From a722e1e794018e37cef832288b9c884a601e09df Mon Sep 17 00:00:00 2001 From: Zac Ravichandran Date: Wed, 2 Apr 2025 10:53:20 -0400 Subject: [PATCH 1/2] Update README.md Add SPINE and RoboPAIR w/ paper and website --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index a28566a..32a5f0f 100755 --- a/README.md +++ b/README.md @@ -34,6 +34,7 @@ If you find this repository useful, please consider [citing](#citation) and STAR --- ## Reasoning +* **SPINE**: "SPINE: Online Semantic Planning for Missions with Incomplete Natural Language Specifications in Unstructured Environments", *International Conference on Robotics and Automation (ICRA), May 2025*. [[Paper](https://arxiv.org/abs/2410.03035)] [[Website](https://zacravichandran.github.io/SPINE/)] * **ELLMER**: "Embodied large language models enable robots to complete long-horizon tasks in unpredictable settings", *Nature Machine Intelligence, Mar 2025*. [[Paper](https://www.nature.com/articles/s42256-025-01005-x)] [[Website](https://www.nature.com/articles/s42256-025-01005-x)] * **AHA**: "AHA: A Vision-Language-Model for Detecting and Reasoning over Failures in Robotic Manipulation", *arXiv, Oct 2024*. [[Paper](https://arxiv.org/abs/2410.00371)] [[Website](https://aha-vlm.github.io/)] * **ReKep**: "ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation", *arXiv, Sep 2024*. [[Paper](https://arxiv.org/abs/2409.01652)] [[Code](https://github.com/huangwl18/ReKep)] [[Website](https://rekep-robot.github.io)] @@ -194,6 +195,7 @@ If you find this repository useful, please consider [citing](#citation) and STAR --- ## Safety, Risks, Red Teaming, and Adversarial Testing +* **RoboPAIR**: "Jailbreaking LLM-Controlled Robots", *International Conference on Robotics and Automation (ICRA) May 2025*. [[Paper](https://arxiv.org/abs/2410.13691)] [Website](https://robopair.org/)] * **Safe LLM-Controlled Robots with Formal Guarantees via Reachability Analysis** *arXiv, Mar 2025* [[arXiv](https://arxiv.org/abs/2503.03911)] [[Code](https://github.com/TUM-CPS-HN/SafeLLMRA)] * **LLM-Driven Robots Risk Enacting Discrimination, Violence, and Unlawful Actions**: *arXiv, Jun 2024*. [[Paper](https://arxiv.org/abs/2406.08824)] * **Highlighting the Safety Concerns of Deploying LLMs/VLMs in Robotics**: *arXiv, Feb 2024*. [[Paper](https://arxiv.org/abs/2402.10340)] From c16563c555b6f62184b1fd4bb4e30ddced2cae1a Mon Sep 17 00:00:00 2001 From: Zac Ravichandran Date: Thu, 3 Apr 2025 15:36:57 -0400 Subject: [PATCH 2/2] Add RoboGuard --- README.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 32a5f0f..6571a7f 100755 --- a/README.md +++ b/README.md @@ -195,7 +195,8 @@ If you find this repository useful, please consider [citing](#citation) and STAR --- ## Safety, Risks, Red Teaming, and Adversarial Testing -* **RoboPAIR**: "Jailbreaking LLM-Controlled Robots", *International Conference on Robotics and Automation (ICRA) May 2025*. [[Paper](https://arxiv.org/abs/2410.13691)] [Website](https://robopair.org/)] +* **RoboPAIR**: "Jailbreaking LLM-Controlled Robots", *International Conference on Robotics and Automation (ICRA) May 2025*. [[Paper](https://arxiv.org/abs/2410.13691)] [[Website](https://robopair.org/)] +* **RoboGuard**: "Safety Guardrails for LLM-Enabled Robots", *arXiv, April 2025*. [[Paper](https://arxiv.org/abs/2503.07885)] [[Website](https://robo-guard.github.io/)] * **Safe LLM-Controlled Robots with Formal Guarantees via Reachability Analysis** *arXiv, Mar 2025* [[arXiv](https://arxiv.org/abs/2503.03911)] [[Code](https://github.com/TUM-CPS-HN/SafeLLMRA)] * **LLM-Driven Robots Risk Enacting Discrimination, Violence, and Unlawful Actions**: *arXiv, Jun 2024*. [[Paper](https://arxiv.org/abs/2406.08824)] * **Highlighting the Safety Concerns of Deploying LLMs/VLMs in Robotics**: *arXiv, Feb 2024*. [[Paper](https://arxiv.org/abs/2402.10340)]