RevoSim: Scalable Multimodal Tactile Simulation for Dexterous Manipulation
RevoSim: Scalable Multimodal Tactile Simulation for Dexterous Manipulation
This paper presents RevoSim, a high-fidelity simulation framework tailored for the BrainCo Revo3 robotic hand. The system models 285 piezoresistive taxels and five visuotactile fingertips to generate synchronized pressure, depth, RGB, and marker-displacement observations. Running on a single RTX 5090 GPU, it supports up to 4,096 parallel environments using a depth-conditioned marker-displacement configuration. The authors demonstrate the ability to train in-hand manipulation and grasping policies entirely within simulation, laying the groundwork for future sim-to-real transfer applications.
The authors introduce RevoSim, a simulation environment specifically designed for the BrainCo Revo3 robotic hand, capable of generating synchronized multimodal tactile and visual data including pressure, depth, RGB, and marker-displacement observations across up to 4,096 parallel environments on a single RTX 5090 GPU.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Environment
- SimulationOpen source S3
Reported numbers
parallel environments
≤4,096
View original evidence
ts up to 4,096 parallel environments. We train in-hand manipulation and grasping policies entirely in simulation, establishing a foundation for future sim-to-real transfer. Project page: https://braincotech.github.io/RevoSim-web/.
Open source S3
Dataset details reported by the source
- Modalities
- pressure Open source S2depth Open source S2RGB Open source S2marker-displacement Open source S2
- Tasks
- in-hand manipulation Open source S3grasping Open source S3
- Embodiments
- BrainCo Revo3 hand Open source S2
- paper: not_reported
- weights: not_reported
- dataset: not_reported
- code: not_reported
What remains unknown
Dataset licensing and commercial-use rights are not established here.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
ts up to 4,096 parallel environments. We train in-hand manipulation and grasping policies entirely in simulation, establishing a foundation for future sim-to-real transfer. Project page: https://braincotech.github.io/RevoSim-web/.
Open source S3
arXiv:2611.08939v1 Announce Type: new Abstract: We present RevoSim, a scalable and high-fidelity multimodal tactile simulator for the BrainCo Revo3 hand that jointly models 285 piezoresistive taxels and five visuotactile fingertips. RevoSim efficiently generates synchronized pressure, depth, RGB, and marker-displacement observations; on a single RTX 5090, its depth-conditioned marker-displacement configuration suppor
Open source S2
Implications for data suppliers
RoboSignal interpretation and collection questions, not statements of buyer demand.
- Confirm the required data type and collection setting with the buyer; this source does not establish a complete collection specification.
- Compare the reported units and scope before using these quantities in a budget. Recording hours, sensor-hours and trajectories are different measures.
- Check the exact dataset version, license, modalities and task coverage against the intended use.
- Validate demand and acceptance criteria with a buyer before scaling. Publication, popularity and a research result do not establish a purchase commitment.
Source：arXiv Robotics — research abstracts · arxiv.org