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.
Learning robotic manipulation policies from point clouds with conditional flow matching.arXiv preprint arXiv:2409.07343
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 7verdicts
UNVERDICTED 7roles
background 1polarities
background 1representative citing papers
KPGrasp is a scalable Transformer flow-matching model using 3D hand keypoints that achieves 76.3% success on Dexonomy (47.4% improvement) and best average on DexGrasp Anything without contact losses or test-time refinement.
IDP generates one-step robot actions by adaptively weighting a scalar potential objective using conditional expert geometry derived from local variations of observation-similar expert actions, combined with expert-proximal terminal evaluation.
A vision-guided hybrid rigid-soft manipulator achieves consistent sub-2cm reaching in unseen cluttered environments via shape-aware planning and learning control without environment-specific retraining.
An invertible adapter for flow matching enables one-step high-dimensional action generation in robotic manipulation, cutting inference time roughly in half while preserving performance.
Trajectory consistency training, smoothness regularization, and higher-order integration for flow matching policies deliver 60-70% success on long-horizon real-robot tasks where baselines achieve 0%.
Framework generates force-informed sim data from one demo to train compliant visuomotor flow matching policies, showing reliable contact on real-robot block flipping and bi-manual tasks.
citing papers explorer
-
RoboFlow4D: A Lightweight Flow World Model Toward Real-Time Flow-Guided Robotic Manipulation
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.
-
KPGrasp: Scalable Keypoint Flow Matching for Dexterous Grasp Generation
KPGrasp is a scalable Transformer flow-matching model using 3D hand keypoints that achieves 76.3% success on Dexonomy (47.4% improvement) and best average on DexGrasp Anything without contact losses or test-time refinement.
-
Implicit Drifting Policy: One-Step Action Generation via Conditional Expert Geometry
IDP generates one-step robot actions by adaptively weighting a scalar potential objective using conditional expert geometry derived from local variations of observation-similar expert actions, combined with expert-proximal terminal evaluation.
-
HyReach: Vision-Guided Hybrid Manipulator Reaching in Unseen Cluttered Environments
A vision-guided hybrid rigid-soft manipulator achieves consistent sub-2cm reaching in unseen cluttered environments via shape-aware planning and learning control without environment-specific retraining.
-
Invertible Neural Network Adapter for One-Step Flow Matching in Robot Manipulation
An invertible adapter for flow matching enables one-step high-dimensional action generation in robotic manipulation, cutting inference time roughly in half while preserving performance.
-
Trajectory-Consistent Flow Matching for Robust Visuomotor Policy Learning
Trajectory consistency training, smoothness regularization, and higher-order integration for flow matching policies deliver 60-70% success on long-horizon real-robot tasks where baselines achieve 0%.
-
Flow with the Force Field: Learning 3D Compliant Flow Matching Policies from Force and Demonstration-Guided Simulation Data
Framework generates force-informed sim data from one demo to train compliant visuomotor flow matching policies, showing reliable contact on real-robot block flipping and bi-manual tasks.