paper-with-me

홈 › Papers

STEER: Flexible Robotic Manipulation via Dense Language Grounding

2024-11-05 · Laura Smith, Alex Irpan, Montserrat Gonzalez Arenas, Sean Kirmani, Dmitry Kalashnikov, Dhruv Shah, Ted Xiao

The complexity of the real world demands robotic systems that can intelligently adapt to unseen situations. We present STEER, a robot learning framework that bridges high-level, commonsense reasoning with precise, flexible low-level control. Our approach translates complex situational awareness into actionable low-level behavior through training language-grounded policies with dense annotation. By structuring policy training around fundamental, modular manipulation skills expressed in natural language, STEER exposes an expressive interface for humans or Vision-Language Models (VLMs) to intelligently orchestrate the robot's behavior by reasoning about the task and context. Our experiments demonstrate the skills learned via STEER can be combined to synthesize novel behaviors to adapt to new situations or perform completely new tasks without additional data collection or training.

📄 PDF Abstract BibTeX arXiv:2411.03409

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

$R^3$: Training Robots to Reason in Natural Language via Reinforcement Learning

2026-08-26 · Lehong Wu, Yuxiao Qu, Zheyuan Hu, Ivan Zhang 외 arxiv

Reasoning in language allows foundation models to spend more test-time compute on hard problems, such as those requiring decomposition, constraint tracking, and prediction of future consequences. Whether this mechanism c…

Reinforcement Learning

ReSiReg: Towards Spatially Consistent Semantics in Language-Conditioned Robotic Tasks

2026-06-17 · Simon Schwaiger, David Seyser, Alessandro Scherl, Wilfried Wöber 외 arxiv

Vision-Language Models (VLMs) enable robots to follow open-language instructions. However, dense VLM embeddings have shown to be noisy and lack spatial consistency. This is problematic for robotic applications, which req…

Trajectory Adaptation using Large Language Models

2025-04-17 · Anurag Maurya, Tashmoy Ghosh, Ravi Prakash

Adapting robot trajectories based on human instructions as per new situations is essential for achieving more intuitive and scalable human-robot interactions. This work proposes a flexible language-based framework to ada…

Robot Manipulation

MARVL: Multi-Stage Guidance for Robotic Manipulation via Vision-Language Models

2026-01-28 · Xunlan Zhou, Xuanlin Chen, Shaowei Zhang, ShengHua Wan 외 arxiv

Designing dense reward functions is pivotal for efficient robotic Reinforcement Learning (RL). However, most dense rewards rely on manual engineering, which fundamentally limits the scalability and automation of reinforc…

Reinforcement Learning

Stable Language Guidance for Vision-Language-Action Models

2026-01-07 · Zhihao Zhan, Yuhao Chen, Jiaying Zhou, Qinhan Lyu 외 arxiv

Vision-Language-Action (VLA) models have demonstrated impressive capabilities in generalized robotic control; however, they remain notoriously brittle to linguistic perturbations. We identify a critical ``modality collap…