Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[IROS'21] SurRoL: An Open-source Reinforcement Learning Centered and dVRK Compatible Platform for Surgical Robot Learning
| Date | Stars |
|---|---|
| 2026-07-25 | 265 |
| 2026-07-28 | 265 |
| 2026-07-30 | 265 |
| 2026-07-31 | 265 |
| 2026-08-04 | 266 |
| 2026-08-06 | 267 |
Today
+1 stars today
This week
+2 stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.76%/day
## Surgical embodied intelligence for generalized task autonomy in laparoscopic robot-assisted surgery
### [[Project Website]](https://med-air.github.io/SurRoL/)
**Science Robotics'25**: Surgical embodied intelligence for generalized task autonomy in laparoscopic robot-assisted surgery [[Paper](https://www.science.org/doi/10.1126/scirobotics.adt3093)] [[Code](https://github.com/med-air/SurRoL/tree/SR-VPPV)]
**arXiv'24**: Efficient Physically-based Simulation of Soft Bodies in Embodied Environment for Surgical Robot [[Paper](https://arxiv.org/abs/2402.01181)] [[Code](https://github.com/med-air/SurRoL/tree/Dev)]
**ICRA'24**: Multi-objective Cross-task Learning via Goal-conditioned GPT-based Decision Transformers for Surgical Robot Task Automation [[Paper](https://arxiv.org/abs/2405.18757)] [[Code](https://github.com/med-air/SurRoL/blob/Dev/rl/README.md)]
**IROS'23**: Value-Informed Skill Chaining for Policy Learning of Long-Horizon Tasks with Surgical Robot [[Paper](https://arxiv.org/abs/2307.16503)] [[Code](https://github.com/med-air/ViSkill)]
**RA-L'23**: Human-in-the-loop Embodied Intelligence with Interactive Simulation Environment for Surgical Robot Learning [[Paper](https://arxiv.org/abs/2301.00452)] [[Code](https://github.com/med-air/SurRoL/tree/SurRoL-v2)]
**ICRA'23**: Demonstration-Guided Reinforcement Learning with Efficient Exploration for Task Automation of Surgical Robot [[Paper](https://arxiv.org/abs/2302.09772)] [[Code](https://github.com/med-air/DEX)]
**ISMR'22**: Integrating Artificial Intelligence and Augmented Reality in Robotic Surgery: An Initial dVRK Study Using a Surgical Education Scenario [[Paper](https://arxiv.org/abs/2201.00383)]
**IROS'21**: SurRoL: An Open-source RL Centered and dVRK Compatible Platform for Surgical Robot Learning [[Paper](https://arxiv.org/abs/2108.13035)] [[Code](https://github.com/med-air/SurRoL/tree/main)]
<p align="center">
<img src="README.assets/img/overview.png" width="80%" height="80%" alt="SurRoL"/>
</p>
## Features
- [dVRK](https://github.com/jhu-dvrk/sawIntuitiveResearchKit/wiki) compatible [robots](./surrol/robots).
- [OpenAI Gym](https://github.com/openai/gym) style [API](./surrol/gym) for reinforcement learning.
- Rich collection of [assets](./surrol/assets) and task environments.
- Based on [PyBullet](https://github.com/bulletphysics/bullet3) and [Taichi](https://www.taichi-lang.org/) for physics simulation.
- Allow human interaction with [Touch Haptic Device](https://www.3dsystems.com/haptics-devices/touch) and real-world [dVRK](https://github.com/jhu-dvrk/sawIntuitiveResearchKit/wiki) robots.
- Zero-shot sim-to-real transfer capabilities
**System Requirements:** Ubuntu 20.04 with Python 3.7
## Code Structure
```
|- VPPV # surgical task automation framework
|- Training # simulator training
|- data_generation # enviroment for generating the data to train perceptual regressor
|- state_regress # code for training perceptual regressor
|- policy_learning # enviroment for training the RL policy
|- Deployment # VPPV deployment in the real world
|- dVRK # code of VPPV deployment for game-based training tasks
|- Sentire # code of VPPV deployment for ex vivo and in vivo experiments
|- Benchmark # benchmark for policy learning
|- state_based # enviroment and implementation for state based methods
|- vision_based # enviroment and implementation for vision based methods
|- Haptic_guidance # enviroment and implementation for intelligent haptic guidance
|- Data_driven_scene_simulation # enviroment and implementation for data driven surgical scene simulation
```
## Detailed Usage
### VPPV
The VPPV framework consists of two main components:
#### 1. Training
- **Data Generation** (`VPPV/Training/data_generation/`)
Excerpt of 7,636 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:a0191b75fb164569, topic:simulation, readme:robotics, desc:robot learning
matched fp:a0191b75fb164569, topic:reinforcement-learning, desc:reinforcement learning, readme:reinforcement learning