Article

SymBridge: Bilateral-Symmetry-Aware Vision–Language–Action Learning with Head-Mounted Display Teleoperation for Sim2Real Transfer in Bimanual Manipulation

2026-05-27

Abstract excerpt

Vision–Language–Action (VLA) models trained on embodied demonstration data exhibit substantial performance degradation when transferred from simulation to reality. We argue that part of this gap is attributable to the implicit and incomplete encoding of geometric and bilateral symmetries in manipulation. We introduce SymBridge, a symmetry-aware framework whose acting group is the semidirect product G=Z2⋉R3⋊SO(2)z,...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 61838c33-3708-5580-8ee7-359bf00c18e7
DOI: 10.20944/preprints202605.1763.v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

SymBridge: Bilateral-Symmetry-Aware Vision–Language–Action Learning with Head-Mounted Display Teleoperation for Sim2Real Transfer in Bimanual ManipulationDOI 10.20944/preprints202605.1763.v1Read

Beyond Kinesthetic Twins: A Dematerialized Control Primitive for Zero-Shot Generalization Across Robot MorphologiesSemantic proximity Read

Vision-Language-Action and Vision Language Models for Robot Manipulation: A Comprehensive Review Towards Real-World ApplicationsSemantic proximity Read

Measuring Cross-Embodiment Transfer Without Fooling YourselfSemantic proximity Read

Multimodal Vision Language Models in Interactive and Physical EnvironmentsSemantic proximity Read

EnerVerse-AC: Envisioning Embodied Environments with Action ConditionSemantic proximity Read

Competitive, Cooperative, and Everything In-Between: The Janus Protocol for Strategy-Infused Language ModelsSemantic proximity Read

Collaborative Assembly with Dynamic Environment for Human-Robot Interaction via Multi-Modal Large Language ModelSemantic proximity Read

Physical AI: The Next Frontier in AI and Robotics to Build Truly Autonomous MachinesSemantic proximity Read

Deep kinematic inference affords efficient and scalable control of bodily movementsSemantic proximity Read

Safe Reinforcement Learning for Vision-Based Robotic Manipulation in Human-Centered EnvironmentsSemantic proximity Read

LabOS: The AI-XR Co-Scientist That Sees and Works With HumansSemantic proximity Read

Physic Grounded Vision Foundation Models for Human Computer Interaction in Embodied EnvironmentsSemantic proximity Read