed to improve motion planning for robotic manipulators.
arXiv AI
Jul 9
Shared Modular Recurrence in Contextual MDPs for Universal Morphology Control
arXiv:2506. 08630v3 Announce Type: replace Abstract: A universal controller for any robot morphology would greatly improve computational and data efficiency.
arXiv Machine Learning
Aug 31
FlowCorrect: Efficient Interactive Correction of Generative Flow Policies for Robotic Manipulation
FlowCorrect is a modular interactive imitation learning method that allows real‑time adaptation of generative flow‑matching manipulation policies using sparse, relative human corrections. During task execution, a human provides brief corrective pose nudges through a lightweight VR interface, and FlowCorrect locally adapts the policy without retraining the backbone, maintaining performance on previously learned scenarios. Experiments on a real‑world robot across four tabletop tasks show that, with a low correction budget, FlowCorrect achieves an 80% success rate on previously failed cases while preserving performance on solved scenarios.
arXiv Computer Vision
Sep 25
BeyondRetarget: Learning Executable Humanoid Motions Directly from Monocular Video
BeyondRetarget is an end‑to‑end framework that learns to generate executable humanoid robot motions directly from monocular RGB videos, bypassing the need for an explicit human motion representation. By learning robot‑oriented implicit representations and incorporating a contact‑aware motion optimization mechanism, the method captures cross‑morphology motion structures and improves temporal consistency and physical plausibility. Experiments demonstrate that BeyondRetarget achieves higher execution success rates, lower latency, and greater accuracy and robustness in both simulation and real humanoid robots.
arXiv AI
Jul 1
A Scalable Whole-body Motion Transfer via Implicit Kinodynamic Motion Retargeting
arXiv:2509. 15443v2 Announce Type: replace-cross Abstract: Human-to-humanoid imitation learning presents a promising pathway to address the severe data scarcity bottleneck in robotics by utilizing abundant, large-scale human motion collections.
arXiv AI
Sep 24
Distillation for Efficient Multitask Manipulation Policies via Conditional Flow Matching
The paper proposes a method to train efficient multi‑task manipulation policies by distilling knowledge from single‑task Conditional Flow Matching (CFM) experts. Instead of training separate models for each task, the authors transfer the experts’ learned velocity fields into a shared policy, combining this distillation signal with the original CFM objective. Experiments on RLBench demonstrate that this approach improves multi‑task performance while keeping the model size fixed, avoiding the need for larger capacity or performance drops seen with naive concatenated training.
arXiv AI
Sep 4
BRIDGE: An Open-Source Humanoid Platform via Morphology-Control Co-Design for Physical AI
The paper introduces BRIDGE, an open‑source 88 cm tall humanoid robot designed through a data‑driven morphology‑control co‑design framework that optimizes the robot’s body shape for human‑like movement. A new metric combining kinematic retargeting fidelity and dynamic tracking performance is proposed to evaluate morphological fidelity, and the framework achieves state‑of‑the‑art results compared to existing humanoids such as Bumi, K1, and Toddlerbot. The resulting platform, released with its control policy and supporting materials, demonstrates superior fidelity in capturing human motion, robust balance, and highly dynamic maneuvers.
arXiv Computer Vision
Sep 15
MoCapAnything V2: End-to-End Motion Capture for Arbitrary Skeletons
arXiv:2604.28130v4 Announce Type: replace Abstract: Recent methods for arbitrary-skeleton motion capture from monocular video follow a factorized pipeline, where a Video-to-Pose network predicts join...