Generative policies trained with human demonstrations can autonomously accomplish multimodal, long-horizon tasks. However, during inference, humans are often removed from the policy execution loop, limiting the ability to guide a pre-trained policy towards a specific sub-goal or trajectory shape among multiple predictions. Naive human intervention may inadvertently exacerbate distribution shift, leading to constraint violations or execution failures. To better align policy output with human intent without inducing out-of-distribution errors, we propose an Inference-Time Policy Steering (ITPS) framework that leverages human interactions to bias the generative sampling process, rather than fine-tuning the policy on interaction data. We evaluate ITPS across three simulated and real-world benchmarks, testing three forms of human interaction and associated alignment distance metrics. Among six sampling strategies, our proposed stochastic sampling with diffusion policy achieves the best trade-off between alignment and distribution shift. Videos are available at https://yanweiw.github.io/itps/.
Towards Deploying VLA without Fine-Tuning: Plug-and-Play Inference-Time VLA Policy Steering via Embodied Evolutionary Diffusion
Collaborative and Versatile Robots (CLOVER) Laboratory, T-Stone Robotics Institute, The Chinese University of Hong Kong, Hong Kong(协作与多功能机器人实验室,T-Stone机器人研究所,香港中文大学,香港);Φ \Phi -Institute for Physical Human Intelligence(物理人机智能研究所);Center for Embodied Artificial Intelligence and Computer Vision, Shenzhen Loop Area Institute, Shenzhen, China(具身人工智能与计算机视觉中心,深圳环园研究院,深圳,中国);Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genoa, Italy(先进机器人系,意大利理工学院,热那亚,意大利)
What do VLM-Based Vision-Language Navigation Models Rely on: Interpreting and Steering Policy Behavior
University of Technology Nuremberg(纽伦堡工业大学);ETH Zürich(苏黎世联邦理工学院);Inria, Ecole Normale Supérieure, CNRS, PSL Research University(法国国家信息与自动化研究所,巴黎高等师范学校,法国国家科学研究中心,巴黎文理研究大学)
School of Computing and Data Science, The University of Hong Kong(香港大学计算与数据科学学院);Shanghai Qizhi Institute(上海启智研究院);Shanghai Jiao Tong University(上海交通大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Institute for Interdisciplinary Information Sciences, Tsinghua University(清华大学交叉信息研究院)
Multi-Modal Decentralized Reinforcement Learning for Modular Reconfigurable Lunar Robots
Space Robotics Lab. (SRL) in Department of Aerospace Engineering, Graduate School of Engineering, Tohoku University(太空机器人实验室(SRL)位于东东北大学航空航天工程系研究生院);Politecnico di Milano(米兰理工大学)
VLS: Steering Pretrained Robot Policies via Vision-Language Models
University of Washington(华盛顿大学);University of Oxford(牛津大学);National University of Singapore(新加坡国立大学);Allen Institute for Artificial Intelligence(人工智能研究院)