aiqbench analysis
MuseVLA advances robotic manipulation by introducing an adaptive framework that dynamically selects and fuses non-visual sensors like thermal, audio, and radar inputs alongside standard vision data. By decoupling sensor processing from the core model backbone and utilizing a synthetic data pipeline to augment training sets, this approach significantly improves success rates on dexterous tasks without requiring expensive multisensory datasets for every new modality. This work represents a meaningful step toward more robust AI agents capable of perceiving physical properties that cameras alone cannot capture.
MuseVLA: An Adaptive Multimodal Sensing Vision-Language-Action Model for Robotic Manipulation
arXiv:2606.17598v1 Announce Type: new Abstract: Humans naturally leverage diverse sensing modalities to interact with the physical world, while most Vision-Language-Action (VLA) models for robotics rely solely on RGB observations. This limits their ability to perceive physical properties that are difficult or impossible to infer from RGB cameras, such as temperature, sound, or radar response. We present MuseVLA, an adaptive multimodal sensing VLA model that integrates novel sensors as on-demand tools for robotic manipulation. Given a task instruction and visual context, MuseVLA first generates a sensor token and target description that select the sensing modality to invoke and what to attend to, analogous to a tool call with arguments. It then converts the selected sensor measurement into a grounded sensor image, a unified intermediate representation that encodes heterogeneous readings for multimodal fusion and action generation. This design decouples sensor-specific processing from the VLA backbone, enabling efficient integration of diverse modalities. To reduce the need for expensive multisensory robot datasets, we further introduce a data synthesis pipeline that augments existing RGB video datasets with grounded sensor images, enabling generalization to unseen sensor-guided tasks. We evaluate MuseVLA on a real-world robot across challenging dexterous hand manipulation tasks that require multimodal sensing inputs, including temperature-guided pick-and-place, audio-driven object search, and radar-assisted hidden object retrieval. MuseVLA achieves 80.6% success rate on average, outperforming RGB-only and multisensory VLA baselines significantly, and exhibits strong zero-shot capabilities on unseen tasks.
Abstract:Humans naturally leverage diverse sensing modalities to interact with the physical world, while most Vision-Language-Action (VLA) models for robotics rely solely on RGB observations. This limits their ability to perceive physical properties that are difficult or impossible to infer from RGB cameras, such as temperature, sound, or radar response. We present MuseVLA, an adaptive multimodal sensing VLA model that integrates novel sensors as on-demand tools for robotic manipulation. Given a task instruction and visual context, MuseVLA first generates a sensor token and target description that select the sensing modality to invoke and what to attend to, analogous to a tool call with arguments. It then converts the selected sensor measurement into a grounded sensor image, a unified intermediate representation that encodes heterogeneous readings for multimodal fusion and action generation. This design decouples sensor-specific processing from the VLA backbone, enabling efficient integration of diverse modalities. To reduce the need for expensive multisensory robot datasets, we further introduce a data synthesis pipeline that augments existing RGB video datasets with grounded sensor images, enabling generalization to unseen sensor-guided tasks. We evaluate MuseVLA on a real-world robot across challenging dexterous hand manipulation tasks that require multimodal sensing inputs, including temperature-guided pick-and-place, audio-driven object search, and radar-assisted hidden object retrieval. MuseVLA achieves 80.6% success rate on average, outperforming RGB-only and multisensory VLA baselines significantly, and exhibits strong zero-shot capabilities on unseen tasks.
Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
arXiv:2606.17598 [cs.RO]
(or arXiv:2606.17598v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.17598 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 326 words
Related coverage
NVIDIA GTC Taipei at COMPUTEX: Live Updates on What’s Next in AI
NVIDIA · May 21, 2026
DeCAL: Towards Physically-Grounded Dexterous Vision-Language-Action Models via Contact-Aware Latent Co-Imagination
arXiv · Sep 9, 2026
The Machines that Make the Machines
NVIDIA · Oct 7, 2026
Runway’s WorldPrompt and the Engineering of Real-Time Worlds
Latent Space · Sep 25, 2026